up

Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>
opencode: add Cog memory skill
2026-02-09 17:31:21 +00:00 · 2026-02-09 17:28:35 +00:00 · 2026-02-09 17:18:36 +00:00 · 2026-02-09 17:16:58 +00:00 · 2026-02-09 17:15:10 +00:00 · 2026-02-09 15:00:24 +00:00
63 changed files with 5531 additions and 617 deletions
--- a/.sops.yaml
+++ b/.sops.yaml
@@ -1,7 +1,6 @@
 keys:
  - &host_tahani age1njjegjjdqzfnrr54f536yl4lduqgna3wuv7ef6vtl9jw5cju0grsgy62tm
  - &host_michael age187jl7e4k9n4guygkmpuqzeh0wenefwrfkpvuyhvwjrjwxqpzassqq3x67j
-  - &host_mindy age1dqt3znmzcgghsjjzzax0pf0eyu95h0p7kaf5v988ysjv7fl7lumsatl048
  - &host_jason age1ez6j3r5wdp0tjy7n5qzv5vfakdc2nh2zeu388zu7a80l0thv052syxq5e2
  - &host_chidi age1tlymdmaukhwupzrhszspp26lgd8s64rw4vu9lwc7gsgrjm78095s9fe9l3
 creation_rules:
@@ -10,6 +9,5 @@ creation_rules:
      - age:
        - *host_tahani
        - *host_michael
-        - *host_mindy
        - *host_jason
        - *host_chidi
--- a/.stignore
+++ b/.stignore
@@ -1,2 +0,0 @@
-.jj/
-.git/
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,14 +1,11 @@
 # AGENTS.md

-## ⚠️ VERSION CONTROL: JUJUTSU (jj) ONLY
-**NEVER run git commands.** This repo uses Jujutsu (`jj`). Use `jj status`, `jj diff`, `jj commit`, etc.
-
 ## Build Commands

 ### Local Development
 ```bash
 nix run .#build               # Build current host config
-nix run .#build -- <hostname> # Build specific host (chidi, jason, michael, mindy, tahani)
+nix run .#build -- <hostname> # Build specific host (chidi, jason, michael, tahani)
 nix run .#apply               # Build and apply locally (darwin-rebuild/nixos-rebuild switch)
 nix flake check               # Validate flake
 ```
@@ -16,7 +13,7 @@ nix flake check               # Validate flake
 ### Remote Deployment (NixOS only)
 ```bash
 colmena build                 # Build all NixOS hosts
-colmena apply --on <host>     # Deploy to specific NixOS host (michael, mindy, tahani)
+colmena apply --on <host>     # Deploy to specific NixOS host (michael, tahani)
 colmena apply                 # Deploy to all NixOS hosts
 ```

--- a/flake.lock
+++ b/flake.lock
@@ -6,7 +6,7 @@
          "llm-agents",
          "nixpkgs"
        ],
-        "systems": "systems_2"
+        "systems": "systems"
      },
      "locked": {
        "lastModified": 1769353768,
@@ -85,11 +85,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1768764703,
-        "narHash": "sha256-5ulSDyOG1U+1sJhkJHYsUOWEsmtLl97O0NTVMvgIVyc=",
+        "lastModified": 1770184146,
+        "narHash": "sha256-DsqnN6LvXmohTRaal7tVZO/AKBuZ02kPBiZKSU4qa/k=",
        "owner": "LnL7",
        "repo": "nix-darwin",
-        "rev": "0fc4e7ac670a0ed874abacf73c4b072a6a58064b",
+        "rev": "0d7874ef7e3ba02d58bebb871e6e29da36fa1b37",
        "type": "github"
      },
      "original": {
@@ -183,11 +183,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1768135262,
-        "narHash": "sha256-PVvu7OqHBGWN16zSi6tEmPwwHQ4rLPU9Plvs8/1TUBY=",
+        "lastModified": 1769996383,
+        "narHash": "sha256-AnYjnFWgS49RlqX7LrC4uA+sCCDBj0Ry/WOJ5XWAsa0=",
        "owner": "hercules-ci",
        "repo": "flake-parts",
-        "rev": "80daad04eddbbf5a4d883996a73f3f542fa437ac",
+        "rev": "57928607ea566b5db3ad13af0e57e921e6b12381",
        "type": "github"
      },
      "original": {
@@ -213,7 +213,7 @@
    },
    "flake-utils_2": {
      "inputs": {
-        "systems": "systems"
+        "systems": "systems_2"
      },
      "locked": {
        "lastModified": 1731533236,
@@ -231,25 +231,7 @@
    },
    "flake-utils_3": {
      "inputs": {
-        "systems": "systems_3"
-      },
-      "locked": {
-        "lastModified": 1731533236,
-        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
-    "flake-utils_4": {
-      "inputs": {
-        "systems": "systems_5"
+        "systems": "systems_4"
      },
      "locked": {
        "lastModified": 1731533236,
@@ -272,11 +254,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1769978395,
-        "narHash": "sha256-gj1yP3spUb1vGtaF5qPhshd2j0cg4xf51pklDsIm19Q=",
+        "lastModified": 1770586272,
+        "narHash": "sha256-Ucci8mu8QfxwzyfER2DQDbvW9t1BnTUJhBmY7ybralo=",
        "owner": "nix-community",
        "repo": "home-manager",
-        "rev": "984708c34d3495a518e6ab6b8633469bbca2f77a",
+        "rev": "b1f916ba052341edc1f80d4b2399f1092a4873ca",
        "type": "github"
      },
      "original": {
@@ -288,11 +270,11 @@
    "homebrew-cask": {
      "flake": false,
      "locked": {
-        "lastModified": 1770030613,
-        "narHash": "sha256-L6vhgGvvJAh6Rka7kLlaTgNvAEtUcN0Kdo3mw982JMg=",
+        "lastModified": 1770623639,
+        "narHash": "sha256-LNLzbnhp5IEizTMMapF2FtLVD21sFzBfVgXcwNz7fKU=",
        "owner": "homebrew",
        "repo": "homebrew-cask",
-        "rev": "d26a4c23bffaf74e850e1707e2c7b3da9a3f8ff6",
+        "rev": "c3bb7aedf0881187cbeb55ad2873240feba21603",
        "type": "github"
      },
      "original": {
@@ -304,11 +286,11 @@
    "homebrew-core": {
      "flake": false,
      "locked": {
-        "lastModified": 1770034814,
-        "narHash": "sha256-1ny8x58/AuTUVXdaIO2rMtXjR2lxJji4xOsMcWuRpn8=",
+        "lastModified": 1770627860,
+        "narHash": "sha256-ihOndNFECGtZhkrtynP8nDJ8fbSxhNd2zWcq3CLDnQA=",
        "owner": "homebrew",
        "repo": "homebrew-core",
-        "rev": "d29c1ee0e447466c3e29a2acde2a1a31bca2dadd",
+        "rev": "a12e59e6d202fc64aee013f8574c043a4c00a271",
        "type": "github"
      },
      "original": {
@@ -317,53 +299,18 @@
        "type": "github"
      }
    },
-    "jj-ryu": {
-      "flake": false,
-      "locked": {
-        "lastModified": 1769803702,
-        "narHash": "sha256-gE4lvqyC2LRAWNDUGePklORWjyEofs/dHLHVBAub424=",
-        "owner": "dmmulroy",
-        "repo": "jj-ryu",
-        "rev": "aade8d5acb9c2411828f38049a9b42a4b14529b8",
-        "type": "github"
-      },
-      "original": {
-        "owner": "dmmulroy",
-        "repo": "jj-ryu",
-        "type": "github"
-      }
-    },
-    "jj-starship": {
-      "inputs": {
-        "flake-utils": "flake-utils_2",
-        "nixpkgs": "nixpkgs"
-      },
-      "locked": {
-        "lastModified": 1769370163,
-        "narHash": "sha256-YfcFlJsPCRfqhN+3JUWE77c+eHIp5RAu2rq/JhSxCec=",
-        "owner": "dmmulroy",
-        "repo": "jj-starship",
-        "rev": "76cf00619b0cce5bd08a1b9a49b310ed928794d5",
-        "type": "github"
-      },
-      "original": {
-        "owner": "dmmulroy",
-        "repo": "jj-starship",
-        "type": "github"
-      }
-    },
    "llm-agents": {
      "inputs": {
        "blueprint": "blueprint",
-        "nixpkgs": "nixpkgs_2",
+        "nixpkgs": "nixpkgs",
        "treefmt-nix": "treefmt-nix"
      },
      "locked": {
-        "lastModified": 1770003467,
-        "narHash": "sha256-1JYYf58PMCs2gFy3eO1TM5UcYbTevqnl80SQNNIfJS0=",
+        "lastModified": 1770616720,
+        "narHash": "sha256-NY7yFg3ZG0fzseC4SK/TQjgaODczuvCDtJZNsBmN2QU=",
        "owner": "numtide",
        "repo": "llm-agents.nix",
-        "rev": "a8387ff56912f1a6cbc8fdf4c6de4af55530a5bf",
+        "rev": "09019dadd541051fc11f5008b56f4e8a14d2df4c",
        "type": "github"
      },
      "original": {
@@ -375,7 +322,7 @@
    "lumen": {
      "inputs": {
        "fenix": "fenix",
-        "flake-utils": "flake-utils_3",
+        "flake-utils": "flake-utils_2",
        "nixpkgs": [
          "nixpkgs"
        ]
@@ -435,11 +382,11 @@
    },
    "nixpkgs": {
      "locked": {
-        "lastModified": 1766840161,
-        "narHash": "sha256-Ss/LHpJJsng8vz1Pe33RSGIWUOcqM1fjrehjUkdrWio=",
+        "lastModified": 1770537093,
+        "narHash": "sha256-pF1quXG5wsgtyuPOHcLfYg/ft/QMr8NnX0i6tW2187s=",
        "owner": "NixOS",
        "repo": "nixpkgs",
-        "rev": "3edc4a30ed3903fdf6f90c837f961fa6b49582d1",
+        "rev": "fef9403a3e4d31b0a23f0bacebbec52c248fbb51",
        "type": "github"
      },
      "original": {
@@ -466,27 +413,11 @@
    },
    "nixpkgs_2": {
      "locked": {
-        "lastModified": 1769861202,
-        "narHash": "sha256-JwhbEHmbFFH754loOPbpjPHf9EAi+oMm2RsFXnlbt1g=",
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "f214de98544a6acf0d9917ba265ac50849048fcb",
-        "type": "github"
-      },
-      "original": {
-        "owner": "NixOS",
-        "ref": "nixpkgs-unstable",
-        "repo": "nixpkgs",
-        "type": "github"
-      }
-    },
-    "nixpkgs_3": {
-      "locked": {
-        "lastModified": 1770034734,
-        "narHash": "sha256-ntFDQMr1u+2a3UlNWFj33B56x0AhHRtTuySf6vgbUpo=",
+        "lastModified": 1770627848,
+        "narHash": "sha256-pWVT4wjh+HKIdvGhph0vU1Kh48OSaSutPGpXxGNxSxw=",
        "owner": "nixos",
        "repo": "nixpkgs",
-        "rev": "a2afac3f36e986c4c08495361ee8571e808fd13c",
+        "rev": "fe776c9fe2c37f51546bb50ced285ea2a365e7d9",
        "type": "github"
      },
      "original": {
@@ -496,13 +427,13 @@
        "type": "github"
      }
    },
-    "nixpkgs_4": {
+    "nixpkgs_3": {
      "locked": {
-        "lastModified": 1768875095,
-        "narHash": "sha256-dYP3DjiL7oIiiq3H65tGIXXIT1Waiadmv93JS0sS+8A=",
+        "lastModified": 1770380644,
+        "narHash": "sha256-P7dWMHRUWG5m4G+06jDyThXO7kwSk46C1kgjEWcybkE=",
        "owner": "NixOS",
        "repo": "nixpkgs",
-        "rev": "ed142ab1b3a092c4d149245d0c4126a5d7ea00b0",
+        "rev": "ae67888ff7ef9dff69b3cf0cc0fbfbcd3a722abe",
        "type": "github"
      },
      "original": {
@@ -512,7 +443,7 @@
        "type": "github"
      }
    },
-    "nixpkgs_5": {
+    "nixpkgs_4": {
      "locked": {
        "lastModified": 1765934234,
        "narHash": "sha256-pJjWUzNnjbIAMIc5gRFUuKCDQ9S1cuh3b2hKgA7Mc4A=",
@@ -531,15 +462,15 @@
    "nixvim": {
      "inputs": {
        "flake-parts": "flake-parts_2",
-        "nixpkgs": "nixpkgs_4",
-        "systems": "systems_4"
+        "nixpkgs": "nixpkgs_3",
+        "systems": "systems_3"
      },
      "locked": {
-        "lastModified": 1770025103,
-        "narHash": "sha256-Qlb19PP0n6s+v1MywVjROV5XwsCvA58XXiXHk0Govb4=",
+        "lastModified": 1770627083,
+        "narHash": "sha256-Js8WrUwQ3lLRjWb8jGGE5npRN96E4mtPwyuNDuCDkcg=",
        "owner": "nix-community",
        "repo": "nixvim",
-        "rev": "31c3b3687dc85e3fbbf5c44728a5ee231608f8a9",
+        "rev": "d354487c4692de3d0918170c45bde05175b12e30",
        "type": "github"
      },
      "original": {
@@ -551,11 +482,11 @@
    "nono": {
      "flake": false,
      "locked": {
-        "lastModified": 1770047555,
-        "narHash": "sha256-BL1lBZYs6bsjk/+g+Zc2lUjErlvgYYJQqYEKLUjvtVU=",
+        "lastModified": 1770553882,
+        "narHash": "sha256-yEXw+rtuhoZvx1eO2Q+qPeGpvVbyASh7D9YEVAteoo8=",
        "owner": "lukehinds",
        "repo": "nono",
-        "rev": "8d382fbc0b21ad06d255a97000d876c15b5dea09",
+        "rev": "e80983bb6a4058335e96e02eeabe17314f771a9c",
        "type": "github"
      },
      "original": {
@@ -564,6 +495,39 @@
        "type": "github"
      }
    },
+    "openusage": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1770543295,
+        "narHash": "sha256-DvgEPZhFm06igalUPgnQ8VLkl0gk/3rm+lbEJ2/s7gM=",
+        "owner": "robinebers",
+        "repo": "openusage",
+        "rev": "22a7bd5f7856397400e60dd787ad82b23c763969",
+        "type": "github"
+      },
+      "original": {
+        "owner": "robinebers",
+        "ref": "v0.5.1",
+        "repo": "openusage",
+        "type": "github"
+      }
+    },
+    "overseer": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1770303305,
+        "narHash": "sha256-NM1haQAk1mWdmewgIv6tzApaIQxWKrIrri0+uXHY3Zc=",
+        "owner": "dmmulroy",
+        "repo": "overseer",
+        "rev": "5880d97939744ff72eb552c671da2fae1789041e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "dmmulroy",
+        "repo": "overseer",
+        "type": "github"
+      }
+    },
    "root": {
      "inputs": {
        "colmena": "colmena",
@@ -573,14 +537,14 @@
        "home-manager": "home-manager",
        "homebrew-cask": "homebrew-cask",
        "homebrew-core": "homebrew-core",
-        "jj-ryu": "jj-ryu",
-        "jj-starship": "jj-starship",
        "llm-agents": "llm-agents",
        "lumen": "lumen",
        "nix-homebrew": "nix-homebrew",
-        "nixpkgs": "nixpkgs_3",
+        "nixpkgs": "nixpkgs_2",
        "nixvim": "nixvim",
        "nono": "nono",
+        "openusage": "openusage",
+        "overseer": "overseer",
        "sops-nix": "sops-nix",
        "zjstatus": "zjstatus"
      }
@@ -630,11 +594,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1769921679,
-        "narHash": "sha256-twBMKGQvaztZQxFxbZnkg7y/50BW9yjtCBWwdjtOZew=",
+        "lastModified": 1770526836,
+        "narHash": "sha256-xbvX5Ik+0inJcLJtJ/AajAt7xCk6FOCrm5ogpwwvVDg=",
        "owner": "Mic92",
        "repo": "sops-nix",
-        "rev": "1e89149dcfc229e7e2ae24a8030f124a31e4f24f",
+        "rev": "d6e0e666048a5395d6ea4283143b7c9ac704720d",
        "type": "github"
      },
      "original": {
@@ -719,21 +683,6 @@
        "type": "github"
      }
    },
-    "systems_5": {
-      "locked": {
-        "lastModified": 1681028828,
-        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
-        "owner": "nix-systems",
-        "repo": "default",
-        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
-        "type": "github"
-      },
-      "original": {
-        "owner": "nix-systems",
-        "repo": "default",
-        "type": "github"
-      }
-    },
    "treefmt-nix": {
      "inputs": {
        "nixpkgs": [
@@ -742,11 +691,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1769691507,
-        "narHash": "sha256-8aAYwyVzSSwIhP2glDhw/G0i5+wOrren3v6WmxkVonM=",
+        "lastModified": 1770228511,
+        "narHash": "sha256-wQ6NJSuFqAEmIg2VMnLdCnUc0b7vslUohqqGGD+Fyxk=",
        "owner": "numtide",
        "repo": "treefmt-nix",
-        "rev": "28b19c5844cc6e2257801d43f2772a4b4c050a1b",
+        "rev": "337a4fe074be1042a35086f15481d763b8ddc0e7",
        "type": "github"
      },
      "original": {
@@ -758,8 +707,8 @@
    "zjstatus": {
      "inputs": {
        "crane": "crane",
-        "flake-utils": "flake-utils_4",
-        "nixpkgs": "nixpkgs_5",
+        "flake-utils": "flake-utils_3",
+        "nixpkgs": "nixpkgs_4",
        "rust-overlay": "rust-overlay"
      },
      "locked": {
--- a/flake.nix
+++ b/flake.nix
@@ -40,15 +40,18 @@
 			url = "github:jnsahaj/lumen";
 			inputs.nixpkgs.follows = "nixpkgs";
 		};
-		jj-ryu = {
-			url = "github:dmmulroy/jj-ryu";
-			flake = false;
-		};
-		jj-starship.url = "github:dmmulroy/jj-starship";
 		nono = {
 			url = "github:lukehinds/nono";
 			flake = false;
 		};
+		overseer = {
+			url = "github:dmmulroy/overseer";
+			flake = false;
+		};
+		openusage = {
+			url = "github:robinebers/openusage/v0.5.1";
+			flake = false;
+		};
 	};

 	outputs = inputs @ {flake-parts, ...}:
--- a/hosts/chidi/default.nix
+++ b/hosts/chidi/default.nix
@@ -25,20 +25,18 @@
 			../../profiles/bash.nix
 			../../profiles/bat.nix
 			../../profiles/direnv.nix
-			../../profiles/eza.nix
-			../../profiles/fish.nix
+			../../profiles/nushell.nix
 			../../profiles/fzf.nix
 			../../profiles/ghostty.nix
 			../../profiles/git.nix
 			../../profiles/home.nix
-			../../profiles/jjui.nix
-			../../profiles/jujutsu.nix
 			../../profiles/lazygit.nix
 			../../profiles/lumen.nix
 			../../profiles/mise.nix
 			../../profiles/nono.nix
 			../../profiles/neovim
 			../../profiles/opencode.nix
+			../../profiles/claude-code.nix
 			../../profiles/ripgrep.nix
 			../../profiles/ssh.nix
 			../../profiles/starship.nix
--- a/hosts/jason/default.nix
+++ b/hosts/jason/default.nix
@@ -24,20 +24,18 @@
 			../../profiles/bash.nix
 			../../profiles/bat.nix
 			../../profiles/direnv.nix
-			../../profiles/eza.nix
-			../../profiles/fish.nix
+			../../profiles/nushell.nix
 			../../profiles/fzf.nix
 			../../profiles/ghostty.nix
 			../../profiles/git.nix
 			../../profiles/home.nix
-			../../profiles/jjui.nix
-			../../profiles/jujutsu.nix
 			../../profiles/lazygit.nix
 			../../profiles/lumen.nix
 			../../profiles/mise.nix
 			../../profiles/nono.nix
 			../../profiles/neovim
 			../../profiles/opencode.nix
+			../../profiles/claude-code.nix
 			../../profiles/ripgrep.nix
 			../../profiles/ssh.nix
 			../../profiles/starship.nix
--- a/hosts/michael/default.nix
+++ b/hosts/michael/default.nix
@@ -39,7 +39,7 @@

 	home-manager.users.${user} = {
 		imports = [
-			../../profiles/fish.nix
+			../../profiles/nushell.nix
 			../../profiles/home.nix
 			../../profiles/ssh.nix
 			inputs.nixvim.homeModules.nixvim
--- a/hosts/tahani/default.nix
+++ b/hosts/tahani/default.nix
@@ -26,19 +26,18 @@
 			../../profiles/bash.nix
 			../../profiles/bat.nix
 			../../profiles/direnv.nix
-			../../profiles/eza.nix
-			../../profiles/fish.nix
+			../../profiles/nushell.nix
 			../../profiles/fzf.nix
 			../../profiles/git.nix
 			../../profiles/home.nix
-			../../profiles/jjui.nix
-			../../profiles/jujutsu.nix
 			../../profiles/lazygit.nix
 			../../profiles/lumen.nix
 			../../profiles/mise.nix
 			../../profiles/nono.nix
 			../../profiles/neovim
 			../../profiles/opencode.nix
+			../../profiles/overseer.nix
+			../../profiles/claude-code.nix
 			../../profiles/ripgrep.nix
 			../../profiles/ssh.nix
 			../../profiles/starship.nix
--- a/overlays/jj-ryu.nix
+++ b/overlays/jj-ryu.nix
@@ -1,7 +0,0 @@
-{inputs}: final: prev: {
-	jj-ryu =
-		import ../lib/build-rust-package.nix {
-			inherit prev;
-			input = inputs.jj-ryu;
-		};
-}
--- a/overlays/jj-starship.nix
+++ b/overlays/jj-starship.nix
@@ -1 +0,0 @@
-{inputs}: inputs.jj-starship.overlays.default
--- a/overlays/openusage.nix
+++ b/overlays/openusage.nix
@@ -0,0 +1,132 @@
+{inputs}: final: prev: let
+	version = "0.5.1";
+in {
+	openusage =
+		prev.rustPlatform.buildRustPackage (finalAttrs: {
+				pname = "openusage";
+				inherit version;
+
+				src = inputs.openusage;
+
+				cargoRoot = "src-tauri";
+				cargoLock = {
+					lockFile = "${inputs.openusage}/src-tauri/Cargo.lock";
+					outputHashes = {
+						"tauri-nspanel-2.1.0" = "sha256-PLACEHOLDER";
+						"tauri-plugin-aptabase-1.0.0" = "sha256-PLACEHOLDER";
+					};
+				};
+				buildAndTestSubdir = finalAttrs.cargoRoot;
+
+				node_modules =
+					prev.stdenv.mkDerivation {
+						inherit (finalAttrs) src version;
+						pname = "${finalAttrs.pname}-node_modules";
+
+						impureEnvVars =
+							prev.lib.fetchers.proxyImpureEnvVars
+							++ [
+								"GIT_PROXY_COMMAND"
+								"SOCKS_SERVER"
+							];
+
+						nativeBuildInputs = [
+							prev.bun
+							prev.writableTmpDirAsHomeHook
+						];
+
+						dontConfigure = true;
+						dontFixup = true;
+						dontPatchShebangs = true;
+
+						buildPhase = ''
+							runHook preBuild
+
+							export BUN_INSTALL_CACHE_DIR=$(mktemp -d)
+
+							bun install \
+								--no-progress \
+								--frozen-lockfile \
+								--ignore-scripts
+
+							runHook postBuild
+						'';
+
+						installPhase = ''
+							runHook preInstall
+							cp -R ./node_modules $out
+							runHook postInstall
+						'';
+
+						outputHash = "sha256-PLACEHOLDER";
+						outputHashMode = "recursive";
+					};
+
+				nativeBuildInputs = [
+					prev.cargo-tauri.hook
+					prev.rustPlatform.bindgenHook
+					prev.bun
+					prev.nodejs
+					prev.pkg-config
+					prev.makeBinaryWrapper
+				];
+
+				buildInputs =
+					prev.lib.optionals prev.stdenv.isDarwin (
+						with prev.darwin.apple_sdk.frameworks; [
+							AppKit
+							CoreFoundation
+							CoreServices
+							Security
+							WebKit
+						]
+					);
+
+				# Disable updater artifact generation — we don't have signing keys.
+				tauriConf = builtins.toJSON {bundle.createUpdaterArtifacts = false;};
+				passAsFile = ["tauriConf"];
+				preBuild = ''
+					tauriBuildFlags+=(
+						"--config"
+						"$tauriConfPath"
+					)
+				'';
+
+				configurePhase = ''
+					runHook preConfigure
+
+					# Copy pre-fetched node_modules
+					cp -R ${finalAttrs.node_modules} node_modules/
+					chmod -R u+rw node_modules
+					chmod -R u+x node_modules/.bin
+					patchShebangs node_modules
+
+					export HOME=$TMPDIR
+					export PATH="$PWD/node_modules/.bin:$PATH"
+
+					# Bundle plugins (copy from plugins/ to src-tauri/resources/bundled_plugins/)
+					${prev.nodejs}/bin/node copy-bundled.cjs
+
+					runHook postConfigure
+				'';
+
+				env = {
+					OPENSSL_NO_VENDOR = true;
+				};
+
+				doCheck = false;
+
+				postInstall =
+					prev.lib.optionalString prev.stdenv.isDarwin ''
+						makeWrapper $out/Applications/OpenUsage.app/Contents/MacOS/OpenUsage $out/bin/openusage
+					'';
+
+				meta = {
+					description = "Track all your AI coding subscriptions in one place";
+					homepage = "https://github.com/robinebers/openusage";
+					license = prev.lib.licenses.mit;
+					platforms = prev.lib.platforms.darwin;
+					mainProgram = "openusage";
+				};
+			});
+}
--- a/overlays/overseer.nix
+++ b/overlays/overseer.nix
@@ -0,0 +1,101 @@
+{inputs}: final: prev: let
+	manifest = (prev.lib.importTOML "${inputs.overseer}/overseer/Cargo.toml").package;
+
+	overseer-cli =
+		prev.rustPlatform.buildRustPackage {
+			pname = "overseer-cli";
+			version = manifest.version;
+
+			cargoLock.lockFile = "${inputs.overseer}/overseer/Cargo.lock";
+
+			src = "${inputs.overseer}/overseer";
+
+			nativeBuildInputs = with prev; [
+				pkg-config
+			];
+
+			buildInputs = with prev; [
+				openssl
+			];
+
+			OPENSSL_NO_VENDOR = 1;
+
+			doCheck = false;
+		};
+
+	overseer-host =
+		prev.buildNpmPackage {
+			pname = "overseer-host";
+			version = manifest.version;
+
+			src = "${inputs.overseer}/host";
+
+			npmDepsHash = "sha256-WIjx6N8vnH3C6Kxn4tiryi3bM0xnov5ok2k9XrndIS0=";
+
+			buildPhase = ''
+				runHook preBuild
+				npm run build
+				runHook postBuild
+			'';
+
+			installPhase = ''
+				runHook preInstall
+				mkdir -p $out
+				cp -r dist $out/
+				cp -r node_modules $out/
+				cp package.json $out/
+				runHook postInstall
+			'';
+		};
+
+	overseer-ui =
+		prev.buildNpmPackage {
+			pname = "overseer-ui";
+			version = manifest.version;
+
+			src = "${inputs.overseer}/ui";
+
+			npmDepsHash = "sha256-krOsSd8OAPsdCOCf1bcz9c/Myj6jpHOkaD/l+R7PQpY=";
+
+			buildPhase = ''
+				runHook preBuild
+				npm run build
+				runHook postBuild
+			'';
+
+			installPhase = ''
+				runHook preInstall
+				mkdir -p $out
+				cp -r dist $out/
+				runHook postInstall
+			'';
+		};
+in {
+	# The CLI looks for host/dist/index.js and ui/dist relative to the binary
+	# Using paths like: exe_dir.join("../@dmmulroy/overseer/host/dist/index.js")
+	# So we create: bin/os and @dmmulroy/overseer/host/dist/index.js
+	overseer =
+		prev.runCommand "overseer-${manifest.version}" {
+			nativeBuildInputs = [prev.makeWrapper];
+		} ''
+			# Create npm-like structure that the CLI expects
+			mkdir -p $out/bin
+			mkdir -p $out/@dmmulroy/overseer/host
+			mkdir -p $out/@dmmulroy/overseer/ui
+
+			# Copy host files
+			cp -r ${overseer-host}/dist $out/@dmmulroy/overseer/host/
+			cp -r ${overseer-host}/node_modules $out/@dmmulroy/overseer/host/
+			cp ${overseer-host}/package.json $out/@dmmulroy/overseer/host/
+
+			# Copy UI files
+			cp -r ${overseer-ui}/dist $out/@dmmulroy/overseer/ui/
+
+			# Copy CLI binary
+			cp ${overseer-cli}/bin/os $out/bin/os
+
+			# Make wrapper that ensures node is available
+			wrapProgram $out/bin/os \
+				--prefix PATH : ${prev.nodejs}/bin
+		'';
+}
--- a/profiles/atuin.nix
+++ b/profiles/atuin.nix
@@ -1,7 +1,7 @@
 {
 	programs.atuin = {
 		enable = true;
-		enableFishIntegration = true;
+		enableNushellIntegration = true;
 		flags = [
 			"--disable-up-arrow"
 		];
--- a/profiles/claude-code.nix
+++ b/profiles/claude-code.nix
@@ -0,0 +1,9 @@
+{
+	inputs,
+	pkgs,
+	...
+}: {
+	home.packages = [
+		inputs.llm-agents.packages.${pkgs.stdenv.hostPlatform.system}.claude-code
+	];
+}
--- a/profiles/core.nix
+++ b/profiles/core.nix
@@ -1,5 +1,6 @@
 {pkgs, ...}: {
 	programs.fish.enable = true;
+	environment.shells = [pkgs.nushell];

 	nixpkgs = {
 		config = {
--- a/profiles/darwin.nix
+++ b/profiles/darwin.nix
@@ -118,7 +118,7 @@
 		name = user;
 		home = "/Users/${user}";
 		isHidden = false;
-		shell = pkgs.fish;
+		shell = pkgs.nushell;
 	};

 	home-manager.useGlobalPkgs = true;
--- a/profiles/eza.nix
+++ b/profiles/eza.nix
@@ -1,6 +0,0 @@
-{
-	programs.eza = {
-		enable = true;
-		enableFishIntegration = true;
-	};
-}
--- a/profiles/fish.nix
+++ b/profiles/fish.nix
@@ -1,54 +0,0 @@
-{
-	programs.fish = {
-		enable = true;
-		functions = {
-			open_project = ''
-				set -l base "$HOME/Projects"
-				set -l choice (fd -t d -d 1 -a . "$base/Personal" "$base/Work" \
-				    | string replace -r -- "^$base/" "" \
-				    | fzf --prompt "project > ")
-				test -n "$choice"; and cd "$base/$choice"
-			'';
-		};
-		interactiveShellInit = ''
-			set fish_greeting
-
-			set fish_color_normal 4c4f69
-			set fish_color_command 1e66f5
-			set fish_color_param dd7878
-			set fish_color_keyword d20f39
-			set fish_color_quote 40a02b
-			set fish_color_redirection ea76cb
-			set fish_color_end fe640b
-			set fish_color_comment 8c8fa1
-			set fish_color_error d20f39
-			set fish_color_gray 9ca0b0
-			set fish_color_selection --background=ccd0da
-			set fish_color_search_match --background=ccd0da
-			set fish_color_option 40a02b
-			set fish_color_operator ea76cb
-			set fish_color_escape e64553
-			set fish_color_autosuggestion 9ca0b0
-			set fish_color_cancel d20f39
-			set fish_color_cwd df8e1d
-			set fish_color_user 179299
-			set fish_color_host 1e66f5
-			set fish_color_host_remote 40a02b
-			set fish_color_status d20f39
-			set fish_pager_color_progress 9ca0b0
-			set fish_pager_color_prefix ea76cb
-			set fish_pager_color_completion 4c4f69
-			set fish_pager_color_description 9ca0b0
-
-			set -gx LS_COLORS "$(vivid generate catppuccin-latte)"
-
-			set -gx COLORTERM truecolor
-			set -gx COLORFGBG "15;0"
-			set -gx TERM_BACKGROUND light
-
-			for mode in default insert
-			  bind --mode $mode \cp open_project
-			end
-		'';
-	};
-}
--- a/profiles/fzf.nix
+++ b/profiles/fzf.nix
@@ -1,7 +1,6 @@
 {
 	programs.fzf = {
 		enable = true;
-		enableFishIntegration = true;
 	};

 	home.sessionVariables = {
--- a/profiles/ghostty.nix
+++ b/profiles/ghostty.nix
@@ -1,6 +1,6 @@
 {pkgs, ...}: {
 	xdg.configFile."ghostty/config".text = ''
-		command = ${pkgs.fish}/bin/fish
+		command = ${pkgs.nushell}/bin/nu
 		theme = Catppuccin Latte
 		window-padding-x = 12
 		window-padding-y = 3
@@ -10,7 +10,7 @@
 		cursor-style = block
 		mouse-hide-while-typing = true
 		mouse-scroll-multiplier = 1.25
-		shell-integration = fish
+		shell-integration = none
 		shell-integration-features = no-cursor
 		clipboard-read = allow
 		clipboard-write = allow
--- a/profiles/git.nix
+++ b/profiles/git.nix
@@ -95,15 +95,10 @@ in {
 		gf = "git fetch";
 		gfa = "git fetch --all --tags --prune";
 		gfo = "git fetch origin";
-		gfg = "git ls-files | grep";
 		gg = "git gui citool";
 		gga = "git gui citool --amend";
-		ggpull = "git pull origin \"$(git branch --show-current)\"";
-		ggpush = "git push origin \"$(git branch --show-current)\"";
-		ggsup = "git branch --set-upstream-to=origin/$(git branch --show-current)";
 		ghh = "git help";
 		gignore = "git update-index --assume-unchanged";
-		gignored = "git ls-files -v | grep \"^[[:lower:]]\"";
 		gl = "git pull";
 		glg = "git log --stat";
 		glgp = "git log --stat --patch";
@@ -118,7 +113,6 @@ in {
 		glols = "git log --graph --pretty=\"%Cred%h%Creset -%C(auto)%d%Creset %s %Cgreen(%ar) %C(bold blue)<%an>%Creset\" --stat";
 		glod = "git log --graph --pretty=\"%Cred%h%Creset -%C(auto)%d%Creset %s %Cgreen(%ad) %C(bold blue)<%an>%Creset\"";
 		glods = "git log --graph --pretty=\"%Cred%h%Creset -%C(auto)%d%Creset %s %Cgreen(%ad) %C(bold blue)<%an>%Creset\" --date=short";
-		gluc = "git pull upstream $(git branch --show-current)";
 		glum = "git pull upstream main";
 		gm = "git merge";
 		gma = "git merge --abort";
@@ -133,7 +127,6 @@ in {
 		gpd = "git push --dry-run";
 		gpf = "git push --force-with-lease";
 		gpod = "git push origin --delete";
-		gpoat = "git push origin --all && git push origin --tags";
 		gpr = "git pull --rebase";
 		gpra = "git pull --rebase --autostash";
 		gprav = "git pull --rebase --autostash -v";
@@ -142,8 +135,6 @@ in {
 		gprv = "git pull --rebase -v";
 		gprum = "git pull --rebase upstream main";
 		gprumi = "git pull --rebase=interactive upstream main";
-		gpsup = "git push --set-upstream origin $(git branch --show-current)";
-		gpsupf = "git push --set-upstream origin $(git branch --show-current) --force-with-lease";
 		gpv = "git push --verbose";
 		gpu = "git push upstream";
 		gr = "git remote";
@@ -169,13 +160,11 @@ in {
 		grm = "git rm";
 		grmc = "git rm --cached";
 		grmv = "git remote rename";
-		groh = "git reset origin/$(git branch --show-current) --hard";
 		grrm = "git remote remove";
 		grs = "git restore";
 		grset = "git remote set-url";
 		grss = "git restore --source";
 		grst = "git restore --staged";
-		grt = "cd \"$(git rev-parse --show-toplevel || echo .)\"";
 		gru = "git reset --";
 		grup = "git remote update";
 		grv = "git remote --verbose";
@@ -201,16 +190,43 @@ in {
 		gswm = "git switch main";
 		gta = "git tag --annotate";
 		gts = "git tag --sign";
-		gtv = "git tag | sort -V";
 		gunignore = "git update-index --no-assume-unchanged";
-		gunwip = "git rev-list --max-count=1 --format=\"%s\" HEAD | grep -q \"\\--wip--\" && git reset HEAD~1";
 		gwch = "git whatchanged -p --abbrev-commit --pretty=medium";
-		gwipe = "git reset --hard && git clean --force -df";
 		gwt = "git worktree";
 		gwta = "git worktree add";
 		gwtls = "git worktree list";
 		gwtmv = "git worktree move";
 		gwtrm = "git worktree remove";
-		gwip = "git add -A; git rm $(git ls-files --deleted) 2> /dev/null; git commit --no-verify --no-gpg-sign --message \"--wip-- [skip ci]\"";
 	};
+
+	# Complex git aliases that require pipes/subshells — nushell `alias` can't
+	# handle these, so they're defined as custom commands instead.
+	programs.nushell.extraConfig = ''
+		def ggpull [] { git pull origin (git branch --show-current | str trim) }
+		def ggpush [] { git push origin (git branch --show-current | str trim) }
+		def ggsup [] { git branch $"--set-upstream-to=origin/(git branch --show-current | str trim)" }
+		def gluc [] { git pull upstream (git branch --show-current | str trim) }
+		def gpsup [] { git push --set-upstream origin (git branch --show-current | str trim) }
+		def gpsupf [] { git push --set-upstream origin (git branch --show-current | str trim) --force-with-lease }
+		def groh [] { git reset $"origin/(git branch --show-current | str trim)" --hard }
+		def --env grt [] {
+			let toplevel = (do { git rev-parse --show-toplevel } | complete | get stdout | str trim)
+			if ($toplevel | is-not-empty) { cd $toplevel } else { cd . }
+		}
+		def gfg [...pattern: string] { git ls-files | lines | where {|f| $f =~ ($pattern | str join ".*") } }
+		def gignored [] { git ls-files -v | lines | where {|l| ($l | str substring 0..1) =~ "[a-z]" } }
+		def gpoat [] { git push origin --all; git push origin --tags }
+		def gtv [] { git tag | lines | sort }
+		def gwipe [] { git reset --hard; git clean --force -df }
+		def gunwip [] {
+			let msg = (git rev-list --max-count=1 --format="%s" HEAD | lines | get 1)
+			if ($msg | str contains "--wip--") { git reset HEAD~1 }
+		}
+		def gwip [] {
+			git add -A
+			let deleted = (git ls-files --deleted | lines)
+			if ($deleted | is-not-empty) { git rm ...$deleted }
+			git commit --no-verify --no-gpg-sign --message "--wip-- [skip ci]"
+		}
+	'';
 }
--- a/profiles/jjui.nix
+++ b/profiles/jjui.nix
@@ -1,5 +0,0 @@
-{
-	programs.jjui = {
-		enable = true;
-	};
-}
--- a/profiles/jujutsu.nix
+++ b/profiles/jujutsu.nix
@@ -1,60 +0,0 @@
-{
-	programs.jujutsu = {
-		enable = true;
-		settings = {
-			user = {
-				name = "Christoph Schmatzler";
-				email = "christoph@schmatzler.com";
-			};
-			git = {
-				sign-on-push = true;
-				subprocess = true;
-				write-change-id-header = true;
-				private-commits = "description(glob:'wip:*') | description(glob:'WIP:*') | description(exact:'')";
-			};
-			fsmonitor = {
-				backend = "watchman";
-			};
-			ui = {
-				default-command = "status";
-				diff-formatter = ":git";
-				pager = ["delta" "--pager" "less -FRX"];
-				diff-editor = ["nvim" "-c" "DiffEditor $left $right $output"];
-				movement = {
-					edit = true;
-				};
-			};
-			aliases = {
-				n = ["new"];
-				tug = ["bookmark" "move" "--from" "closest_bookmark(@-)" "--to" "@-"];
-				stack = ["log" "-r" "stack()"];
-				retrunk = ["rebase" "-d" "trunk()"];
-				bm = ["bookmark"];
-				gf = ["git" "fetch"];
-				gp = ["git" "push"];
-			};
-			revset-aliases = {
-				"closest_bookmark(to)" = "heads(::to & bookmarks())";
-				"closest_pushable(to)" = "heads(::to & mutable() & ~description(exact:\"\") & (~empty() | merges()))";
-				"mine()" = "author(\"christoph@schmatzler.com\")";
-				"wip()" = "mine() ~ immutable()";
-				"open()" = "mine() ~ ::trunk()";
-				"current()" = "@:: & mutable()";
-				"stack()" = "reachable(@, mutable())";
-			};
-			templates = {
-				draft_commit_description = ''
-					concat(
-					  coalesce(description, default_commit_description, "\n"),
-					  surround(
-					    "\nJJ: This commit contains the following changes:\n", "",
-					    indent("JJ:     ", diff.stat(72)),
-					  ),
-					  "\nJJ: ignore-rest\n",
-					  diff.git(),
-					)
-				'';
-			};
-		};
-	};
-}
--- a/profiles/mise.nix
+++ b/profiles/mise.nix
@@ -1,7 +1,7 @@
 {
 	programs.mise = {
 		enable = true;
-		enableFishIntegration = true;
+		enableNushellIntegration = true;
 		globalConfig.settings = {
 			auto_install = false;
 		};
--- a/profiles/neovim/default.nix
+++ b/profiles/neovim/default.nix
@@ -8,7 +8,6 @@
 		./plugins/grug-far.nix
 		./plugins/harpoon.nix
 		./plugins/hunk.nix
-		./plugins/jj-diffconflicts.nix
 		./plugins/lsp.nix
 		./plugins/mini.nix
 		./plugins/oil.nix
--- a/profiles/neovim/mappings.nix
+++ b/profiles/neovim/mappings.nix
@@ -118,21 +118,15 @@
 			options.desc = "Visit paths (cwd)";
 		}
 		# g - git
-		{
-			mode = "n";
-			key = "<leader>gc";
-			action = ":JJDiffConflicts<CR>";
-			options.desc = "Resolve conflicts";
-		}
 		{
 			mode = "n";
 			key = "<leader>gg";
 			action.__raw = ''
 				function()
-				  require('toggleterm.terminal').Terminal:new({ cmd = 'jjui', direction = 'float' }):toggle()
+				  require('toggleterm.terminal').Terminal:new({ cmd = 'lazygit', direction = 'float' }):toggle()
 				end
 			'';
-			options.desc = "jjui";
+			options.desc = "lazygit";
 		}
 		# l - lsp/formatter
 		{
--- a/profiles/neovim/plugins/jj-diffconflicts.nix
+++ b/profiles/neovim/plugins/jj-diffconflicts.nix
@@ -1,14 +0,0 @@
-{pkgs, ...}: {
-	programs.nixvim.extraPlugins = [
-		(pkgs.vimUtils.buildVimPlugin {
-				name = "jj-diffconflicts";
-				src =
-					pkgs.fetchFromGitHub {
-						owner = "rafikdraoui";
-						repo = "jj-diffconflicts";
-						rev = "main";
-						hash = "sha256-hvMXpslucywVYA9Sdxx6IcXQXYcYNWK8s9jr+KtStdI=";
-					};
-			})
-	];
-}
--- a/profiles/nixos.nix
+++ b/profiles/nixos.nix
@@ -66,7 +66,7 @@
 				"network"
 				"systemd-journal"
 			];
-			shell = pkgs.fish;
+			shell = pkgs.nushell;
 			openssh.authorizedKeys.keys = constants.sshKeys;
 		};

--- a/profiles/nono.nix
+++ b/profiles/nono.nix
@@ -2,18 +2,4 @@
 	home.packages = with pkgs; [
 		nono
 	];
-
-	xdg.configFile."nono/profiles/opencode.toml".text = ''
-		[meta]
-		name = "opencode"
-		version = "1.0.0"
-		description = "OpenCode AI agent"
-
-		[filesystem]
-		allow = ["$WORKDIR"]
-		read = ["$XDG_CONFIG_HOME/opencode"]
-
-		[network]
-		block = false
-	'';
 }
--- a/profiles/nushell.nix
+++ b/profiles/nushell.nix
@@ -0,0 +1,225 @@
+{pkgs, ...}: {
+	programs.nushell = {
+		enable = true;
+
+		settings = {
+			show_banner = false;
+			completions = {
+				algorithm = "fuzzy";
+				case_sensitive = false;
+			};
+			history = {
+				file_format = "sqlite";
+			};
+		};
+
+		environmentVariables = {
+			COLORTERM = "truecolor";
+			COLORFGBG = "15;0";
+			TERM_BACKGROUND = "light";
+		};
+
+		extraEnv = ''
+			$env.LS_COLORS = (${pkgs.vivid}/bin/vivid generate catppuccin-latte)
+		'';
+
+		extraConfig = ''
+			# --- Catppuccin Latte Theme ---
+			let theme = {
+				rosewater: "#dc8a78"
+				flamingo: "#dd7878"
+				pink: "#ea76cb"
+				mauve: "#8839ef"
+				red: "#d20f39"
+				maroon: "#e64553"
+				peach: "#fe640b"
+				yellow: "#df8e1d"
+				green: "#40a02b"
+				teal: "#179299"
+				sky: "#04a5e5"
+				sapphire: "#209fb5"
+				blue: "#1e66f5"
+				lavender: "#7287fd"
+				text: "#4c4f69"
+				subtext1: "#5c5f77"
+				subtext0: "#6c6f85"
+				overlay2: "#7c7f93"
+				overlay1: "#8c8fa1"
+				overlay0: "#9ca0b0"
+				surface2: "#acb0be"
+				surface1: "#bcc0cc"
+				surface0: "#ccd0da"
+				base: "#eff1f5"
+				mantle: "#e6e9ef"
+				crust: "#dce0e8"
+			}
+
+			let scheme = {
+				recognized_command: $theme.blue
+				unrecognized_command: $theme.text
+				constant: $theme.peach
+				punctuation: $theme.overlay2
+				operator: $theme.sky
+				string: $theme.green
+				virtual_text: $theme.surface2
+				variable: { fg: $theme.flamingo attr: i }
+				filepath: $theme.yellow
+			}
+
+			$env.config.color_config = {
+				separator: { fg: $theme.surface2 attr: b }
+				leading_trailing_space_bg: { fg: $theme.lavender attr: u }
+				header: { fg: $theme.text attr: b }
+				row_index: $scheme.virtual_text
+				record: $theme.text
+				list: $theme.text
+				hints: $scheme.virtual_text
+				search_result: { fg: $theme.base bg: $theme.yellow }
+				shape_closure: $theme.teal
+				closure: $theme.teal
+				shape_flag: { fg: $theme.maroon attr: i }
+				shape_matching_brackets: { attr: u }
+				shape_garbage: $theme.red
+				shape_keyword: $theme.mauve
+				shape_match_pattern: $theme.green
+				shape_signature: $theme.teal
+				shape_table: $scheme.punctuation
+				cell-path: $scheme.punctuation
+				shape_list: $scheme.punctuation
+				shape_record: $scheme.punctuation
+				shape_vardecl: $scheme.variable
+				shape_variable: $scheme.variable
+				empty: { attr: n }
+				filesize: {||
+					if $in < 1kb {
+						$theme.teal
+					} else if $in < 10kb {
+						$theme.green
+					} else if $in < 100kb {
+						$theme.yellow
+					} else if $in < 10mb {
+						$theme.peach
+					} else if $in < 100mb {
+						$theme.maroon
+					} else if $in < 1gb {
+						$theme.red
+					} else {
+						$theme.mauve
+					}
+				}
+				duration: {||
+					if $in < 1day {
+						$theme.teal
+					} else if $in < 1wk {
+						$theme.green
+					} else if $in < 4wk {
+						$theme.yellow
+					} else if $in < 12wk {
+						$theme.peach
+					} else if $in < 24wk {
+						$theme.maroon
+					} else if $in < 52wk {
+						$theme.red
+					} else {
+						$theme.mauve
+					}
+				}
+				datetime: {|| (date now) - $in |
+					if $in < 1day {
+						$theme.teal
+					} else if $in < 1wk {
+						$theme.green
+					} else if $in < 4wk {
+						$theme.yellow
+					} else if $in < 12wk {
+						$theme.peach
+					} else if $in < 24wk {
+						$theme.maroon
+					} else if $in < 52wk {
+						$theme.red
+					} else {
+						$theme.mauve
+					}
+				}
+				shape_external: $scheme.unrecognized_command
+				shape_internalcall: $scheme.recognized_command
+				shape_external_resolved: $scheme.recognized_command
+				shape_block: $scheme.recognized_command
+				block: $scheme.recognized_command
+				shape_custom: $theme.pink
+				custom: $theme.pink
+				background: $theme.base
+				foreground: $theme.text
+				cursor: { bg: $theme.rosewater fg: $theme.base }
+				shape_range: $scheme.operator
+				range: $scheme.operator
+				shape_pipe: $scheme.operator
+				shape_operator: $scheme.operator
+				shape_redirection: $scheme.operator
+				glob: $scheme.filepath
+				shape_directory: $scheme.filepath
+				shape_filepath: $scheme.filepath
+				shape_glob_interpolation: $scheme.filepath
+				shape_globpattern: $scheme.filepath
+				shape_int: $scheme.constant
+				int: $scheme.constant
+				bool: $scheme.constant
+				float: $scheme.constant
+				nothing: $scheme.constant
+				binary: $scheme.constant
+				shape_nothing: $scheme.constant
+				shape_bool: $scheme.constant
+				shape_float: $scheme.constant
+				shape_binary: $scheme.constant
+				shape_datetime: $scheme.constant
+				shape_literal: $scheme.constant
+				string: $scheme.string
+				shape_string: $scheme.string
+				shape_string_interpolation: $theme.flamingo
+				shape_raw_string: $scheme.string
+				shape_externalarg: $scheme.string
+			}
+			$env.config.highlight_resolved_externals = true
+			$env.config.explore = {
+				status_bar_background: { fg: $theme.text, bg: $theme.mantle },
+				command_bar_text: { fg: $theme.text },
+				highlight: { fg: $theme.base, bg: $theme.yellow },
+				status: {
+					error: $theme.red,
+					warn: $theme.yellow,
+					info: $theme.blue,
+				},
+				selected_cell: { bg: $theme.blue fg: $theme.base },
+			}
+
+			# --- Custom Commands ---
+			def --env open_project [] {
+				let base = ($env.HOME | path join "Projects")
+				let choice = (
+					${pkgs.fd}/bin/fd -t d -d 1 -a . ($base | path join "Personal") ($base | path join "Work")
+					| lines
+					| each {|p| $p | str replace $"($base)/" "" }
+					| str join "\n"
+					| ${pkgs.fzf}/bin/fzf --prompt "project > "
+				)
+				if ($choice | str trim | is-not-empty) {
+					cd ($base | path join ($choice | str trim))
+				}
+			}
+
+			# --- Keybinding: Ctrl+O for open_project ---
+			$env.config.keybindings = ($env.config.keybindings | append [
+				{
+					name: open_project
+					modifier: control
+					keycode: char_o
+					mode: [emacs vi_insert vi_normal]
+					event: {
+						send: executehostcommand
+						cmd: "open_project"
+					}
+				}
+			])
+		'';
+	};
+}
--- a/profiles/opencode.nix
+++ b/profiles/opencode.nix
@@ -6,18 +6,18 @@
 	home.sessionVariables = {
 		OPENCODE_ENABLE_EXA = 1;
 		OPENCODE_EXPERIMENTAL_LSP_TOOL = 1;
-		# OPENCODE_EXPERIMENTAL_MARKDOWN = 1;
+		OPENCODE_EXPERIMENTAL_MARKDOWN = 1;
 		OPENCODE_EXPERIMENTAL_PLAN_MODE = 1;
-		OPENCODE_EXPERIMENTAL_FILE_WATCHER = 1;
 	};

 	programs.opencode = {
 		enable = true;
 		package = inputs.llm-agents.packages.${pkgs.stdenv.hostPlatform.system}.opencode;
 		settings = {
-			model = "opencode/claude-opus-4-5";
+			model = "anthropic/claude-opus-4-6";
 			small_model = "opencode/minimax-m2.1";
 			theme = "catppuccin";
+			plugin = ["oh-my-opencode" "opencode-anthropic-auth"];
 			keybinds = {
 				leader = "ctrl+o";
 			};
@@ -28,14 +28,15 @@
 					"*.env.*" = "deny";
 					"*.envrc" = "deny";
 					"secrets/*" = "deny";
+					"~/.local/share/opencode/mcp-auth.json" = "deny";
 				};
 			};
 			agent = {
 				plan = {
-					model = "opencode/gpt-5.2-codex";
+					model = "anthropic/claude-opus-4-6";
 				};
 				explore = {
-					model = "opencode/minimax-m2.1";
+					model = "anthropic/claude-haiku-4-5";
 				};
 			};
 			instructions = [
@@ -49,6 +50,14 @@
 				};
 			};
 			mcp = {
+				cog = {
+					enabled = true;
+					type = "remote";
+					url = "https://trycog.ai/mcp";
+					headers = {
+						Authorization = "Bearer {env:COG_API_TOKEN}";
+					};
+				};
 				context7 = {
 					enabled = true;
 					type = "remote";
@@ -64,21 +73,10 @@
 					type = "local";
 					command = ["bunx" "opensrc-mcp"];
 				};
-				appsignal = {
-					enabled = true;
+				overseer = {
+					enabled = false;
 					type = "local";
-					command = [
-						"docker"
-						"run"
-						"-i"
-						"--rm"
-						"-e"
-						"APPSIGNAL_API_KEY"
-						"appsignal/mcp"
-					];
-					environment = {
-						APPSIGNAL_API_KEY = "{env:APPSIGNAL_API_KEY}";
-					};
+					command = ["${pkgs.overseer}/bin/os" "mcp"];
 				};
 			};
 		};
@@ -101,5 +99,14 @@
 			source = ./opencode/tool;
 			recursive = true;
 		};
+		"opencode/oh-my-opencode.json".text =
+			builtins.toJSON {
+				"$schema" = "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json";
+				disabled_mcps = ["websearch" "context7" "grep_app"];
+				git_master = {
+					commit_footer = false;
+					include_co_authored_by = false;
+				};
+			};
 	};
 }
--- a/profiles/opencode/agent/oracle.md
+++ b/profiles/opencode/agent/oracle.md
@@ -1,86 +0,0 @@
---
-description: Senior engineering advisor for code reviews, architecture decisions, complex debugging, and planning. Invoke when you need deeper analysis before acting — reviews, trade-offs, debugging race conditions, planning refactors. Prompt with precise problem + files. Ask for concrete outcomes.
-mode: subagent
-model: opencode/gpt-5.2-codex
-options:
-  thinking:
-    type: enabled
-    budgetTokens: 31999
-permission:
-  "*": deny
-  read: allow
-  grep: allow
-  glob: allow
-  webfetch: allow
-  lsp: allow
---
-
-You are the Oracle - an expert AI advisor with advanced reasoning capabilities.
-
-Your role is to provide high-quality technical guidance, code reviews, architectural advice, and strategic planning for software engineering tasks.
-
-You are a subagent inside an AI coding system, called when the main agent needs a smarter, more capable model. You are invoked in a zero-shot manner - no one can ask you follow-up questions or provide follow-up answers.
-
-## Key Responsibilities
-
- Analyze code and architecture patterns
- Provide specific, actionable technical recommendations
- Plan implementations and refactoring strategies
- Answer deep technical questions with clear reasoning
- Suggest best practices and improvements
- Identify potential issues and propose solutions
-
-## Operating Principles (Simplicity-First)
-
-1. **Default to simplest viable solution** that meets stated requirements
-2. **Prefer minimal, incremental changes** that reuse existing code, patterns, and dependencies
-3. **Optimize for maintainability and developer time** over theoretical scalability
-4. **Apply YAGNI and KISS** - avoid premature optimization
-5. **One primary recommendation** - offer alternatives only if trade-offs are materially different
-6. **Calibrate depth to scope** - brief for small tasks, deep only when required
-7. **Stop when "good enough"** - note signals that would justify revisiting
-
-## Effort Estimates
-
-Include rough effort signal when proposing changes:
- **S** (<1 hour) - trivial, single-location change
- **M** (1-3 hours) - moderate, few files
- **L** (1-2 days) - significant, cross-cutting
- **XL** (>2 days) - major refactor or new system
-
-## Response Format
-
-Keep responses concise and action-oriented. For straightforward questions, collapse sections as appropriate:
-
-### 1. TL;DR
-1-3 sentences with the recommended simple approach.
-
-### 2. Recommendation
-Numbered steps or short checklist. Include minimal diffs/snippets only as needed.
-
-### 3. Rationale
-Brief justification. Mention why alternatives are unnecessary now.
-
-### 4. Risks & Guardrails
-Key caveats and mitigations.
-
-### 5. When to Reconsider
-Concrete triggers that justify a more complex design.
-
-### 6. Advanced Path (optional)
-Brief outline only if relevant and trade-offs are significant.
-
-## Tool Usage
-
-You have read-only access: read, grep, glob, LSP, webfetch.
-Use them freely to verify assumptions and gather context. Your extended thinking enables deep analysis - leverage it fully.
-
-## Guidelines
-
- Investigate thoroughly; report concisely - focus on highest-leverage insights
- For planning tasks, break down into minimal steps that achieve the goal incrementally
- Justify recommendations briefly - avoid long speculative exploration
- If the request is ambiguous, state your interpretation explicitly before answering
- If unanswerable from available context, say so directly
-
-**IMPORTANT:** Only your last message is returned to the main agent and displayed to the user. Make it comprehensive yet focused, with a clear, simple recommendation that enables immediate action.
--- a/profiles/opencode/command/code-review.md
+++ b/profiles/opencode/command/code-review.md
@@ -1,11 +1,8 @@
 ---
 description: Review changes with parallel @code-review subagents
-agent: plan
 ---
 Review the code changes using THREE (3) @code-review subagents and correlate results into a summary ranked by severity. Use the provided user guidance to steer the review and focus on specific code paths, changes, and/or areas of concern.

 Guidance: $ARGUMENTS

-First, call `skill({ name: 'vcs-detect' })` to determine whether the repo uses git or jj, then use the appropriate VCS commands throughout.
-
 Review uncommitted changes by default. If no uncommitted changes, review the last commit. If the user provides a pull request/merge request number or link, use CLI tools (gh/glab) to fetch it and then perform your review.
--- a/profiles/opencode/command/overseer-plan.md
+++ b/profiles/opencode/command/overseer-plan.md
@@ -0,0 +1,17 @@
+---
+description: Convert a markdown plan/spec to Overseer tasks
+---
+
+Convert markdown planning documents into trackable Overseer task hierarchies.
+
+First, invoke the skill tool to load the overseer-plan skill:
+
+```
+skill({ name: 'overseer-plan' })
+```
+
+Then follow the skill instructions to convert the document.
+
+<user-request>
+$ARGUMENTS
+</user-request>
--- a/profiles/opencode/command/overseer.md
+++ b/profiles/opencode/command/overseer.md
@@ -0,0 +1,17 @@
+---
+description: Manage tasks via Overseer - create, list, start, complete, find ready work
+---
+
+Task orchestration via Overseer codemode MCP.
+
+First, invoke the skill tool to load the overseer skill:
+
+```
+skill({ name: 'overseer' })
+```
+
+Then follow the skill instructions to manage tasks.
+
+<user-request>
+$ARGUMENTS
+</user-request>
--- a/profiles/opencode/command/plan-spec.md
+++ b/profiles/opencode/command/plan-spec.md
@@ -0,0 +1,17 @@
+---
+description: Dialogue-driven spec development through skeptical questioning
+---
+
+Develop implementation-ready specs through iterative dialogue and skeptical questioning.
+
+First, invoke the skill tool to load the spec-planner skill:
+
+```
+skill({ name: 'spec-planner' })
+```
+
+Then follow the skill instructions to develop the spec.
+
+<user-request>
+$ARGUMENTS
+</user-request>
--- a/profiles/opencode/skill/cog/SKILL.md
+++ b/profiles/opencode/skill/cog/SKILL.md
@@ -0,0 +1,406 @@
+---
+name: cog
+description: Persistent knowledge graph memory via Cog MCP. Use when recording insights, querying prior knowledge, or managing memory consolidation.
+metadata:
+  author: trycog
+  version: "1.0.0"
+---
+
+# Cog Memory System
+
+Persistent knowledge graph for teams. Concepts (engrams) linked via relationships (synapses). Spreading activation surfaces connected knowledge.
+
+## Core Workflow
+
+```
+1. UNDERSTAND task (read files, parse request)
+2. QUERY Cog with specific keywords  <- MANDATORY, no exceptions
+3. WAIT for results
+4. EXPLORE/IMPLEMENT guided by Cog knowledge
+5. RECORD insights as short-term memories during work
+6. CONSOLIDATE memories after work (reinforce valid, flush invalid)
+```
+
+**Hierarchy of truth:** Current code > User statements > Cog knowledge
+
+---
+
+## Visual Indicators (MANDATORY)
+
+Print before EVERY Cog tool call:
+
+| Tool | Print |
+|------|-------|
+| `cog_recall` | `Querying Cog...` |
+| `cog_learn` | `Recording to Cog...` |
+| `cog_associate` | `Linking concepts...` |
+| `cog_update` | `Updating engram...` |
+| `cog_trace` | `Tracing connections...` |
+| `cog_connections` | `Exploring connections...` |
+| `cog_unlink` | `Removing link...` |
+| `cog_list_short_term` | `Listing short-term memories...` |
+| `cog_reinforce` | `Reinforcing memory...` |
+| `cog_flush` | `Flushing invalid memory...` |
+| `cog_verify` | `Verifying synapse...` |
+| `cog_stale` | `Listing stale synapses...` |
+
+---
+
+## Tools Reference
+
+| Tool | Purpose |
+|------|---------|
+| `cog_recall` | Search with spreading activation |
+| `cog_learn` | Create memory with **chains** (sequential) or associations (hub) |
+| `cog_get` | Retrieve engram by ID |
+| `cog_associate` | Link two existing concepts |
+| `cog_trace` | Find paths between concepts |
+| `cog_update` | Modify engram term/definition |
+| `cog_unlink` | Remove synapse |
+| `cog_connections` | List engram connections |
+| `cog_bootstrap` | Exploration prompt for empty brains |
+| `cog_list_short_term` | List pending consolidations |
+| `cog_reinforce` | Convert short-term to long-term |
+| `cog_flush` | Delete invalid short-term memory |
+| `cog_verify` | Confirm synapse is still accurate |
+| `cog_stale` | List synapses needing verification |
+
+---
+
+## Querying Rules
+
+### Before exploring code, ALWAYS query Cog first
+
+Even for "trivial" tasks. The 2-second query may reveal gotchas, prior solutions, or context that changes your approach.
+
+### Query Reformulation (Critical for Recall)
+
+Before calling `cog_recall`, **transform your query from question-style to definition-style**. You are an LLM -- use that capability to bridge the vocabulary gap between how users ask questions and how knowledge is stored.
+
+#### Think like a definition, not a question
+
+| User Intent | Don't Query | Do Query |
+|-------------|-------------|----------|
+| "How do I handle stale data?" | `"handle stale data"` | `"cache invalidation event-driven TTL expiration data freshness"` |
+| "Why does auth break after a while?" | `"auth breaks"` | `"token expiration refresh timing session timeout JWT lifecycle"` |
+| "Where should validation go?" | `"where validation"` | `"input validation system boundaries sanitization defense in depth"` |
+
+#### The reformulation process
+
+1. **Identify the concept** -- What is the user actually asking about?
+2. **Generate canonical terms** -- What would an engram about this be titled?
+3. **Add related terminology** -- What words would the DEFINITION use?
+4. **Include synonyms** -- What other terms describe the same thing?
+
+#### Example transformation
+
+```
+User asks: "Why is the payment service sometimes charging twice?"
+
+Your thinking:
+- Concept: duplicate charges, idempotency
+- Canonical terms: "idempotency", "duplicate prevention", "payment race condition"
+- Definition words: "idempotent", "transaction", "mutex", "lock", "retry"
+- Synonyms: "double charge", "duplicate transaction"
+
+Query: "payment idempotency duplicate transaction race condition mutex retry"
+```
+
+### Query with specific keywords
+
+| Task Type | Understand First | Then Query With |
+|-----------|------------------|-----------------|
+| Bug fix | Error message, symptoms | `"canonical error name component pattern race condition"` |
+| Feature | User's description | `"domain terms design patterns architectural concepts"` |
+| Test fix | Read the test file | `"API names assertion patterns test utilities"` |
+| Architecture | System area | `"component relationships boundaries dependencies"` |
+
+**Bad:** `"authentication"` (too vague)
+**Good:** `"JWT refresh token expiration session lifecycle OAuth flow"` (definition-style)
+
+### Use Cog results
+
+- Follow paths Cog reveals
+- Read components Cog mentions first
+- Heed gotchas Cog warns about
+- If Cog is wrong, correct it immediately with `cog_update`
+
+---
+
+## Recording Rules
+
+### CRITICAL: Chains vs Associations
+
+**Before recording, ask: Is this sequential or hub-shaped?**
+
+| Structure | Use | Example |
+|-----------|-----|---------|
+| **Sequential** (A -> B -> C) | `chain_to` | Technology enables Pattern enables Feature |
+| **Hub** (A, B, C all connect to X) | `associations` | Meeting connects to Participants, Outcomes |
+
+**Default to chains** for:
+- Technology dependencies (DB -> ORM -> API)
+- Causal sequences (Cause -> Effect -> Consequence)
+- Architectural decisions (ADR -> Technology -> Feature)
+- Enabling relationships (Infrastructure -> enables -> Capability)
+- Reasoning paths (Premise -> implies -> Conclusion)
+
+**Use associations** for:
+- Hub/star patterns (one thing connects to many unrelated things)
+- Linking to existing concepts in the graph
+- Multi-party contexts (meetings, decisions with stakeholders)
+
+### Chain Example (PREFERRED for dependencies)
+
+```
+cog_learn({
+  "term": "PostgreSQL",
+  "definition": "Relational database with ACID guarantees",
+  "chain_to": [
+    {"term": "Ecto ORM", "definition": "Elixir database wrapper with changesets", "predicate": "enables"},
+    {"term": "Phoenix Contexts", "definition": "Business logic boundaries in Phoenix", "predicate": "enables"}
+  ]
+})
+```
+
+Creates: PostgreSQL ->[enables]-> Ecto ORM ->[enables]-> Phoenix Contexts
+
+### Association Example (for hubs)
+
+```
+cog_learn({
+  "term": "Auth Review 2024-01-20",
+  "definition": "Decided JWT with refresh tokens. Rejected session cookies.",
+  "associations": [
+    {"target": "JWT Pattern", "predicate": "leads_to"},
+    {"target": "Session Cookies", "predicate": "contradicts"},
+    {"target": "Mobile Team", "predicate": "is_component_of"}
+  ]
+})
+```
+
+Creates hub: JWT Pattern <-[leads_to]<- Auth Review ->[contradicts]-> Session Cookies
+
+---
+
+### When to record (during work)
+
+At these checkpoints, ask: *"What did I just learn that I didn't know 5 minutes ago?"*
+
+| Checkpoint | Record |
+|------------|--------|
+| After identifying root cause | Why it was broken |
+| After reading surprising code | The non-obvious behavior |
+| After a failed attempt | Why it didn't work |
+| Before implementing fix | The insight (freshest now) |
+| After discovering connection | The relationship |
+| After a meeting or decision | The context hub linking participants and outcomes |
+| After researching/exploring architecture | System limits, configuration points, component boundaries |
+
+**Record immediately.** Don't wait until task end -- you'll forget details.
+
+### Before calling `cog_learn`
+
+1. **Decide: chain or hub?** (see above)
+2. **For chains**: Build the sequence of steps with `chain_to`
+3. **For hubs**: Identify association targets from source material or Cog query
+
+**Skip the query when:**
+- Source material explicitly names related concepts (ADRs, documentation, structured data)
+- You already know target terms from conversation context
+- The insight references specific concepts by name
+
+**Query first when:**
+- Recording an insight and unsure what it relates to
+- Source is vague about connections
+- Exploring a new domain with unknown existing concepts
+
+### After calling `cog_learn`
+
+The operation is complete. **Do NOT verify your work by:**
+- Calling `cog_recall` to check the engram exists
+- Calling `cog_connections` to verify associations were created
+- Calling `cog_trace` to see if paths formed
+
+Trust the response confirmation. Verification wastes turns and adds no value -- if the operation failed, you'll see an error.
+
+### Recording Efficiency
+
+**One operation = one tool call.** Use `chain_to` for sequences, `associations` for hubs.
+
+**Never** follow `cog_learn` with separate `cog_associate` calls -- put all relationships in the original call.
+
+### Writing good engrams
+
+**Terms (2-5 words):**
+- "Session Token Refresh Timing"
+- "Why We Chose PostgreSQL"
+- NOT "Architecture" (too broad)
+- NOT "Project Overview" (super-hub)
+
+**Definitions (1-3 sentences):**
+1. What it is
+2. Why it matters / consequences
+3. Related keywords for search
+
+**Never create super-hubs** -- engrams so generic everything connects to them (e.g., "Overview", "Main System"). They pollute search results.
+
+### Relationship predicates
+
+| Predicate | Meaning | Best for | Use in |
+|-----------|---------|----------|--------|
+| `enables` | A makes B possible | Tech dependencies | **chain_to** |
+| `requires` | A is prerequisite for B | Dependencies | **chain_to** |
+| `implies` | If A then B | Logical consequences | **chain_to** |
+| `leads_to` | A flows to B | Outcomes, consequences | **chain_to** |
+| `precedes` | A comes before B | Sequencing, timelines | **chain_to** |
+| `derived_from` | A is based on B | Origins | **chain_to** |
+| `contradicts` | A and B mutually exclusive | Rejected alternatives | associations |
+| `is_component_of` | A is part of B | Parts to whole | associations |
+| `contains` | A includes B | Whole to parts | associations |
+| `example_of` | A demonstrates pattern B | Instances of patterns | associations |
+| `generalizes` | A is broader than B | Abstract concepts | associations |
+| `supersedes` | A replaces B | Deprecations | associations |
+| `similar_to` | A and B are closely related | Related approaches | associations |
+| `contrasts_with` | A is alternative to B | Different approaches | associations |
+| `related_to` | General link (use sparingly) | When nothing else fits | associations |
+
+**Chain predicates** (`enables`, `requires`, `implies`, `leads_to`, `precedes`, `derived_from`) express **flow** -- use them in `chain_to` to build traversable paths.
+
+### Modeling Complex Contexts (Hub Node Pattern)
+
+Synapses are binary (one source, one target). For multi-party relationships, use a **hub engram** connecting all participants.
+
+#### When to use hub nodes
+
+| Scenario | Hub Example | Connected Concepts |
+|----------|-------------|-------------------|
+| Meeting with outcomes | "Q1 Planning 2024-01" | Participants, decisions |
+| Decision with stakeholders | "Decision: Adopt GraphQL" | Pros, cons, voters |
+| Feature with components | "User Auth Feature" | OAuth, session, UI |
+| Incident with timeline | "2024-01 Payment Outage" | Cause, systems, fix |
+
+---
+
+## Consolidation (MANDATORY)
+
+**Every task must end with consolidation.** Short-term memories decay in 24 hours.
+
+### After work is complete:
+
+```
+cog_list_short_term({"limit": 20})
+```
+
+For each memory:
+- **Valid and useful?** -> `cog_reinforce` (makes permanent)
+- **Wrong or not useful?** -> `cog_flush` (deletes)
+
+### When to reinforce immediately
+
+- Insights from code you just wrote (you know it's correct)
+- Gotchas you just hit and fixed
+- Patterns you just applied successfully
+
+### When to wait for validation
+
+- Hypotheses about why something is broken
+- Assumptions about unfamiliar code
+- Solutions you haven't tested
+
+---
+
+## Verification (Prevents Staleness)
+
+Synapses decay if not verified as still semantically accurate.
+
+### When to verify
+
+- After using `cog_trace` and confirming paths are correct
+- When reviewing `cog_connections` and relationships hold
+- After successfully using knowledge from a synapse
+
+### Staleness levels
+
+| Level | Months Unverified | Score | Behavior |
+|-------|-------------------|-------|----------|
+| Fresh | < 3 | 0.0-0.49 | Normal |
+| Warning | 3-6 | 0.5-0.79 | Appears in `cog_stale` |
+| Critical | 6+ | 0.8-0.99 | Penalty in path scoring |
+| Deprecated | 12+ | 1.0 | Excluded from spreading activation |
+
+### Periodic maintenance
+
+Run `cog_stale({"level": "all"})` periodically to review relationships that may have become outdated. For each stale synapse:
+
+- **Still accurate?** -> `cog_verify` to reset staleness
+- **No longer true?** -> `cog_unlink` to remove
+
+---
+
+## Validation & Correction
+
+### Cog is hints, not truth
+
+Always verify against current code. If Cog is wrong:
+
+| Scenario | Action |
+|----------|--------|
+| Minor inaccuracy | `cog_update` to fix |
+| Pattern changed significantly | Unlink old, create new engram |
+| Completely obsolete | Update to note "DEPRECATED: [reason]" |
+
+---
+
+## Subagents
+
+Subagents MUST query Cog before exploring. Same rules apply:
+1. Understand task
+2. **Reformulate query to definition-style**
+3. Query Cog with reformulated keywords
+4. Wait for results
+5. Then explore
+
+---
+
+## Summary Reporting
+
+Only mention Cog when relevant:
+
+| Condition | Include |
+|-----------|---------|
+| Cog helped | `**Cog helped by:** [specific value]` |
+| Memories created | `**Recorded to Cog:** [term names]` |
+| Cog not used | Nothing (don't mention Cog) |
+| Cog queried but unhelpful | Don't mention the empty query, but **still record** new knowledge you discovered through exploration |
+
+---
+
+## Never Store
+
+- Passwords, API keys, tokens, secrets
+- SSH/PGP keys, certificates
+- Connection strings with credentials
+- PII (emails, SSNs, credit cards)
+- `.env` file contents
+
+Server auto-rejects sensitive content.
+
+---
+
+## Limitations
+
+- **No engram deletion** -- use `cog_update` or `cog_unlink`
+- **No multi-query** -- chain manually
+- **One synapse per direction** -- repeat calls strengthen existing link
+
+---
+
+## Spreading Activation
+
+`cog_recall` returns:
+1. **Seeds** -- direct matches
+2. **Paths** -- engrams connecting seeds (built from chains!)
+3. **Synapses** -- relationships along paths
+
+This surfaces the "connective tissue" between results. **Chains create these traversable paths.**
--- a/profiles/opencode/skill/overseer-plan/SKILL.md
+++ b/profiles/opencode/skill/overseer-plan/SKILL.md
@@ -0,0 +1,110 @@
+---
+name: overseer-plan
+description: Convert markdown planning documents to Overseer tasks via MCP codemode. Use when converting plans, specs, or design docs to trackable task hierarchies.
+license: MIT
+metadata:
+  author: dmmulroy
+  version: "1.0.0"
+---
+
+# Converting Markdown Documents to Overseer Tasks
+
+Use `/overseer-plan` to convert any markdown planning document into trackable Overseer tasks.
+
+## When to Use
+
+- After completing a plan in plan mode
+- Converting specs/design docs to implementation tasks
+- Creating tasks from roadmap or milestone documents
+
+## Usage
+
+```
+/overseer-plan <markdown-file-path>
+/overseer-plan <file> --priority 3           # Set priority (1-5)
+/overseer-plan <file> --parent <task-id>     # Create as child of existing task
+```
+
+## What It Does
+
+1. Reads markdown file
+2. Extracts title from first `#` heading (strips "Plan: " prefix)
+3. Creates Overseer milestone (or child task if `--parent` provided)
+4. Analyzes structure for child task breakdown
+5. Creates child tasks (depth 1) or subtasks (depth 2) when appropriate
+6. Returns task ID and breakdown summary
+
+## Hierarchy Levels
+
+| Depth | Name | Example |
+|-------|------|---------|
+| 0 | **Milestone** | "Add user authentication system" |
+| 1 | **Task** | "Implement JWT middleware" |
+| 2 | **Subtask** | "Add token verification function" |
+
+## Breakdown Decision
+
+**Create subtasks when:**
+- 3-7 clearly separable work items
+- Implementation across multiple files/components
+- Clear sequential dependencies
+
+**Keep single milestone when:**
+- 1-2 steps only
+- Work items tightly coupled
+- Plan is exploratory/investigative
+
+## Task Quality Criteria
+
+Every task must be:
+- **Atomic**: Single committable unit of work
+- **Validated**: Has tests OR explicit acceptance criteria in context ("Done when: ...")
+- **Clear**: Technical, specific, imperative verb
+
+Every milestone must:
+- **Demoable**: Produces runnable/testable increment
+- **Builds on prior**: Can depend on previous milestone's output
+
+## Review Workflow
+
+1. Analyze document -> propose breakdown
+2. **Invoke Oracle** to review breakdown and suggest improvements
+3. Incorporate feedback
+4. Create in Overseer (persists to SQLite via MCP)
+
+## After Creating
+
+```javascript
+await tasks.get("<id>");                    // TaskWithContext (full context + learnings)
+await tasks.list({ parentId: "<id>" });     // Task[] (children without context chain)
+await tasks.start("<id>");                  // Task (VCS required - creates bookmark, records start commit)
+await tasks.complete("<id>", { result: "...", learnings: [...] });  // Task (VCS required - commits, bubbles learnings)
+```
+
+**VCS Required**: `start` and `complete` require jj or git (fail with `NotARepository` if none found). CRUD operations work without VCS.
+
+**Note**: Priority must be 1-5. Blockers cannot be ancestors or descendants.
+
+## When NOT to Use
+
+- Document incomplete or exploratory
+- Content not actionable
+- No meaningful planning content
+
+---
+
+## Reading Order
+
+| Task | File |
+|------|------|
+| Understanding API | @file references/api.md |
+| Agent implementation | @file references/implementation.md |
+| See examples | @file references/examples.md |
+
+## In This Reference
+
+| File | Purpose |
+|------|---------|
+| `references/api.md` | Overseer MCP codemode API types/methods |
+| `references/implementation.md` | Step-by-step execution instructions for agent |
+| `references/examples.md` | Complete worked examples |
--- a/profiles/opencode/skill/overseer-plan/references/api.md
+++ b/profiles/opencode/skill/overseer-plan/references/api.md
@@ -0,0 +1,192 @@
+# Overseer Codemode MCP API
+
+Execute JavaScript code to interact with Overseer task management.
+
+## Task Interfaces
+
+```typescript
+// Basic task - returned by list(), create(), start(), complete()
+// Note: Does NOT include context or learnings fields
+interface Task {
+  id: string;
+  parentId: string | null;
+  description: string;
+  priority: 1 | 2 | 3 | 4 | 5;
+  completed: boolean;
+  completedAt: string | null;
+  startedAt: string | null;
+  createdAt: string;            // ISO 8601
+  updatedAt: string;
+  result: string | null;        // Completion notes
+  commitSha: string | null;     // Auto-populated on complete
+  depth: 0 | 1 | 2;             // 0=milestone, 1=task, 2=subtask
+  blockedBy?: string[];         // Blocking task IDs (omitted if empty)
+  blocks?: string[];            // Tasks this blocks (omitted if empty)
+  bookmark?: string;            // VCS bookmark name (if started)
+  startCommit?: string;         // Commit SHA at start
+  effectivelyBlocked: boolean;  // True if task OR ancestor has incomplete blockers
+}
+
+// Task with full context - returned by get(), nextReady()
+interface TaskWithContext extends Task {
+  context: {
+    own: string;              // This task's context
+    parent?: string;          // Parent's context (depth > 0)
+    milestone?: string;       // Root milestone's context (depth > 1)
+  };
+  learnings: {
+    own: Learning[];          // This task's learnings (bubbled from completed children)
+    parent: Learning[];       // Parent's learnings (depth > 0)
+    milestone: Learning[];    // Milestone's learnings (depth > 1)
+  };
+}
+
+// Task tree structure - returned by tree()
+interface TaskTree {
+  task: Task;
+  children: TaskTree[];
+}
+
+// Progress summary - returned by progress()
+interface TaskProgress {
+  total: number;
+  completed: number;
+  ready: number;     // !completed && !effectivelyBlocked
+  blocked: number;   // !completed && effectivelyBlocked
+}
+
+// Task type alias for depth filter
+type TaskType = "milestone" | "task" | "subtask";
+```
+
+## Learning Interface
+
+```typescript
+interface Learning {
+  id: string;
+  taskId: string;
+  content: string;
+  sourceTaskId: string | null;
+  createdAt: string;
+}
+```
+
+## Tasks API
+
+```typescript
+declare const tasks: {
+  list(filter?: { 
+    parentId?: string; 
+    ready?: boolean; 
+    completed?: boolean;
+    depth?: 0 | 1 | 2;    // 0=milestones, 1=tasks, 2=subtasks
+    type?: TaskType;      // Alias: "milestone"|"task"|"subtask" (mutually exclusive with depth)
+  }): Promise<Task[]>;
+  get(id: string): Promise<TaskWithContext>;
+  create(input: {
+    description: string;
+    context?: string;
+    parentId?: string;
+    priority?: 1 | 2 | 3 | 4 | 5;  // Must be 1-5
+    blockedBy?: string[];          // Cannot be ancestors/descendants
+  }): Promise<Task>;
+  update(id: string, input: {
+    description?: string;
+    context?: string;
+    priority?: 1 | 2 | 3 | 4 | 5;
+    parentId?: string;
+  }): Promise<Task>;
+  start(id: string): Promise<Task>;
+  complete(id: string, input?: { result?: string; learnings?: string[] }): Promise<Task>;
+  reopen(id: string): Promise<Task>;
+  delete(id: string): Promise<void>;
+  block(taskId: string, blockerId: string): Promise<void>;
+  unblock(taskId: string, blockerId: string): Promise<void>;
+  nextReady(milestoneId?: string): Promise<TaskWithContext | null>;
+  tree(rootId?: string): Promise<TaskTree | TaskTree[]>;
+  search(query: string): Promise<Task[]>;
+  progress(rootId?: string): Promise<TaskProgress>;
+};
+```
+
+| Method | Returns | Description |
+|--------|---------|-------------|
+| `list` | `Task[]` | Filter by `parentId`, `ready`, `completed`, `depth`, `type` |
+| `get` | `TaskWithContext` | Get task with full context chain + inherited learnings |
+| `create` | `Task` | Create task (priority must be 1-5) |
+| `update` | `Task` | Update description, context, priority, parentId |
+| `start` | `Task` | **VCS required** - creates bookmark, records start commit |
+| `complete` | `Task` | **VCS required** - commits changes + bubbles learnings to parent |
+| `reopen` | `Task` | Reopen completed task |
+| `delete` | `void` | Delete task + best-effort VCS bookmark cleanup |
+| `block` | `void` | Add blocker (cannot be self, ancestor, or descendant) |
+| `unblock` | `void` | Remove blocker relationship |
+| `nextReady` | `TaskWithContext \| null` | Get deepest ready leaf with full context |
+| `tree` | `TaskTree \| TaskTree[]` | Get task tree (all milestones if no ID) |
+| `search` | `Task[]` | Search by description/context/result (case-insensitive) |
+| `progress` | `TaskProgress` | Aggregate counts for milestone or all tasks |
+
+## Learnings API
+
+Learnings are added via `tasks.complete(id, { learnings: [...] })` and bubble to immediate parent (preserving `sourceTaskId`).
+
+```typescript
+declare const learnings: {
+  list(taskId: string): Promise<Learning[]>;
+};
+```
+
+| Method | Description |
+|--------|-------------|
+| `list` | List learnings for task |
+
+## VCS Integration (Required for Workflow)
+
+VCS operations are **automatically handled** by the tasks API:
+
+| Task Operation | VCS Effect |
+|----------------|------------|
+| `tasks.start(id)` | **VCS required** - creates bookmark `task/<id>`, records start commit |
+| `tasks.complete(id)` | **VCS required** - commits changes (NothingToCommit = success) |
+| `tasks.delete(id)` | Best-effort bookmark cleanup (logs warning on failure) |
+
+**VCS (jj or git) is required** for start/complete. Fails with `NotARepository` if none found. CRUD operations work without VCS.
+
+## Quick Examples
+
+```javascript
+// Create milestone with subtask
+const milestone = await tasks.create({
+  description: "Build authentication system",
+  context: "JWT-based auth with refresh tokens",
+  priority: 1
+});
+
+const subtask = await tasks.create({
+  description: "Implement token refresh logic",
+  parentId: milestone.id,
+  context: "Handle 7-day expiry"
+});
+
+// Start work (VCS required - creates bookmark)
+await tasks.start(subtask.id);
+
+// ... do implementation work ...
+
+// Complete task with learnings (VCS required - commits changes, bubbles learnings to parent)
+await tasks.complete(subtask.id, {
+  result: "Implemented using jose library",
+  learnings: ["Use jose instead of jsonwebtoken"]
+});
+
+// Get progress summary
+const progress = await tasks.progress(milestone.id);
+// -> { total: 2, completed: 1, ready: 1, blocked: 0 }
+
+// Search tasks
+const authTasks = await tasks.search("authentication");
+
+// Get task tree
+const tree = await tasks.tree(milestone.id);
+// -> { task: Task, children: TaskTree[] }
+```
--- a/profiles/opencode/skill/overseer-plan/references/examples.md
+++ b/profiles/opencode/skill/overseer-plan/references/examples.md
@@ -0,0 +1,177 @@
+# Examples
+
+## Example 1: With Breakdown
+
+### Input (`auth-plan.md`)
+
+```markdown
+# Plan: Add Authentication System
+
+## Implementation
+1. Create database schema for users/tokens
+2. Implement auth controller with endpoints
+3. Add JWT middleware for route protection
+4. Build frontend login/register forms
+5. Add integration tests
+```
+
+### Execution
+
+```javascript
+const milestone = await tasks.create({
+  description: "Add Authentication System",
+  context: `# Add Authentication System\n\n## Implementation\n1. Create database schema...`,
+  priority: 3
+});
+
+const subtasks = [
+  { desc: "Create database schema for users/tokens", done: "Migration runs, tables exist with FK constraints" },
+  { desc: "Implement auth controller with endpoints", done: "POST /register, /login return expected responses" },
+  { desc: "Add JWT middleware for route protection", done: "Unauthorized requests return 401, valid tokens pass" },
+  { desc: "Build frontend login/register forms", done: "Forms render, submit without errors" },
+  { desc: "Add integration tests", done: "`npm test` passes with auth coverage" }
+];
+
+for (const sub of subtasks) {
+  await tasks.create({ 
+    description: sub.desc, 
+    context: `Part of 'Add Authentication System'.\n\nDone when: ${sub.done}`,
+    parentId: milestone.id 
+  });
+}
+
+return { milestone: milestone.id, subtaskCount: subtasks.length };
+```
+
+### Output
+
+```
+Created milestone task_01ABC from plan
+
+Analyzed plan structure: Found 5 distinct implementation steps
+Created 5 subtasks:
+- task_02XYZ: Create database schema for users/tokens
+- task_03ABC: Implement auth controller with endpoints
+- task_04DEF: Add JWT middleware for route protection
+- task_05GHI: Build frontend login/register forms
+- task_06JKL: Add integration tests
+
+View structure: execute `await tasks.list({ parentId: "task_01ABC" })`
+```
+
+## Example 2: No Breakdown
+
+### Input (`bugfix-plan.md`)
+
+```markdown
+# Plan: Fix Login Validation Bug
+
+## Problem
+Login fails when username has spaces
+
+## Solution
+Update validation regex in auth.ts line 42
+```
+
+### Execution
+
+```javascript
+const milestone = await tasks.create({
+  description: "Fix Login Validation Bug",
+  context: `# Fix Login Validation Bug\n\n## Problem\nLogin fails...`,
+  priority: 3
+});
+
+return { milestone: milestone.id, breakdown: false };
+```
+
+### Output
+
+```
+Created milestone task_01ABC from plan
+
+Plan describes a cohesive single task. No subtask breakdown needed.
+
+View task: execute `await tasks.get("task_01ABC")`
+```
+
+## Example 3: Epic-Level (Two-Level Hierarchy)
+
+### Input (`full-auth-plan.md`)
+
+```markdown
+# Complete User Authentication System
+
+## Phase 1: Backend Infrastructure
+1. Database schema for users/sessions
+2. Password hashing with bcrypt
+3. JWT token generation
+
+## Phase 2: API Endpoints
+1. POST /auth/register
+2. POST /auth/login
+3. POST /auth/logout
+
+## Phase 3: Frontend
+1. Login/register forms
+2. Protected routes
+3. Session persistence
+```
+
+### Execution
+
+```javascript
+const milestone = await tasks.create({
+  description: "Complete User Authentication System",
+  context: `<full-markdown>`,
+  priority: 3
+});
+
+const phases = [
+  { name: "Backend Infrastructure", items: [
+    { desc: "Database schema", done: "Migration runs, tables exist" },
+    { desc: "Password hashing", done: "bcrypt hashes verified in tests" },
+    { desc: "JWT tokens", done: "Token generation/validation works" }
+  ]},
+  { name: "API Endpoints", items: [
+    { desc: "POST /auth/register", done: "Creates user, returns 201" },
+    { desc: "POST /auth/login", done: "Returns JWT on valid credentials" },
+    { desc: "POST /auth/logout", done: "Invalidates session, returns 200" }
+  ]},
+  { name: "Frontend", items: [
+    { desc: "Login/register forms", done: "Forms render, submit successfully" },
+    { desc: "Protected routes", done: "Redirect to login when unauthenticated" },
+    { desc: "Session persistence", done: "Refresh maintains logged-in state" }
+  ]}
+];
+
+for (const phase of phases) {
+  const phaseTask = await tasks.create({
+    description: phase.name,
+    parentId: milestone.id
+  });
+  for (const item of phase.items) {
+    await tasks.create({ 
+      description: item.desc, 
+      context: `Part of '${phase.name}'.\n\nDone when: ${item.done}`,
+      parentId: phaseTask.id 
+    });
+  }
+}
+
+return milestone;
+```
+
+### Output
+
+```
+Created milestone task_01ABC from plan
+
+Analyzed plan structure: Found 3 major phases
+Created as milestone with 3 tasks:
+- task_02XYZ: Backend Infrastructure (3 subtasks)
+- task_03ABC: API Endpoints (3 subtasks)
+- task_04DEF: Frontend (3 subtasks)
+
+View structure: execute `await tasks.list({ parentId: "task_01ABC" })`
+```
--- a/profiles/opencode/skill/overseer-plan/references/implementation.md
+++ b/profiles/opencode/skill/overseer-plan/references/implementation.md
@@ -0,0 +1,210 @@
+# Implementation Instructions
+
+**For the skill agent executing `/overseer-plan`.** Follow this workflow exactly.
+
+## Step 1: Read Markdown File
+
+Read the provided file using the Read tool.
+
+## Step 2: Extract Title
+
+- Parse first `#` heading as title
+- Strip "Plan: " prefix if present (case-insensitive)
+- Fallback: use filename without extension
+
+## Step 3: Create Milestone via MCP
+
+Basic creation:
+
+```javascript
+const milestone = await tasks.create({
+  description: "<extracted-title>",
+  context: `<full-markdown-content>`,
+  priority: <priority-if-provided-else-3>
+});
+return milestone;
+```
+
+With `--parent` option:
+
+```javascript
+const task = await tasks.create({
+  description: "<extracted-title>",
+  context: `<full-markdown-content>`,
+  parentId: "<parent-id>",
+  priority: <priority-if-provided-else-3>
+});
+return task;
+```
+
+Capture returned task ID for subsequent steps.
+
+## Step 4: Analyze Plan Structure
+
+### Breakdown Indicators
+
+1. **Numbered/bulleted implementation lists (3-7 items)**
+   ```markdown
+   ## Implementation
+   1. Create database schema
+   2. Build API endpoints
+   3. Add frontend components
+   ```
+
+2. **Clear subsections under implementation/tasks/steps**
+   ```markdown
+   ### 1. Backend Changes
+   - Modify server.ts
+   
+   ### 2. Frontend Updates
+   - Update login form
+   ```
+
+3. **File-specific sections**
+   ```markdown
+   ### `src/auth.ts` - Add JWT validation
+   ### `src/middleware.ts` - Create auth middleware
+   ```
+
+4. **Sequential phases**
+   ```markdown
+   **Phase 1: Database Layer**
+   **Phase 2: API Layer**
+   ```
+
+### Do NOT Break Down When
+
+- Only 1-2 steps/items
+- Plan is a single cohesive fix
+- Content is exploratory ("investigate", "research")
+- Work items inseparable
+- Plan very short (<10 lines)
+
+## Step 5: Validate Atomicity & Acceptance Criteria
+
+For each proposed task, verify:
+- **Atomic**: Can be completed in single commit
+- **Validated**: Has clear acceptance criteria
+
+If task too large -> split further.
+If no validation -> add to context:
+
+```
+Done when: <specific observable criteria>
+```
+
+Examples of good acceptance criteria:
+- "Done when: `npm test` passes, new migration applied"
+- "Done when: API returns 200 with expected payload"
+- "Done when: Component renders without console errors"
+- "Done when: Type check passes (`tsc --noEmit`)"
+
+## Step 6: Oracle Review
+
+Before creating tasks, invoke Oracle to review the proposed breakdown.
+
+**Prompt Oracle with:**
+
+```
+Review this task breakdown for "<milestone>":
+
+1. <task> - Done when: <criteria>
+2. <task> - Done when: <criteria>
+...
+
+Check:
+- Are tasks truly atomic (single commit)?
+- Is validation criteria clear and observable?
+- Does milestone deliver demoable increment?
+- Missing dependencies/blockers?
+- Any tasks that should be split or merged?
+```
+
+Incorporate Oracle's feedback, then proceed to create tasks.
+
+## Step 7: Create Subtasks (If Breaking Down)
+
+### Extract for Each Subtask
+
+1. **Description**: Strip numbering, keep concise (1-10 words), imperative form
+2. **Context**: Section content + "Part of [milestone description]" + acceptance criteria
+
+### Flat Breakdown
+
+```javascript
+const subtasks = [
+  { description: "Create database schema", context: "Schema for users/tokens. Part of 'Add Auth'.\n\nDone when: Migration runs, tables exist with FK constraints." },
+  { description: "Build API endpoints", context: "POST /auth/register, /auth/login. Part of 'Add Auth'.\n\nDone when: Endpoints return expected responses, tests pass." }
+];
+
+const created = [];
+for (const sub of subtasks) {
+  const task = await tasks.create({
+    description: sub.description,
+    context: sub.context,
+    parentId: milestone.id
+  });
+  created.push(task);
+}
+return { milestone: milestone.id, subtasks: created };
+```
+
+### Epic-Level Breakdown (phases with sub-items)
+
+```javascript
+// Create phase as task under milestone
+const phase = await tasks.create({
+  description: "Backend Infrastructure",
+  context: "Phase 1 context...",
+  parentId: milestoneId
+});
+
+// Create subtasks under phase
+for (const item of phaseItems) {
+  await tasks.create({
+    description: item.description,
+    context: item.context,
+    parentId: phase.id
+  });
+}
+```
+
+## Step 8: Report Results
+
+### Subtasks Created
+
+```
+Created milestone <id> from plan
+
+Analyzed plan structure: Found <N> distinct implementation steps
+Created <N> subtasks:
+- <id>: <description>
+- <id>: <description>
+...
+
+View structure: execute `await tasks.list({ parentId: "<id>" })`
+```
+
+### No Breakdown
+
+```
+Created milestone <id> from plan
+
+Plan describes a cohesive single task. No subtask breakdown needed.
+
+View task: execute `await tasks.get("<id>")`
+```
+
+### Epic-Level Breakdown
+
+```
+Created milestone <id> from plan
+
+Analyzed plan structure: Found <N> major phases
+Created as milestone with <N> tasks:
+- <id>: <phase-name> (<M> subtasks)
+- <id>: <phase-name> (<M> subtasks)
+...
+
+View structure: execute `await tasks.list({ parentId: "<id>" })`
+```
--- a/profiles/opencode/skill/overseer/SKILL.md
+++ b/profiles/opencode/skill/overseer/SKILL.md
@@ -0,0 +1,191 @@
+---
+name: overseer
+description: Manage tasks via Overseer codemode MCP. Use when tracking multi-session work, breaking down implementation, or persisting context for handoffs.
+license: MIT
+metadata:
+  author: dmmulroy
+  version: "1.0.0"
+---
+
+# Agent Coordination with Overseer
+
+## Core Principle: Tickets, Not Todos
+
+Overseer tasks are **tickets** - structured artifacts with comprehensive context:
+
+- **Description**: One-line summary (issue title)
+- **Context**: Full background, requirements, approach (issue body)
+- **Result**: Implementation details, decisions, outcomes (PR description)
+
+Think: "Would someone understand the what, why, and how from this task alone AND what success looks like?"
+
+## Task IDs are Ephemeral
+
+**Never reference task IDs in external artifacts** (commits, PRs, docs). Task IDs like `task_01JQAZ...` become meaningless once tasks complete. Describe the work itself, not the task that tracked it.
+
+## Overseer vs OpenCode's TodoWrite
+
+|                 | Overseer                              | TodoWrite              |
+| --------------- | ------------------------------------- | ---------------------- |
+| **Persistence** | SQLite database                       | Session-only           |
+| **Context**     | Rich (description + context + result) | Basic                  |
+| **Hierarchy**   | 3-level (milestone -> task -> subtask)| Flat                   |
+
+Use **Overseer** for persistent work. Use **TodoWrite** for ephemeral in-session tracking only.
+
+## When to Use Overseer
+
+**Use Overseer when:**
+- Breaking down complexity into subtasks
+- Work spans multiple sessions
+- Context needs to persist for handoffs
+- Recording decisions for future reference
+
+**Skip Overseer when:**
+- Work is a single atomic action
+- Everything fits in one message exchange
+- Overhead exceeds value
+- TodoWrite is sufficient
+
+## Finding Work
+
+```javascript
+// Get next ready task with full context (recommended for work sessions)
+const task = await tasks.nextReady(milestoneId); // TaskWithContext | null
+if (!task) {
+  console.log("No ready tasks");
+  return;
+}
+
+// Get all ready tasks (for progress overview)
+const readyTasks = await tasks.list({ ready: true }); // Task[]
+```
+
+**Use `nextReady()`** when starting work - returns `TaskWithContext | null` (deepest ready leaf with full context chain + inherited learnings).
+**Use `list({ ready: true })`** for status/progress checks - returns `Task[]` without context chain.
+
+## Basic Workflow
+
+```javascript
+// 1. Get next ready task (returns TaskWithContext | null)
+const task = await tasks.nextReady();
+if (!task) return "No ready tasks";
+
+// 2. Review context (available on TaskWithContext)
+console.log(task.context.own);       // This task's context
+console.log(task.context.parent);    // Parent's context (if depth > 0)
+console.log(task.context.milestone); // Root milestone context (if depth > 1)
+console.log(task.learnings.own);     // Learnings attached to this task (bubbled from children)
+
+// 3. Start work (VCS required - creates bookmark, records start commit)
+await tasks.start(task.id);
+
+// 4. Implement...
+
+// 5. Complete with learnings (VCS required - commits changes, bubbles learnings to parent)
+await tasks.complete(task.id, {
+  result: "Implemented login endpoint with JWT tokens",
+  learnings: ["bcrypt rounds should be 12 for production"]
+});
+```
+
+See @file references/workflow.md for detailed workflow guidance.
+
+## Understanding Task Context
+
+Tasks have **progressive context** - inherited from ancestors:
+
+```javascript
+const task = await tasks.get(taskId); // Returns TaskWithContext
+// task.context.own      - this task's context (always present)
+// task.context.parent   - parent task's context (if depth > 0)
+// task.context.milestone - root milestone's context (if depth > 1)
+
+// Task's own learnings (bubbled from completed children)
+// task.learnings.own - learnings attached to this task
+```
+
+## Return Type Summary
+
+| Method | Returns | Notes |
+|--------|---------|-------|
+| `tasks.get(id)` | `TaskWithContext` | Full context chain + inherited learnings |
+| `tasks.nextReady()` | `TaskWithContext \| null` | Deepest ready leaf with full context |
+| `tasks.list()` | `Task[]` | Basic task fields only |
+| `tasks.create()` | `Task` | No context chain |
+| `tasks.start/complete()` | `Task` | No context chain |
+
+## Blockers
+
+Blockers prevent a task from being ready until the blocker completes.
+
+**Constraints:**
+- Blockers cannot be self
+- Blockers cannot be ancestors (parent, grandparent, etc.)
+- Blockers cannot be descendants
+- Creating/reparenting with invalid blockers is rejected
+
+```javascript
+// Add blocker - taskA waits for taskB
+await tasks.block(taskA.id, taskB.id);
+
+// Remove blocker
+await tasks.unblock(taskA.id, taskB.id);
+```
+
+## Task Hierarchies
+
+Three levels: **Milestone** (depth 0) -> **Task** (depth 1) -> **Subtask** (depth 2).
+
+| Level | Name | Purpose | Example |
+|-------|------|---------|---------|
+| 0 | **Milestone** | Large initiative | "Add user authentication system" |
+| 1 | **Task** | Significant work item | "Implement JWT middleware" |
+| 2 | **Subtask** | Atomic step | "Add token verification function" |
+
+**Choosing the right level:**
+- Small feature (1-2 files) -> Single task
+- Medium feature (3-7 steps) -> Task with subtasks
+- Large initiative (5+ tasks) -> Milestone with tasks
+
+See @file references/hierarchies.md for detailed guidance.
+
+## Recording Results
+
+Complete tasks **immediately after implementing AND verifying**:
+- Capture decisions while fresh
+- Note deviations from plan
+- Document verification performed
+- Create follow-up tasks for tech debt
+
+Your result must include explicit verification evidence. See @file references/verification.md.
+
+## Best Practices
+
+1. **Right-size tasks**: Completable in one focused session
+2. **Clear completion criteria**: Context should define "done"
+3. **Don't over-decompose**: 3-7 children per parent
+4. **Action-oriented descriptions**: Start with verbs ("Add", "Fix", "Update")
+5. **Verify before completing**: Tests passing, manual testing done
+
+---
+
+## Reading Order
+
+| Task | File |
+|------|------|
+| Understanding API | @file references/api.md |
+| Implementation workflow | @file references/workflow.md |
+| Task decomposition | @file references/hierarchies.md |
+| Good/bad examples | @file references/examples.md |
+| Verification checklist | @file references/verification.md |
+
+## In This Reference
+
+| File | Purpose |
+|------|---------|
+| `references/api.md` | Overseer MCP codemode API types/methods |
+| `references/workflow.md` | Start->implement->complete workflow |
+| `references/hierarchies.md` | Milestone/task/subtask organization |
+| `references/examples.md` | Good/bad context and result examples |
+| `references/verification.md` | Verification checklist and process |
--- a/profiles/opencode/skill/overseer/references/api.md
+++ b/profiles/opencode/skill/overseer/references/api.md
@@ -0,0 +1,192 @@
+# Overseer Codemode MCP API
+
+Execute JavaScript code to interact with Overseer task management.
+
+## Task Interface
+
+```typescript
+// Basic task - returned by list(), create(), start(), complete()
+// Note: Does NOT include context or learnings fields
+interface Task {
+  id: string;
+  parentId: string | null;
+  description: string;
+  priority: 1 | 2 | 3 | 4 | 5;
+  completed: boolean;
+  completedAt: string | null;
+  startedAt: string | null;
+  createdAt: string;            // ISO 8601
+  updatedAt: string;
+  result: string | null;        // Completion notes
+  commitSha: string | null;     // Auto-populated on complete
+  depth: 0 | 1 | 2;             // 0=milestone, 1=task, 2=subtask
+  blockedBy?: string[];         // Blocking task IDs (omitted if empty)
+  blocks?: string[];            // Tasks this blocks (omitted if empty)
+  bookmark?: string;            // VCS bookmark name (if started)
+  startCommit?: string;         // Commit SHA at start
+  effectivelyBlocked: boolean;  // True if task OR ancestor has incomplete blockers
+}
+
+// Task with full context - returned by get(), nextReady()
+interface TaskWithContext extends Task {
+  context: {
+    own: string;              // This task's context
+    parent?: string;          // Parent's context (depth > 0)
+    milestone?: string;       // Root milestone's context (depth > 1)
+  };
+  learnings: {
+    own: Learning[];          // This task's learnings (bubbled from completed children)
+    parent: Learning[];       // Parent's learnings (depth > 0)
+    milestone: Learning[];    // Milestone's learnings (depth > 1)
+  };
+}
+
+// Task tree structure - returned by tree()
+interface TaskTree {
+  task: Task;
+  children: TaskTree[];
+}
+
+// Progress summary - returned by progress()
+interface TaskProgress {
+  total: number;
+  completed: number;
+  ready: number;     // !completed && !effectivelyBlocked
+  blocked: number;   // !completed && effectivelyBlocked
+}
+
+// Task type alias for depth filter
+type TaskType = "milestone" | "task" | "subtask";
+```
+
+## Learning Interface
+
+```typescript
+interface Learning {
+  id: string;
+  taskId: string;
+  content: string;
+  sourceTaskId: string | null;
+  createdAt: string;
+}
+```
+
+## Tasks API
+
+```typescript
+declare const tasks: {
+  list(filter?: { 
+    parentId?: string; 
+    ready?: boolean; 
+    completed?: boolean;
+    depth?: 0 | 1 | 2;    // 0=milestones, 1=tasks, 2=subtasks
+    type?: TaskType;      // Alias: "milestone"|"task"|"subtask" (mutually exclusive with depth)
+  }): Promise<Task[]>;
+  get(id: string): Promise<TaskWithContext>;
+  create(input: {
+    description: string;
+    context?: string;
+    parentId?: string;
+    priority?: 1 | 2 | 3 | 4 | 5;  // Required range: 1-5
+    blockedBy?: string[];
+  }): Promise<Task>;
+  update(id: string, input: {
+    description?: string;
+    context?: string;
+    priority?: 1 | 2 | 3 | 4 | 5;
+    parentId?: string;
+  }): Promise<Task>;
+  start(id: string): Promise<Task>;
+  complete(id: string, input?: { result?: string; learnings?: string[] }): Promise<Task>;
+  reopen(id: string): Promise<Task>;
+  delete(id: string): Promise<void>;
+  block(taskId: string, blockerId: string): Promise<void>;
+  unblock(taskId: string, blockerId: string): Promise<void>;
+  nextReady(milestoneId?: string): Promise<TaskWithContext | null>;
+  tree(rootId?: string): Promise<TaskTree | TaskTree[]>;
+  search(query: string): Promise<Task[]>;
+  progress(rootId?: string): Promise<TaskProgress>;
+};
+```
+
+| Method | Returns | Description |
+|--------|---------|-------------|
+| `list` | `Task[]` | Filter by `parentId`, `ready`, `completed`, `depth`, `type` |
+| `get` | `TaskWithContext` | Get task with full context chain + inherited learnings |
+| `create` | `Task` | Create task (priority must be 1-5) |
+| `update` | `Task` | Update description, context, priority, parentId |
+| `start` | `Task` | **VCS required** - creates bookmark, records start commit |
+| `complete` | `Task` | **VCS required** - commits changes + bubbles learnings to parent |
+| `reopen` | `Task` | Reopen completed task |
+| `delete` | `void` | Delete task + best-effort VCS bookmark cleanup |
+| `block` | `void` | Add blocker (cannot be self, ancestor, or descendant) |
+| `unblock` | `void` | Remove blocker relationship |
+| `nextReady` | `TaskWithContext \| null` | Get deepest ready leaf with full context |
+| `tree` | `TaskTree \| TaskTree[]` | Get task tree (all milestones if no ID) |
+| `search` | `Task[]` | Search by description/context/result (case-insensitive) |
+| `progress` | `TaskProgress` | Aggregate counts for milestone or all tasks |
+
+## Learnings API
+
+Learnings are added via `tasks.complete(id, { learnings: [...] })` and bubble to immediate parent (preserving `sourceTaskId`).
+
+```typescript
+declare const learnings: {
+  list(taskId: string): Promise<Learning[]>;
+};
+```
+
+| Method | Description |
+|--------|-------------|
+| `list` | List learnings for task |
+
+## VCS Integration (Required for Workflow)
+
+VCS operations are **automatically handled** by the tasks API:
+
+| Task Operation | VCS Effect |
+|----------------|------------|
+| `tasks.start(id)` | **VCS required** - creates bookmark `task/<id>`, records start commit |
+| `tasks.complete(id)` | **VCS required** - commits changes (NothingToCommit = success) |
+| `tasks.delete(id)` | Best-effort bookmark cleanup (logs warning on failure) |
+
+**VCS (jj or git) is required** for start/complete. Fails with `NotARepository` if none found. CRUD operations work without VCS.
+
+## Quick Examples
+
+```javascript
+// Create milestone with subtask
+const milestone = await tasks.create({
+  description: "Build authentication system",
+  context: "JWT-based auth with refresh tokens",
+  priority: 1
+});
+
+const subtask = await tasks.create({
+  description: "Implement token refresh logic",
+  parentId: milestone.id,
+  context: "Handle 7-day expiry"
+});
+
+// Start work (auto-creates VCS bookmark)
+await tasks.start(subtask.id);
+
+// ... do implementation work ...
+
+// Complete task with learnings (VCS required - commits changes, bubbles learnings to parent)
+await tasks.complete(subtask.id, {
+  result: "Implemented using jose library",
+  learnings: ["Use jose instead of jsonwebtoken"]
+});
+
+// Get progress summary
+const progress = await tasks.progress(milestone.id);
+// -> { total: 2, completed: 1, ready: 1, blocked: 0 }
+
+// Search tasks
+const authTasks = await tasks.search("authentication");
+
+// Get task tree
+const tree = await tasks.tree(milestone.id);
+// -> { task: Task, children: TaskTree[] }
+```
--- a/profiles/opencode/skill/overseer/references/examples.md
+++ b/profiles/opencode/skill/overseer/references/examples.md
@@ -0,0 +1,195 @@
+# Examples
+
+Good and bad examples for writing task context and results.
+
+## Writing Context
+
+Context should include everything needed to do the work without asking questions:
+- **What** needs to be done and why
+- **Implementation approach** (steps, files to modify, technical choices)
+- **Done when** (acceptance criteria)
+
+### Good Context Example
+
+```javascript
+await tasks.create({
+  description: "Migrate storage to one file per task",
+  context: `Change storage format for git-friendliness:
+
+Structure:
+.overseer/
+└── tasks/
+    ├── task_01ABC.json
+    └── task_02DEF.json
+
+NO INDEX - just scan task files. For typical task counts (<100), this is fast.
+
+Implementation:
+1. Update storage.ts:
+   - read(): Scan .overseer/tasks/*.json, parse each, return TaskStore
+   - write(task): Write single task to .overseer/tasks/{id}.json
+   - delete(id): Remove .overseer/tasks/{id}.json
+   - Add readTask(id) for single task lookup
+
+2. Task file format: Same as current Task schema (one task per file)
+
+3. Migration: On read, if old tasks.json exists, migrate to new format
+
+4. Update tests
+
+Benefits:
+- Create = new file (never conflicts)
+- Update = single file change
+- Delete = remove file
+- No index to maintain or conflict
+- git diff shows exactly which tasks changed`
+});
+```
+
+**Why it works:** States the goal, shows the structure, lists specific implementation steps, explains benefits. Someone could pick this up without asking questions.
+
+### Bad Context Example
+
+```javascript
+await tasks.create({
+  description: "Add auth",
+  context: "Need to add authentication"
+});
+```
+
+**What's missing:** How to implement it, what files, what's done when, technical approach.
+
+## Writing Results
+
+Results should capture what was actually done:
+- **What changed** (implementation summary)
+- **Key decisions** (and why)
+- **Verification** (tests passing, manual testing done)
+
+### Good Result Example
+
+```javascript
+await tasks.complete(taskId, `Migrated storage from single tasks.json to one file per task:
+
+Structure:
+- Each task stored as .overseer/tasks/{id}.json
+- No index file (avoids merge conflicts)
+- Directory scanned on read to build task list
+
+Implementation:
+- Modified Storage.read() to scan .overseer/tasks/ directory
+- Modified Storage.write() to write/delete individual task files
+- Auto-migration from old single-file format on first read
+- Atomic writes using temp file + rename pattern
+
+Trade-offs:
+- Slightly slower reads (must scan directory + parse each file)
+- Acceptable since task count is typically small (<100)
+- Better git history - each task change is isolated
+
+Verification:
+- All 60 tests passing
+- Build successful
+- Manually tested migration: old -> new format works`);
+```
+
+**Why it works:** States what changed, lists implementation details, explains trade-offs, confirms verification.
+
+### Bad Result Example
+
+```javascript
+await tasks.complete(taskId, "Fixed the storage issue");
+```
+
+**What's missing:** What was actually implemented, how, what decisions were made, verification evidence.
+
+## Subtask Context Example
+
+Link subtasks to their parent and explain what this piece does specifically:
+
+```javascript
+await tasks.create({
+  description: "Add token verification function",
+  parentId: jwtTaskId,
+  context: `Part of JWT middleware (parent task). This subtask: token verification.
+
+What it does:
+- Verify JWT signature and expiration on protected routes
+- Extract user ID from token payload
+- Attach user object to request
+- Return 401 for invalid/expired tokens
+
+Implementation:
+- Create src/middleware/verify-token.ts
+- Export verifyToken middleware function
+- Use jose library (preferred over jsonwebtoken)
+- Handle expired vs invalid token cases separately
+
+Done when:
+- Middleware function complete and working
+- Unit tests cover valid/invalid/expired scenarios
+- Integrated into auth routes in server.ts
+- Parent task can use this to protect endpoints`
+});
+```
+
+## Error Handling Examples
+
+### Handling Pending Children
+
+```javascript
+try {
+  await tasks.complete(taskId, "Done");
+} catch (err) {
+  if (err.message.includes("pending children")) {
+    const pending = await tasks.list({ parentId: taskId, completed: false });
+    console.log(`Cannot complete: ${pending.length} children pending`);
+    for (const child of pending) {
+      console.log(`- ${child.id}: ${child.description}`);
+    }
+    return;
+  }
+  throw err;
+}
+```
+
+### Handling Blocked Tasks
+
+```javascript
+const task = await tasks.get(taskId);
+
+if (task.blockedBy.length > 0) {
+  console.log("Task is blocked by:");
+  for (const blockerId of task.blockedBy) {
+    const blocker = await tasks.get(blockerId);
+    console.log(`- ${blocker.description} (${blocker.completed ? 'done' : 'pending'})`);
+  }
+  return "Cannot start - blocked by other tasks";
+}
+
+await tasks.start(taskId);
+```
+
+## Creating Task Hierarchies
+
+```javascript
+// Create milestone with tasks
+const milestone = await tasks.create({
+  description: "Implement user authentication",
+  context: "Full auth: JWT, login/logout, password reset, rate limiting",
+  priority: 2
+});
+
+const subtasks = [
+  "Add login endpoint",
+  "Add logout endpoint", 
+  "Implement JWT token service",
+  "Add password reset flow"
+];
+
+for (const desc of subtasks) {
+  await tasks.create({ description: desc, parentId: milestone.id });
+}
+```
+
+See @file references/hierarchies.md for sequential subtasks with blockers.
--- a/profiles/opencode/skill/overseer/references/hierarchies.md
+++ b/profiles/opencode/skill/overseer/references/hierarchies.md
@@ -0,0 +1,170 @@
+# Task Hierarchies
+
+Guidance for organizing work into milestones, tasks, and subtasks.
+
+## Three Levels
+
+| Level | Name | Purpose | Example |
+|-------|------|---------|---------|
+| 0 | **Milestone** | Large initiative (5+ tasks) | "Add user authentication system" |
+| 1 | **Task** | Significant work item | "Implement JWT middleware" |
+| 2 | **Subtask** | Atomic implementation step | "Add token verification function" |
+
+**Maximum depth is 3 levels.** Attempting to create a child of a subtask will fail.
+
+## When to Use Each Level
+
+### Single Task (No Hierarchy)
+- Small feature (1-2 files, ~1 session)
+- Work is atomic, no natural breakdown
+
+### Task with Subtasks
+- Medium feature (3-5 files, 3-7 steps)
+- Work naturally decomposes into discrete steps
+- Subtasks could be worked on independently
+
+### Milestone with Tasks
+- Large initiative (multiple areas, many sessions)
+- Work spans 5+ distinct tasks
+- You want high-level progress tracking
+
+## Creating Hierarchies
+
+```javascript
+// Create the milestone
+const milestone = await tasks.create({
+  description: "Add user authentication system",
+  context: "Full auth system with JWT tokens, password reset...",
+  priority: 2
+});
+
+// Create tasks under it
+const jwtTask = await tasks.create({
+  description: "Implement JWT token generation",
+  context: "Create token service with signing and verification...",
+  parentId: milestone.id
+});
+
+const resetTask = await tasks.create({
+  description: "Add password reset flow",
+  context: "Email-based password reset with secure tokens...",
+  parentId: milestone.id
+});
+
+// For complex tasks, add subtasks
+const verifySubtask = await tasks.create({
+  description: "Add token verification function",
+  context: "Verify JWT signature and expiration...",
+  parentId: jwtTask.id
+});
+```
+
+## Subtask Best Practices
+
+Each subtask should be:
+
+- **Independently understandable**: Clear on its own
+- **Linked to parent**: Reference parent, explain how this piece fits
+- **Specific scope**: What this subtask does vs what parent/siblings do
+- **Clear completion**: Define "done" for this piece specifically
+
+Example subtask context:
+```
+Part of JWT middleware (parent task). This subtask: token verification.
+
+What it does:
+- Verify JWT signature and expiration
+- Extract user ID from payload
+- Return 401 for invalid/expired tokens
+
+Done when:
+- Function complete and tested
+- Unit tests cover valid/invalid/expired cases
+```
+
+## Decomposition Strategy
+
+When faced with large tasks:
+
+1. **Assess scope**: Is this milestone-level (5+ tasks) or task-level (3-7 subtasks)?
+2. Create parent task/milestone with overall goal and context
+3. Analyze and identify 3-7 logical children
+4. Create children with specific contexts and boundaries
+5. Work through systematically, completing with results
+6. Complete parent with summary of overall implementation
+
+### Don't Over-Decompose
+
+- **3-7 children per parent** is usually right
+- If you'd only have 1-2 subtasks, just make separate tasks
+- If you need depth 3+, restructure your breakdown
+
+## Viewing Hierarchies
+
+```javascript
+// List all tasks under a milestone
+const children = await tasks.list({ parentId: milestoneId });
+
+// Get task with context breadcrumb
+const task = await tasks.get(taskId);
+// task.context.parent - parent's context
+// task.context.milestone - root milestone's context
+
+// Check progress
+const pending = await tasks.list({ parentId: milestoneId, completed: false });
+const done = await tasks.list({ parentId: milestoneId, completed: true });
+console.log(`Progress: ${done.length}/${done.length + pending.length}`);
+```
+
+## Completion Rules
+
+1. **Cannot complete with pending children**
+   ```javascript
+   // This will fail if task has incomplete subtasks
+   await tasks.complete(taskId, "Done");
+   // Error: "pending children"
+   ```
+
+2. **Complete children first**
+   - Work through subtasks systematically
+   - Complete each with meaningful results
+
+3. **Parent result summarizes overall implementation**
+   ```javascript
+   await tasks.complete(milestoneId, `User authentication system complete:
+
+   Implemented:
+   - JWT token generation and verification
+   - Login/logout endpoints
+   - Password reset flow
+   - Rate limiting
+
+   5 tasks completed, all tests passing.`);
+   ```
+
+## Blocking Dependencies
+
+Use `blockedBy` for cross-task dependencies:
+
+```javascript
+// Create task that depends on another
+const deployTask = await tasks.create({
+  description: "Deploy to production",
+  context: "...",
+  blockedBy: [testTaskId, reviewTaskId]
+});
+
+// Add blocker to existing task
+await tasks.block(deployTaskId, testTaskId);
+
+// Remove blocker
+await tasks.unblock(deployTaskId, testTaskId);
+```
+
+**Use blockers when:**
+- Task B cannot start until Task A completes
+- Multiple tasks depend on a shared prerequisite
+
+**Don't use blockers when:**
+- Tasks can be worked on in parallel
+- The dependency is just logical grouping (use subtasks instead)
--- a/profiles/opencode/skill/overseer/references/verification.md
+++ b/profiles/opencode/skill/overseer/references/verification.md
@@ -0,0 +1,186 @@
+# Verification Guide
+
+Before marking any task complete, you MUST verify your work. Verification separates "I think it's done" from "it's actually done."
+
+## The Verification Process
+
+1. **Re-read the task context**: What did you originally commit to do?
+2. **Check acceptance criteria**: Does your implementation satisfy the "Done when" conditions?
+3. **Run relevant tests**: Execute the test suite and document results
+4. **Test manually**: Actually try the feature/change yourself
+5. **Compare with requirements**: Does what you built match what was asked?
+
+## Strong vs Weak Verification
+
+### Strong Verification Examples
+
+- "All 60 tests passing, build successful"
+- "All 69 tests passing (4 new tests for middleware edge cases)"
+- "Manually tested with valid/invalid/expired tokens - all cases work"
+- "Ran `cargo test` - 142 tests passed, 0 failed"
+
+### Weak Verification (Avoid)
+
+- "Should work now" - "should" means not verified
+- "Made the changes" - no evidence it works
+- "Added tests" - did the tests pass? What's the count?
+- "Fixed the bug" - what bug? Did you verify the fix?
+- "Done" - done how? prove it
+
+## Verification by Task Type
+
+| Task Type | How to Verify |
+|-----------|---------------|
+| Code changes | Run full test suite, document passing count |
+| New features | Run tests + manual testing of functionality |
+| Configuration | Test the config works (run commands, check workflows) |
+| Documentation | Verify examples work, links resolve, formatting renders |
+| Refactoring | Confirm tests still pass, no behavior changes |
+| Bug fixes | Reproduce bug first, verify fix, add regression test |
+
+## Cross-Reference Checklist
+
+Before marking complete, verify all applicable items:
+
+- [ ] Task description requirements met
+- [ ] Context "Done when" criteria satisfied
+- [ ] Tests passing (document count: "All X tests passing")
+- [ ] Build succeeds (if applicable)
+- [ ] Manual testing done (describe what you tested)
+- [ ] No regressions introduced
+- [ ] Edge cases considered (error handling, invalid input)
+- [ ] Follow-up work identified (created new tasks if needed)
+
+**If you can't check all applicable boxes, the task isn't done yet.**
+
+## Result Examples with Verification
+
+### Code Implementation
+
+```javascript
+await tasks.complete(taskId, `Implemented JWT middleware:
+
+Implementation:
+- Created src/middleware/verify-token.ts
+- Separated 'expired' vs 'invalid' error codes
+- Added user extraction from payload
+
+Verification:
+- All 69 tests passing (4 new tests for edge cases)
+- Manually tested with valid token: Access granted
+- Manually tested with expired token: 401 with 'token_expired'
+- Manually tested with invalid signature: 401 with 'invalid_token'`);
+```
+
+### Configuration/Infrastructure
+
+```javascript
+await tasks.complete(taskId, `Added GitHub Actions workflow for CI:
+
+Implementation:
+- Created .github/workflows/ci.yml
+- Jobs: lint, test, build with pnpm cache
+
+Verification:
+- Pushed to test branch, opened PR #123
+- Workflow triggered automatically
+- All jobs passed (lint: 0 errors, test: 69/69, build: success)
+- Total run time: 2m 34s`);
+```
+
+### Refactoring
+
+```javascript
+await tasks.complete(taskId, `Refactored storage to one file per task:
+
+Implementation:
+- Split tasks.json into .overseer/tasks/{id}.json files
+- Added auto-migration from old format
+- Atomic writes via temp+rename
+
+Verification:
+- All 60 tests passing (including 8 storage tests)
+- Build successful
+- Manually tested migration: old -> new format works
+- Confirmed git diff shows only changed tasks`);
+```
+
+### Bug Fix
+
+```javascript
+await tasks.complete(taskId, `Fixed login validation accepting usernames with spaces:
+
+Root cause:
+- Validation regex didn't account for leading/trailing spaces
+
+Fix:
+- Added .trim() before validation in src/auth/validate.ts:42
+- Updated regex to reject internal spaces
+
+Verification:
+- All 45 tests passing (2 new regression tests)
+- Manually tested:
+  - " admin" -> rejected (leading space)
+  - "admin " -> rejected (trailing space)
+  - "ad min" -> rejected (internal space)
+  - "admin" -> accepted`);
+```
+
+### Documentation
+
+```javascript
+await tasks.complete(taskId, `Updated API documentation for auth endpoints:
+
+Implementation:
+- Added docs for POST /auth/login
+- Added docs for POST /auth/logout
+- Added docs for POST /auth/refresh
+- Included example requests/responses
+
+Verification:
+- All code examples tested and working
+- Links verified (no 404s)
+- Rendered in local preview - formatting correct
+- Spell-checked content`);
+```
+
+## Common Verification Mistakes
+
+| Mistake | Better Approach |
+|---------|-----------------|
+| "Tests pass" | "All 42 tests passing" (include count) |
+| "Manually tested" | "Manually tested X, Y, Z scenarios" (be specific) |
+| "Works" | "Works: [evidence]" (show proof) |
+| "Fixed" | "Fixed: [root cause] -> [solution] -> [verification]" |
+
+## When Verification Fails
+
+If verification reveals issues:
+
+1. **Don't complete the task** - it's not done
+2. **Document what failed** in task context
+3. **Fix the issues** before completing
+4. **Re-verify** after fixes
+
+```javascript
+// Update context with failure notes
+await tasks.update(taskId, {
+  context: task.context + `
+
+Verification attempt 1 (failed):
+- Tests: 41/42 passing
+- Failing: test_token_refresh - timeout issue
+- Need to investigate async handling`
+});
+
+// After fixing
+await tasks.complete(taskId, `Implemented token refresh:
+
+Implementation:
+- Added refresh endpoint
+- Fixed async timeout (was missing await)
+
+Verification:
+- All 42 tests passing (fixed timeout issue)
+- Manual testing: refresh works within 30s window`);
+```
--- a/profiles/opencode/skill/overseer/references/workflow.md
+++ b/profiles/opencode/skill/overseer/references/workflow.md
@@ -0,0 +1,164 @@
+# Implementation Workflow
+
+Step-by-step guide for working with Overseer tasks during implementation.
+
+## 1. Get Next Ready Task
+
+```javascript
+// Get next task with full context (recommended)
+const task = await tasks.nextReady();
+
+// Or scope to specific milestone
+const task = await tasks.nextReady(milestoneId);
+
+if (!task) {
+  return "No tasks ready - all blocked or completed";
+}
+```
+
+`nextReady()` returns a `TaskWithContext` (task with inherited context and learnings) or `null`.
+
+## 2. Review Context
+
+Before starting, verify you can answer:
+- **What** needs to be done specifically?
+- **Why** is this needed?
+- **How** should it be implemented?
+- **When** is it done (acceptance criteria)?
+
+```javascript
+const task = await tasks.get(taskId);
+
+// Task's own context
+console.log("Task:", task.context.own);
+
+// Parent context (if task has parent)
+if (task.context.parent) {
+  console.log("Parent:", task.context.parent);
+}
+
+// Milestone context (if depth > 1)
+if (task.context.milestone) {
+  console.log("Milestone:", task.context.milestone);
+}
+
+// Task's own learnings (bubbled from completed children)
+console.log("Task learnings:", task.learnings.own);
+```
+
+**If any answer is unclear:**
+1. Check parent task or completed blockers for details
+2. Suggest entering plan mode to flesh out requirements
+
+**Proceed without full context when:**
+- Task is trivial/atomic (e.g., "Add .gitignore entry")
+- Conversation already provides the missing context
+- Description itself is sufficiently detailed
+
+## 3. Start Task
+
+```javascript
+await tasks.start(taskId);
+```
+
+**VCS Required:** Creates bookmark `task/<id>`, records start commit. Fails with `NotARepository` if no jj/git found.
+
+After starting, the task status changes to `in_progress`.
+
+## 4. Implement
+
+Work on the task implementation. Note any learnings to include when completing.
+
+## 5. Verify Work
+
+Before completing, verify your implementation. See @file references/verification.md for full checklist.
+
+Quick checklist:
+- [ ] Task description requirements met
+- [ ] Context "Done when" criteria satisfied
+- [ ] Tests passing (document count)
+- [ ] Build succeeds
+- [ ] Manual testing done
+
+## 6. Complete Task with Learnings
+
+```javascript
+await tasks.complete(taskId, {
+  result: `Implemented login endpoint:
+
+Implementation:
+- Created src/auth/login.ts
+- Added JWT token generation
+- Integrated with user service
+
+Verification:
+- All 42 tests passing (3 new)
+- Manually tested valid/invalid credentials`,
+  learnings: [
+    "bcrypt rounds should be 12+ for production",
+    "jose library preferred over jsonwebtoken"
+  ]
+});
+```
+
+**VCS Required:** Commits changes (NothingToCommit treated as success), then deletes the task's bookmark (best-effort) and clears the DB bookmark field on success. Fails with `NotARepository` if no jj/git found.
+
+**Learnings Effect:** Learnings bubble to immediate parent only. `sourceTaskId` is preserved through bubbling, so if this task's learnings later bubble further, the origin is tracked.
+
+The `result` becomes part of the task's permanent record.
+
+## VCS Integration (Required for Workflow)
+
+VCS operations are **automatically handled** by the tasks API:
+
+| Task Operation | VCS Effect |
+|----------------|------------|
+| `tasks.start(id)` | **VCS required** - creates bookmark `task/<id>`, records start commit |
+| `tasks.complete(id)` | **VCS required** - commits changes, deletes bookmark (best-effort), clears DB bookmark on success |
+| `tasks.complete(milestoneId)` | Same + deletes ALL descendant bookmarks recursively (depth-1 and depth-2) |
+| `tasks.delete(id)` | Best-effort bookmark cleanup (logs warning on failure) |
+
+**Note:** VCS (jj or git) is required for start/complete. CRUD operations work without VCS.
+
+## Error Handling
+
+### Pending Children
+
+```javascript
+try {
+  await tasks.complete(taskId, "Done");
+} catch (err) {
+  if (err.message.includes("pending children")) {
+    const pending = await tasks.list({ parentId: taskId, completed: false });
+    return `Cannot complete: ${pending.length} children pending`;
+  }
+  throw err;
+}
+```
+
+### Task Not Ready
+
+```javascript
+const task = await tasks.get(taskId);
+
+// Check if blocked
+if (task.blockedBy.length > 0) {
+  console.log("Blocked by:", task.blockedBy);
+  // Complete blockers first or unblock
+  await tasks.unblock(taskId, blockerId);
+}
+```
+
+## Complete Workflow Example
+
+```javascript
+const task = await tasks.nextReady();
+if (!task) return "No ready tasks";
+
+await tasks.start(task.id);
+// ... implement ...
+await tasks.complete(task.id, {
+  result: "Implemented: ... Verification: All 58 tests passing",
+  learnings: ["Use jose for JWT"]
+});
+```
--- a/profiles/opencode/skill/solidjs/SKILL.md
+++ b/profiles/opencode/skill/solidjs/SKILL.md
@@ -0,0 +1,464 @@
+---
+name: solidjs
+description: |
+  SolidJS framework development skill for building reactive web applications with fine-grained reactivity.
+  Use when working with SolidJS projects including: (1) Creating components with signals, stores, and effects,
+  (2) Implementing reactive state management, (3) Using control flow components (Show, For, Switch/Match),
+  (4) Setting up routing with Solid Router, (5) Building full-stack apps with SolidStart,
+  (6) Data fetching with createResource, (7) Context API for shared state, (8) SSR/SSG configuration.
+  Triggers: solid, solidjs, solid-js, solid start, solidstart, createSignal, createStore, createEffect.
+---
+
+# SolidJS Development
+
+SolidJS is a declarative JavaScript library for building user interfaces with fine-grained reactivity. Unlike virtual DOM frameworks, Solid compiles templates to real DOM nodes and updates them with fine-grained reactions.
+
+## Core Principles
+
+1. **Components run once** — Component functions execute only during initialization, not on every update
+2. **Fine-grained reactivity** — Only the specific DOM nodes that depend on changed data update
+3. **No virtual DOM** — Direct DOM manipulation via compiled templates
+4. **Signals are functions** — Access values by calling: `count()` not `count`
+
+## Reactivity Primitives
+
+### Signals — Basic State
+
+```tsx
+import { createSignal } from "solid-js";
+
+const [count, setCount] = createSignal(0);
+
+// Read value (getter)
+console.log(count()); // 0
+
+// Update value (setter)
+setCount(1);
+setCount(prev => prev + 1); // Functional update
+```
+
+**Options:**
+```tsx
+const [value, setValue] = createSignal(initialValue, {
+  equals: false, // Always trigger updates, even if value unchanged
+  name: "debugName" // For devtools
+});
+```
+
+### Effects — Side Effects
+
+```tsx
+import { createEffect } from "solid-js";
+
+createEffect(() => {
+  console.log("Count changed:", count());
+  // Runs after render, re-runs when dependencies change
+});
+```
+
+**Key behaviors:**
+- Initial run: after render, before browser paint
+- Subsequent runs: when tracked dependencies change
+- Never runs during SSR or hydration
+- Use `onCleanup` for cleanup logic
+
+### Memos — Derived/Cached Values
+
+```tsx
+import { createMemo } from "solid-js";
+
+const doubled = createMemo(() => count() * 2);
+
+// Access like signal
+console.log(doubled()); // Cached, only recalculates when count changes
+```
+
+Use memos when:
+- Derived value is expensive to compute
+- Derived value is accessed multiple times
+- You want to prevent downstream updates when result unchanged
+
+### Resources — Async Data
+
+```tsx
+import { createResource } from "solid-js";
+
+const [user, { mutate, refetch }] = createResource(userId, fetchUser);
+
+// In JSX
+<Show when={!user.loading} fallback={<Loading />}>
+  <div>{user()?.name}</div>
+</Show>
+
+// Resource properties
+user.loading   // boolean
+user.error     // error if failed
+user.state     // "unresolved" | "pending" | "ready" | "refreshing" | "errored"
+user.latest    // last successful value
+```
+
+## Stores — Complex State
+
+For nested objects/arrays with fine-grained updates:
+
+```tsx
+import { createStore } from "solid-js/store";
+
+const [state, setState] = createStore({
+  user: { name: "John", age: 30 },
+  todos: []
+});
+
+// Path syntax updates
+setState("user", "name", "Jane");
+setState("todos", todos => [...todos, newTodo]);
+setState("todos", 0, "completed", true);
+
+// Produce for immer-like updates
+import { produce } from "solid-js/store";
+setState(produce(s => {
+  s.user.age++;
+  s.todos.push(newTodo);
+}));
+```
+
+**Store utilities:**
+- `produce` — Immer-like mutations
+- `reconcile` — Diff and patch data (for API responses)
+- `unwrap` — Get raw non-reactive object
+
+## Components
+
+### Basic Component
+
+```tsx
+import { Component } from "solid-js";
+
+const MyComponent: Component<{ name: string }> = (props) => {
+  return <div>Hello, {props.name}</div>;
+};
+```
+
+### Props Handling
+
+```tsx
+import { splitProps, mergeProps } from "solid-js";
+
+// Default props
+const merged = mergeProps({ size: "medium" }, props);
+
+// Split props (for spreading)
+const [local, others] = splitProps(props, ["class", "onClick"]);
+return <button class={local.class} {...others} />;
+```
+
+**Props rules:**
+- Props are reactive getters — don't destructure at top level
+- Use `props.value` in JSX, not `const { value } = props`
+
+### Children Helper
+
+```tsx
+import { children } from "solid-js";
+
+const Wrapper: Component = (props) => {
+  const resolved = children(() => props.children);
+
+  createEffect(() => {
+    console.log("Children:", resolved());
+  });
+
+  return <div>{resolved()}</div>;
+};
+```
+
+## Control Flow Components
+
+### Show — Conditional Rendering
+
+```tsx
+import { Show } from "solid-js";
+
+<Show when={user()} fallback={<Login />}>
+  {(user) => <Profile user={user()} />}
+</Show>
+```
+
+### For — List Rendering (keyed by reference)
+
+```tsx
+import { For } from "solid-js";
+
+<For each={items()} fallback={<Empty />}>
+  {(item, index) => (
+    <div>{index()}: {item.name}</div>
+  )}
+</For>
+```
+
+**Note:** `index` is a signal, `item` is the value.
+
+### Index — List Rendering (keyed by index)
+
+```tsx
+import { Index } from "solid-js";
+
+<Index each={items()}>
+  {(item, index) => (
+    <input value={item().text} />
+  )}
+</Index>
+```
+
+**Note:** `item` is a signal, `index` is the value. Better for primitive arrays or inputs.
+
+### Switch/Match — Multiple Conditions
+
+```tsx
+import { Switch, Match } from "solid-js";
+
+<Switch fallback={<Default />}>
+  <Match when={state() === "loading"}>
+    <Loading />
+  </Match>
+  <Match when={state() === "error"}>
+    <Error />
+  </Match>
+  <Match when={state() === "success"}>
+    <Success />
+  </Match>
+</Switch>
+```
+
+### Dynamic — Dynamic Component
+
+```tsx
+import { Dynamic } from "solid-js/web";
+
+<Dynamic component={selected()} someProp="value" />
+```
+
+### Portal — Render Outside DOM Hierarchy
+
+```tsx
+import { Portal } from "solid-js/web";
+
+<Portal mount={document.body}>
+  <Modal />
+</Portal>
+```
+
+### ErrorBoundary — Error Handling
+
+```tsx
+import { ErrorBoundary } from "solid-js";
+
+<ErrorBoundary fallback={(err, reset) => (
+  <div>
+    Error: {err.message}
+    <button onClick={reset}>Retry</button>
+  </div>
+)}>
+  <RiskyComponent />
+</ErrorBoundary>
+```
+
+### Suspense — Async Loading
+
+```tsx
+import { Suspense } from "solid-js";
+
+<Suspense fallback={<Loading />}>
+  <AsyncComponent />
+</Suspense>
+```
+
+## Context API
+
+```tsx
+import { createContext, useContext } from "solid-js";
+
+// Create context
+const CounterContext = createContext<{
+  count: () => number;
+  increment: () => void;
+}>();
+
+// Provider component
+export function CounterProvider(props) {
+  const [count, setCount] = createSignal(0);
+
+  return (
+    <CounterContext.Provider value={{
+      count,
+      increment: () => setCount(c => c + 1)
+    }}>
+      {props.children}
+    </CounterContext.Provider>
+  );
+}
+
+// Consumer hook
+export function useCounter() {
+  const ctx = useContext(CounterContext);
+  if (!ctx) throw new Error("useCounter must be used within CounterProvider");
+  return ctx;
+}
+```
+
+## Lifecycle
+
+```tsx
+import { onMount, onCleanup } from "solid-js";
+
+function MyComponent() {
+  onMount(() => {
+    console.log("Mounted");
+    const handler = () => {};
+    window.addEventListener("resize", handler);
+
+    onCleanup(() => {
+      window.removeEventListener("resize", handler);
+    });
+  });
+
+  return <div>Content</div>;
+}
+```
+
+## Refs
+
+```tsx
+let inputRef: HTMLInputElement;
+
+<input ref={inputRef} />
+<input ref={(el) => { /* el is the DOM element */ }} />
+```
+
+## Event Handling
+
+```tsx
+// Standard events (lowercase)
+<button onClick={handleClick}>Click</button>
+<button onClick={(e) => handleClick(e)}>Click</button>
+
+// Delegated events (on:)
+<input on:input={handleInput} />
+
+// Native events (on:) - not delegated
+<div on:scroll={handleScroll} />
+```
+
+## Common Patterns
+
+### Conditional Classes
+
+```tsx
+import { clsx } from "clsx"; // or classList
+
+<div class={clsx("base", { active: isActive() })} />
+<div classList={{ active: isActive(), disabled: isDisabled() }} />
+```
+
+### Batch Updates
+
+```tsx
+import { batch } from "solid-js";
+
+batch(() => {
+  setName("John");
+  setAge(30);
+  // Effects run once after batch completes
+});
+```
+
+### Untrack
+
+```tsx
+import { untrack } from "solid-js";
+
+createEffect(() => {
+  console.log(count()); // tracked
+  console.log(untrack(() => other())); // not tracked
+});
+```
+
+## TypeScript
+
+```tsx
+import type { Component, ParentComponent, JSX } from "solid-js";
+
+// Basic component
+const Button: Component<{ label: string }> = (props) => (
+  <button>{props.label}</button>
+);
+
+// With children
+const Layout: ParentComponent<{ title: string }> = (props) => (
+  <div>
+    <h1>{props.title}</h1>
+    {props.children}
+  </div>
+);
+
+// Event handler types
+const handleClick: JSX.EventHandler<HTMLButtonElement, MouseEvent> = (e) => {
+  console.log(e.currentTarget);
+};
+```
+
+## Project Setup
+
+```bash
+# Create new project
+npm create solid@latest my-app
+
+# With template
+npx degit solidjs/templates/ts my-app
+
+# SolidStart
+npm create solid@latest my-app -- --template solidstart
+```
+
+**vite.config.ts:**
+```ts
+import { defineConfig } from "vite";
+import solid from "vite-plugin-solid";
+
+export default defineConfig({
+  plugins: [solid()]
+});
+```
+
+## Anti-Patterns to Avoid
+
+1. **Destructuring props** — Breaks reactivity
+   ```tsx
+   // ❌ Bad
+   const { name } = props;
+
+   // ✅ Good
+   props.name
+   ```
+
+2. **Accessing signals outside tracking scope**
+   ```tsx
+   // ❌ Won't update
+   console.log(count());
+
+   // ✅ Will update
+   createEffect(() => console.log(count()));
+   ```
+
+3. **Forgetting to call signal getters**
+   ```tsx
+   // ❌ Passes the function
+   <div>{count}</div>
+
+   // ✅ Passes the value
+   <div>{count()}</div>
+   ```
+
+4. **Using array index as key** — Use `<For>` for reference-keyed, `<Index>` for index-keyed
+
+5. **Side effects during render** — Use `createEffect` or `onMount`
--- a/profiles/opencode/skill/solidjs/references/api_reference.md
+++ b/profiles/opencode/skill/solidjs/references/api_reference.md
@@ -0,0 +1,777 @@
+# SolidJS API Reference
+
+Complete reference for all SolidJS primitives, utilities, and component APIs.
+
+## Basic Reactivity
+
+### createSignal
+
+```tsx
+import { createSignal } from "solid-js";
+
+const [getter, setter] = createSignal<T>(initialValue, options?);
+
+// Options
+interface SignalOptions<T> {
+  equals?: false | ((prev: T, next: T) => boolean);
+  name?: string;
+  internal?: boolean;
+}
+```
+
+**Examples:**
+```tsx
+const [count, setCount] = createSignal(0);
+const [user, setUser] = createSignal<User | null>(null);
+
+// Always update
+const [data, setData] = createSignal(obj, { equals: false });
+
+// Custom equality
+const [items, setItems] = createSignal([], {
+  equals: (a, b) => a.length === b.length
+});
+
+// Setter forms
+setCount(5);                      // Direct value
+setCount(prev => prev + 1);       // Functional update
+```
+
+### createEffect
+
+```tsx
+import { createEffect } from "solid-js";
+
+createEffect<T>(fn: (prev: T) => T, initialValue?: T, options?);
+
+// Options
+interface EffectOptions {
+  name?: string;
+}
+```
+
+**Examples:**
+```tsx
+// Basic
+createEffect(() => {
+  console.log("Count:", count());
+});
+
+// With previous value
+createEffect((prev) => {
+  console.log("Changed from", prev, "to", count());
+  return count();
+}, count());
+
+// With cleanup
+createEffect(() => {
+  const handler = () => {};
+  window.addEventListener("resize", handler);
+  onCleanup(() => window.removeEventListener("resize", handler));
+});
+```
+
+### createMemo
+
+```tsx
+import { createMemo } from "solid-js";
+
+const getter = createMemo<T>(fn: (prev: T) => T, initialValue?: T, options?);
+
+// Options
+interface MemoOptions<T> {
+  equals?: false | ((prev: T, next: T) => boolean);
+  name?: string;
+}
+```
+
+**Examples:**
+```tsx
+const doubled = createMemo(() => count() * 2);
+const filtered = createMemo(() => items().filter(i => i.active));
+
+// Previous value
+const delta = createMemo((prev) => count() - prev, 0);
+```
+
+### createResource
+
+```tsx
+import { createResource } from "solid-js";
+
+const [resource, { mutate, refetch }] = createResource(
+  source?,      // Optional reactive source
+  fetcher,      // (source, info) => Promise<T>
+  options?
+);
+
+// Resource properties
+resource()           // T | undefined
+resource.loading     // boolean
+resource.error       // any
+resource.state       // "unresolved" | "pending" | "ready" | "refreshing" | "errored"
+resource.latest      // T | undefined (last successful value)
+
+// Options
+interface ResourceOptions<T> {
+  initialValue?: T;
+  name?: string;
+  deferStream?: boolean;
+  ssrLoadFrom?: "initial" | "server";
+  storage?: (init: T) => [Accessor<T>, Setter<T>];
+  onHydrated?: (key, info: { value: T }) => void;
+}
+```
+
+**Examples:**
+```tsx
+// Without source
+const [users] = createResource(fetchUsers);
+
+// With source
+const [user] = createResource(userId, fetchUser);
+
+// With options
+const [data] = createResource(id, fetchData, {
+  initialValue: [],
+  deferStream: true
+});
+
+// Actions
+mutate(newValue);           // Update locally
+refetch();                  // Re-fetch
+refetch(customInfo);        // Pass to fetcher's info.refetching
+```
+
+## Stores
+
+### createStore
+
+```tsx
+import { createStore } from "solid-js/store";
+
+const [store, setStore] = createStore<T>(initialValue);
+```
+
+**Update patterns:**
+```tsx
+const [state, setState] = createStore({
+  user: { name: "John", age: 30 },
+  todos: [{ id: 1, text: "Learn Solid", done: false }]
+});
+
+// Path syntax
+setState("user", "name", "Jane");
+setState("user", "age", a => a + 1);
+setState("todos", 0, "done", true);
+
+// Array operations
+setState("todos", t => [...t, newTodo]);
+setState("todos", todos.length, newTodo);
+
+// Multiple paths
+setState("todos", { from: 0, to: 2 }, "done", true);
+setState("todos", [0, 2, 4], "done", true);
+setState("todos", i => i.done, "done", false);
+
+// Object merge (shallow)
+setState("user", { age: 31 }); // Keeps other properties
+```
+
+### produce
+
+```tsx
+import { produce } from "solid-js/store";
+
+setState(produce(draft => {
+  draft.user.age++;
+  draft.todos.push({ id: 2, text: "New", done: false });
+  draft.todos[0].done = true;
+}));
+```
+
+### reconcile
+
+```tsx
+import { reconcile } from "solid-js/store";
+
+// Replace with diff (minimal updates)
+setState("todos", reconcile(newTodosFromAPI));
+
+// Options
+reconcile(data, { key: "id", merge: true });
+```
+
+### unwrap
+
+```tsx
+import { unwrap } from "solid-js/store";
+
+const raw = unwrap(store);  // Non-reactive plain object
+```
+
+### createMutable
+
+```tsx
+import { createMutable } from "solid-js/store";
+
+const state = createMutable({
+  count: 0,
+  user: { name: "John" }
+});
+
+// Direct mutation (like MobX)
+state.count++;
+state.user.name = "Jane";
+```
+
+### modifyMutable
+
+```tsx
+import { modifyMutable, reconcile, produce } from "solid-js/store";
+
+modifyMutable(state, reconcile(newData));
+modifyMutable(state, produce(s => { s.count++ }));
+```
+
+## Component APIs
+
+### children
+
+```tsx
+import { children } from "solid-js";
+
+const resolved = children(() => props.children);
+
+// Access
+resolved();           // JSX.Element | JSX.Element[]
+resolved.toArray();   // Always array
+```
+
+### createContext / useContext
+
+```tsx
+import { createContext, useContext } from "solid-js";
+
+const MyContext = createContext<T>(defaultValue?);
+
+// Provider
+<MyContext.Provider value={value}>
+  {children}
+</MyContext.Provider>
+
+// Consumer
+const value = useContext(MyContext);
+```
+
+### createUniqueId
+
+```tsx
+import { createUniqueId } from "solid-js";
+
+const id = createUniqueId();  // "0", "1", etc.
+```
+
+### lazy
+
+```tsx
+import { lazy } from "solid-js";
+
+const LazyComponent = lazy(() => import("./Component"));
+
+// Use with Suspense
+<Suspense fallback={<Loading />}>
+  <LazyComponent />
+</Suspense>
+```
+
+## Lifecycle
+
+### onMount
+
+```tsx
+import { onMount } from "solid-js";
+
+onMount(() => {
+  // Runs once after initial render
+  console.log("Mounted");
+});
+```
+
+### onCleanup
+
+```tsx
+import { onCleanup } from "solid-js";
+
+// In component
+onCleanup(() => {
+  console.log("Cleaning up");
+});
+
+// In effect
+createEffect(() => {
+  const sub = subscribe();
+  onCleanup(() => sub.unsubscribe());
+});
+```
+
+## Reactive Utilities
+
+### batch
+
+```tsx
+import { batch } from "solid-js";
+
+batch(() => {
+  setA(1);
+  setB(2);
+  setC(3);
+  // Effects run once after batch
+});
+```
+
+### untrack
+
+```tsx
+import { untrack } from "solid-js";
+
+createEffect(() => {
+  console.log(a());              // Tracked
+  console.log(untrack(() => b())); // Not tracked
+});
+```
+
+### on
+
+```tsx
+import { on } from "solid-js";
+
+// Explicit dependencies
+createEffect(on(count, (value, prev) => {
+  console.log("Count changed:", prev, "->", value);
+}));
+
+// Multiple dependencies
+createEffect(on([a, b], ([a, b], [prevA, prevB]) => {
+  console.log("Changed");
+}));
+
+// Defer first run
+createEffect(on(count, (v) => console.log(v), { defer: true }));
+```
+
+### mergeProps
+
+```tsx
+import { mergeProps } from "solid-js";
+
+const merged = mergeProps(
+  { size: "medium", color: "blue" },  // Defaults
+  props                                 // Overrides
+);
+```
+
+### splitProps
+
+```tsx
+import { splitProps } from "solid-js";
+
+const [local, others] = splitProps(props, ["class", "onClick"]);
+// local.class, local.onClick
+// others contains everything else
+
+const [a, b, rest] = splitProps(props, ["foo"], ["bar"]);
+```
+
+### createRoot
+
+```tsx
+import { createRoot } from "solid-js";
+
+const dispose = createRoot((dispose) => {
+  const [count, setCount] = createSignal(0);
+  // Use signals...
+  return dispose;
+});
+
+// Later
+dispose();
+```
+
+### getOwner / runWithOwner
+
+```tsx
+import { getOwner, runWithOwner } from "solid-js";
+
+const owner = getOwner();
+
+// Later, in async code
+runWithOwner(owner, () => {
+  createEffect(() => {
+    // This effect has proper ownership
+  });
+});
+```
+
+### mapArray
+
+```tsx
+import { mapArray } from "solid-js";
+
+const mapped = mapArray(
+  () => items(),
+  (item, index) => ({ ...item, doubled: item.value * 2 })
+);
+```
+
+### indexArray
+
+```tsx
+import { indexArray } from "solid-js";
+
+const mapped = indexArray(
+  () => items(),
+  (item, index) => <div>{index}: {item().name}</div>
+);
+```
+
+### observable
+
+```tsx
+import { observable } from "solid-js";
+
+const obs = observable(signal);
+obs.subscribe((value) => console.log(value));
+```
+
+### from
+
+```tsx
+import { from } from "solid-js";
+
+// Convert observable/subscribable to signal
+const signal = from(rxObservable);
+const signal = from((set) => {
+  const unsub = subscribe(set);
+  return unsub;
+});
+```
+
+### catchError
+
+```tsx
+import { catchError } from "solid-js";
+
+catchError(
+  () => riskyOperation(),
+  (err) => console.error("Error:", err)
+);
+```
+
+## Secondary Primitives
+
+### createComputed
+
+```tsx
+import { createComputed } from "solid-js";
+
+// Like createEffect but runs during render phase
+createComputed(() => {
+  setDerived(source() * 2);
+});
+```
+
+### createRenderEffect
+
+```tsx
+import { createRenderEffect } from "solid-js";
+
+// Runs before paint (for DOM measurements)
+createRenderEffect(() => {
+  const height = element.offsetHeight;
+});
+```
+
+### createDeferred
+
+```tsx
+import { createDeferred } from "solid-js";
+
+// Returns value after idle time
+const deferred = createDeferred(() => expensiveComputation(), {
+  timeoutMs: 1000
+});
+```
+
+### createReaction
+
+```tsx
+import { createReaction } from "solid-js";
+
+const track = createReaction(() => {
+  console.log("Something changed");
+});
+
+track(() => count()); // Start tracking
+```
+
+### createSelector
+
+```tsx
+import { createSelector } from "solid-js";
+
+const isSelected = createSelector(selectedId);
+
+<For each={items()}>
+  {(item) => (
+    <div class={isSelected(item.id) ? "selected" : ""}>
+      {item.name}
+    </div>
+  )}
+</For>
+```
+
+## Components
+
+### Show
+
+```tsx
+<Show when={condition()} fallback={<Fallback />}>
+  <Content />
+</Show>
+
+// With callback (narrowed type)
+<Show when={user()}>
+  {(user) => <div>{user().name}</div>}
+</Show>
+```
+
+### For
+
+```tsx
+<For each={items()} fallback={<Empty />}>
+  {(item, index) => <div>{index()}: {item.name}</div>}
+</For>
+```
+
+### Index
+
+```tsx
+<Index each={items()} fallback={<Empty />}>
+  {(item, index) => <input value={item().text} />}
+</Index>
+```
+
+### Switch / Match
+
+```tsx
+<Switch fallback={<Default />}>
+  <Match when={state() === "loading"}>
+    <Loading />
+  </Match>
+  <Match when={state() === "error"}>
+    <Error />
+  </Match>
+</Switch>
+```
+
+### Dynamic
+
+```tsx
+import { Dynamic } from "solid-js/web";
+
+<Dynamic component={selected()} prop={value} />
+<Dynamic component="div" class="dynamic">Content</Dynamic>
+```
+
+### Portal
+
+```tsx
+import { Portal } from "solid-js/web";
+
+<Portal mount={document.body}>
+  <Modal />
+</Portal>
+```
+
+### ErrorBoundary
+
+```tsx
+<ErrorBoundary fallback={(err, reset) => (
+  <div>
+    <p>Error: {err.message}</p>
+    <button onClick={reset}>Retry</button>
+  </div>
+)}>
+  <Content />
+</ErrorBoundary>
+```
+
+### Suspense
+
+```tsx
+<Suspense fallback={<Loading />}>
+  <AsyncContent />
+</Suspense>
+```
+
+### SuspenseList
+
+```tsx
+<SuspenseList revealOrder="forwards" tail="collapsed">
+  <Suspense fallback={<Loading />}><Item1 /></Suspense>
+  <Suspense fallback={<Loading />}><Item2 /></Suspense>
+  <Suspense fallback={<Loading />}><Item3 /></Suspense>
+</SuspenseList>
+```
+
+## Rendering
+
+### render
+
+```tsx
+import { render } from "solid-js/web";
+
+const dispose = render(() => <App />, document.getElementById("root")!);
+
+// Cleanup
+dispose();
+```
+
+### hydrate
+
+```tsx
+import { hydrate } from "solid-js/web";
+
+hydrate(() => <App />, document.getElementById("root")!);
+```
+
+### renderToString
+
+```tsx
+import { renderToString } from "solid-js/web";
+
+const html = renderToString(() => <App />);
+```
+
+### renderToStringAsync
+
+```tsx
+import { renderToStringAsync } from "solid-js/web";
+
+const html = await renderToStringAsync(() => <App />);
+```
+
+### renderToStream
+
+```tsx
+import { renderToStream } from "solid-js/web";
+
+const stream = renderToStream(() => <App />);
+stream.pipe(res);
+```
+
+### isServer
+
+```tsx
+import { isServer } from "solid-js/web";
+
+if (isServer) {
+  // Server-only code
+}
+```
+
+## JSX Attributes
+
+### ref
+
+```tsx
+let el: HTMLDivElement;
+<div ref={el} />
+<div ref={(e) => console.log(e)} />
+```
+
+### classList
+
+```tsx
+<div classList={{ active: isActive(), disabled: isDisabled() }} />
+```
+
+### style
+
+```tsx
+<div style={{ color: "red", "font-size": "14px" }} />
+<div style={`color: ${color()}`} />
+```
+
+### on:event (native)
+
+```tsx
+<div on:click={handleClick} />
+<div on:scroll={handleScroll} />
+```
+
+### use:directive
+
+```tsx
+function clickOutside(el: HTMLElement, accessor: () => () => void) {
+  const handler = (e: MouseEvent) => {
+    if (!el.contains(e.target as Node)) accessor()();
+  };
+  document.addEventListener("click", handler);
+  onCleanup(() => document.removeEventListener("click", handler));
+}
+
+<div use:clickOutside={() => setOpen(false)} />
+```
+
+### prop:property
+
+```tsx
+<input prop:value={value()} />  // Set as property, not attribute
+```
+
+### attr:attribute
+
+```tsx
+<div attr:data-custom={value()} />  // Force attribute
+```
+
+### bool:attribute
+
+```tsx
+<input bool:disabled={isDisabled()} />
+```
+
+### @once
+
+```tsx
+<div title={/*@once*/ staticValue} />  // Never updates
+```
+
+## Types
+
+```tsx
+import type {
+  Component,
+  ParentComponent,
+  FlowComponent,
+  VoidComponent,
+  JSX,
+  Accessor,
+  Setter,
+  Signal,
+  Resource,
+  Owner
+} from "solid-js";
+
+// Component types
+const MyComponent: Component<Props> = (props) => <div />;
+const Parent: ParentComponent<Props> = (props) => <div>{props.children}</div>;
+const Flow: FlowComponent<Props, Item> = (props) => props.children(item);
+const Void: VoidComponent<Props> = (props) => <input />;
+
+// Event types
+type Handler = JSX.EventHandler<HTMLButtonElement, MouseEvent>;
+type ChangeHandler = JSX.ChangeEventHandler<HTMLInputElement>;
+```
--- a/profiles/opencode/skill/solidjs/references/patterns.md
+++ b/profiles/opencode/skill/solidjs/references/patterns.md
@@ -0,0 +1,720 @@
+# SolidJS Patterns & Best Practices
+
+Common patterns, recipes, and best practices for SolidJS development.
+
+## Component Patterns
+
+### Controlled vs Uncontrolled Inputs
+
+**Controlled:**
+```tsx
+function ControlledInput() {
+  const [value, setValue] = createSignal("");
+
+  return (
+    <input
+      value={value()}
+      onInput={(e) => setValue(e.currentTarget.value)}
+    />
+  );
+}
+```
+
+**Uncontrolled with ref:**
+```tsx
+function UncontrolledInput() {
+  let inputRef: HTMLInputElement;
+
+  const handleSubmit = () => {
+    console.log(inputRef.value);
+  };
+
+  return (
+    <>
+      <input ref={inputRef!} />
+      <button onClick={handleSubmit}>Submit</button>
+    </>
+  );
+}
+```
+
+### Compound Components
+
+```tsx
+const Tabs = {
+  Root: (props: ParentProps<{ defaultTab?: string }>) => {
+    const [activeTab, setActiveTab] = createSignal(props.defaultTab ?? "");
+
+    return (
+      <TabsContext.Provider value={{ activeTab, setActiveTab }}>
+        <div class="tabs">{props.children}</div>
+      </TabsContext.Provider>
+    );
+  },
+
+  List: (props: ParentProps) => (
+    <div class="tabs-list" role="tablist">{props.children}</div>
+  ),
+
+  Tab: (props: ParentProps<{ value: string }>) => {
+    const ctx = useTabsContext();
+    return (
+      <button
+        role="tab"
+        aria-selected={ctx.activeTab() === props.value}
+        onClick={() => ctx.setActiveTab(props.value)}
+      >
+        {props.children}
+      </button>
+    );
+  },
+
+  Panel: (props: ParentProps<{ value: string }>) => {
+    const ctx = useTabsContext();
+    return (
+      <Show when={ctx.activeTab() === props.value}>
+        <div role="tabpanel">{props.children}</div>
+      </Show>
+    );
+  }
+};
+
+// Usage
+<Tabs.Root defaultTab="first">
+  <Tabs.List>
+    <Tabs.Tab value="first">First</Tabs.Tab>
+    <Tabs.Tab value="second">Second</Tabs.Tab>
+  </Tabs.List>
+  <Tabs.Panel value="first">First Content</Tabs.Panel>
+  <Tabs.Panel value="second">Second Content</Tabs.Panel>
+</Tabs.Root>
+```
+
+### Render Props
+
+```tsx
+function MouseTracker(props: {
+  children: (pos: { x: number; y: number }) => JSX.Element;
+}) {
+  const [pos, setPos] = createSignal({ x: 0, y: 0 });
+
+  onMount(() => {
+    const handler = (e: MouseEvent) => setPos({ x: e.clientX, y: e.clientY });
+    window.addEventListener("mousemove", handler);
+    onCleanup(() => window.removeEventListener("mousemove", handler));
+  });
+
+  return <>{props.children(pos())}</>;
+}
+
+// Usage
+<MouseTracker>
+  {(pos) => <div>Mouse: {pos.x}, {pos.y}</div>}
+</MouseTracker>
+```
+
+### Higher-Order Components
+
+```tsx
+function withAuth<P extends object>(Component: Component<P>) {
+  return (props: P) => {
+    const { user } = useAuth();
+
+    return (
+      <Show when={user()} fallback={<Redirect to="/login" />}>
+        <Component {...props} />
+      </Show>
+    );
+  };
+}
+
+const ProtectedDashboard = withAuth(Dashboard);
+```
+
+### Polymorphic Components
+
+```tsx
+type PolymorphicProps<E extends keyof JSX.IntrinsicElements> = {
+  as?: E;
+} & JSX.IntrinsicElements[E];
+
+function Box<E extends keyof JSX.IntrinsicElements = "div">(
+  props: PolymorphicProps<E>
+) {
+  const [local, others] = splitProps(props as PolymorphicProps<"div">, ["as"]);
+
+  return <Dynamic component={local.as || "div"} {...others} />;
+}
+
+// Usage
+<Box>Default div</Box>
+<Box as="section">Section element</Box>
+<Box as="button" onClick={handleClick}>Button</Box>
+```
+
+## State Patterns
+
+### Derived State with Multiple Sources
+
+```tsx
+function SearchResults() {
+  const [query, setQuery] = createSignal("");
+  const [filters, setFilters] = createSignal({ category: "all" });
+
+  const results = createMemo(() => {
+    const q = query().toLowerCase();
+    const f = filters();
+
+    return allItems()
+      .filter(item => item.name.toLowerCase().includes(q))
+      .filter(item => f.category === "all" || item.category === f.category);
+  });
+
+  return <For each={results()}>{item => <Item item={item} />}</For>;
+}
+```
+
+### State Machine Pattern
+
+```tsx
+type State = "idle" | "loading" | "success" | "error";
+type Event = { type: "FETCH" } | { type: "SUCCESS"; data: any } | { type: "ERROR"; error: Error };
+
+function createMachine(initial: State) {
+  const [state, setState] = createSignal<State>(initial);
+  const [data, setData] = createSignal<any>(null);
+  const [error, setError] = createSignal<Error | null>(null);
+
+  const send = (event: Event) => {
+    const current = state();
+
+    switch (current) {
+      case "idle":
+        if (event.type === "FETCH") setState("loading");
+        break;
+      case "loading":
+        if (event.type === "SUCCESS") {
+          setData(event.data);
+          setState("success");
+        } else if (event.type === "ERROR") {
+          setError(event.error);
+          setState("error");
+        }
+        break;
+    }
+  };
+
+  return { state, data, error, send };
+}
+```
+
+### Optimistic Updates
+
+```tsx
+const [todos, setTodos] = createStore<Todo[]>([]);
+
+async function deleteTodo(id: string) {
+  const original = [...unwrap(todos)];
+
+  // Optimistic remove
+  setTodos(todos => todos.filter(t => t.id !== id));
+
+  try {
+    await api.deleteTodo(id);
+  } catch {
+    // Rollback on error
+    setTodos(reconcile(original));
+  }
+}
+```
+
+### Undo/Redo
+
+```tsx
+function createHistory<T>(initial: T) {
+  const [past, setPast] = createSignal<T[]>([]);
+  const [present, setPresent] = createSignal<T>(initial);
+  const [future, setFuture] = createSignal<T[]>([]);
+
+  const canUndo = () => past().length > 0;
+  const canRedo = () => future().length > 0;
+
+  const set = (value: T | ((prev: T) => T)) => {
+    const newValue = typeof value === "function"
+      ? (value as (prev: T) => T)(present())
+      : value;
+
+    setPast(p => [...p, present()]);
+    setPresent(newValue);
+    setFuture([]);
+  };
+
+  const undo = () => {
+    if (!canUndo()) return;
+
+    const previous = past()[past().length - 1];
+    setPast(p => p.slice(0, -1));
+    setFuture(f => [present(), ...f]);
+    setPresent(previous);
+  };
+
+  const redo = () => {
+    if (!canRedo()) return;
+
+    const next = future()[0];
+    setPast(p => [...p, present()]);
+    setFuture(f => f.slice(1));
+    setPresent(next);
+  };
+
+  return { value: present, set, undo, redo, canUndo, canRedo };
+}
+```
+
+## Custom Hooks/Primitives
+
+### useLocalStorage
+
+```tsx
+function createLocalStorage<T>(key: string, initialValue: T) {
+  const stored = localStorage.getItem(key);
+  const initial = stored ? JSON.parse(stored) : initialValue;
+
+  const [value, setValue] = createSignal<T>(initial);
+
+  createEffect(() => {
+    localStorage.setItem(key, JSON.stringify(value()));
+  });
+
+  return [value, setValue] as const;
+}
+```
+
+### useDebounce
+
+```tsx
+function createDebounce<T>(source: () => T, delay: number) {
+  const [debounced, setDebounced] = createSignal<T>(source());
+
+  createEffect(() => {
+    const value = source();
+    const timer = setTimeout(() => setDebounced(() => value), delay);
+    onCleanup(() => clearTimeout(timer));
+  });
+
+  return debounced;
+}
+
+// Usage
+const debouncedQuery = createDebounce(query, 300);
+```
+
+### useThrottle
+
+```tsx
+function createThrottle<T>(source: () => T, delay: number) {
+  const [throttled, setThrottled] = createSignal<T>(source());
+  let lastRun = 0;
+
+  createEffect(() => {
+    const value = source();
+    const now = Date.now();
+
+    if (now - lastRun >= delay) {
+      lastRun = now;
+      setThrottled(() => value);
+    } else {
+      const timer = setTimeout(() => {
+        lastRun = Date.now();
+        setThrottled(() => value);
+      }, delay - (now - lastRun));
+      onCleanup(() => clearTimeout(timer));
+    }
+  });
+
+  return throttled;
+}
+```
+
+### useMediaQuery
+
+```tsx
+function createMediaQuery(query: string) {
+  const mql = window.matchMedia(query);
+  const [matches, setMatches] = createSignal(mql.matches);
+
+  onMount(() => {
+    const handler = (e: MediaQueryListEvent) => setMatches(e.matches);
+    mql.addEventListener("change", handler);
+    onCleanup(() => mql.removeEventListener("change", handler));
+  });
+
+  return matches;
+}
+
+// Usage
+const isMobile = createMediaQuery("(max-width: 768px)");
+```
+
+### useClickOutside
+
+```tsx
+function createClickOutside(
+  ref: () => HTMLElement | undefined,
+  callback: () => void
+) {
+  onMount(() => {
+    const handler = (e: MouseEvent) => {
+      const el = ref();
+      if (el && !el.contains(e.target as Node)) {
+        callback();
+      }
+    };
+    document.addEventListener("click", handler);
+    onCleanup(() => document.removeEventListener("click", handler));
+  });
+}
+
+// Usage
+let dropdownRef: HTMLDivElement;
+createClickOutside(() => dropdownRef, () => setOpen(false));
+```
+
+### useIntersectionObserver
+
+```tsx
+function createIntersectionObserver(
+  ref: () => HTMLElement | undefined,
+  options?: IntersectionObserverInit
+) {
+  const [isIntersecting, setIsIntersecting] = createSignal(false);
+
+  onMount(() => {
+    const el = ref();
+    if (!el) return;
+
+    const observer = new IntersectionObserver(([entry]) => {
+      setIsIntersecting(entry.isIntersecting);
+    }, options);
+
+    observer.observe(el);
+    onCleanup(() => observer.disconnect());
+  });
+
+  return isIntersecting;
+}
+```
+
+## Form Patterns
+
+### Form Validation
+
+```tsx
+function createForm<T extends Record<string, any>>(initial: T) {
+  const [values, setValues] = createStore<T>(initial);
+  const [errors, setErrors] = createStore<Partial<Record<keyof T, string>>>({});
+  const [touched, setTouched] = createStore<Partial<Record<keyof T, boolean>>>({});
+
+  const handleChange = (field: keyof T) => (e: Event) => {
+    const target = e.target as HTMLInputElement;
+    setValues(field as any, target.value as any);
+  };
+
+  const handleBlur = (field: keyof T) => () => {
+    setTouched(field as any, true);
+  };
+
+  const validate = (validators: Partial<Record<keyof T, (v: any) => string | undefined>>) => {
+    let isValid = true;
+
+    for (const [field, validator] of Object.entries(validators)) {
+      if (validator) {
+        const error = validator(values[field as keyof T]);
+        setErrors(field as any, error as any);
+        if (error) isValid = false;
+      }
+    }
+
+    return isValid;
+  };
+
+  return { values, errors, touched, handleChange, handleBlur, validate, setValues };
+}
+
+// Usage
+const form = createForm({ email: "", password: "" });
+
+<input
+  value={form.values.email}
+  onInput={form.handleChange("email")}
+  onBlur={form.handleBlur("email")}
+/>
+<Show when={form.touched.email && form.errors.email}>
+  <span class="error">{form.errors.email}</span>
+</Show>
+```
+
+### Field Array
+
+```tsx
+function createFieldArray<T>(initial: T[] = []) {
+  const [fields, setFields] = createStore<T[]>(initial);
+
+  const append = (value: T) => setFields(f => [...f, value]);
+  const remove = (index: number) => setFields(f => f.filter((_, i) => i !== index));
+  const update = (index: number, value: Partial<T>) => setFields(index, v => ({ ...v, ...value }));
+  const move = (from: number, to: number) => {
+    setFields(produce(f => {
+      const [item] = f.splice(from, 1);
+      f.splice(to, 0, item);
+    }));
+  };
+
+  return { fields, append, remove, update, move };
+}
+```
+
+## Performance Patterns
+
+### Virtualized List
+
+```tsx
+function VirtualList<T>(props: {
+  items: T[];
+  itemHeight: number;
+  height: number;
+  renderItem: (item: T, index: number) => JSX.Element;
+}) {
+  const [scrollTop, setScrollTop] = createSignal(0);
+
+  const startIndex = createMemo(() =>
+    Math.floor(scrollTop() / props.itemHeight)
+  );
+
+  const visibleCount = createMemo(() =>
+    Math.ceil(props.height / props.itemHeight) + 1
+  );
+
+  const visibleItems = createMemo(() =>
+    props.items.slice(startIndex(), startIndex() + visibleCount())
+  );
+
+  return (
+    <div
+      style={{ height: `${props.height}px`, overflow: "auto" }}
+      onScroll={(e) => setScrollTop(e.currentTarget.scrollTop)}
+    >
+      <div style={{ height: `${props.items.length * props.itemHeight}px`, position: "relative" }}>
+        <For each={visibleItems()}>
+          {(item, i) => (
+            <div style={{
+              position: "absolute",
+              top: `${(startIndex() + i()) * props.itemHeight}px`,
+              height: `${props.itemHeight}px`
+            }}>
+              {props.renderItem(item, startIndex() + i())}
+            </div>
+          )}
+        </For>
+      </div>
+    </div>
+  );
+}
+```
+
+### Lazy Loading with Intersection Observer
+
+```tsx
+function LazyLoad(props: ParentProps<{ placeholder?: JSX.Element }>) {
+  let ref: HTMLDivElement;
+  const [isVisible, setIsVisible] = createSignal(false);
+
+  onMount(() => {
+    const observer = new IntersectionObserver(
+      ([entry]) => {
+        if (entry.isIntersecting) {
+          setIsVisible(true);
+          observer.disconnect();
+        }
+      },
+      { rootMargin: "100px" }
+    );
+    observer.observe(ref);
+    onCleanup(() => observer.disconnect());
+  });
+
+  return (
+    <div ref={ref!}>
+      <Show when={isVisible()} fallback={props.placeholder}>
+        {props.children}
+      </Show>
+    </div>
+  );
+}
+```
+
+### Memoized Component
+
+```tsx
+// For expensive components that shouldn't re-render on parent updates
+function MemoizedExpensiveList(props: { items: Item[] }) {
+  // Component only re-renders when items actually change
+  return (
+    <For each={props.items}>
+      {(item) => <ExpensiveItem item={item} />}
+    </For>
+  );
+}
+```
+
+## Testing Patterns
+
+### Component Testing
+
+```tsx
+import { render, fireEvent, screen } from "@solidjs/testing-library";
+
+test("Counter increments", async () => {
+  render(() => <Counter />);
+
+  const button = screen.getByRole("button", { name: /increment/i });
+  expect(screen.getByText("Count: 0")).toBeInTheDocument();
+
+  fireEvent.click(button);
+  expect(screen.getByText("Count: 1")).toBeInTheDocument();
+});
+```
+
+### Testing with Context
+
+```tsx
+function renderWithContext(component: () => JSX.Element) {
+  return render(() => (
+    <ThemeProvider>
+      <AuthProvider>
+        {component()}
+      </AuthProvider>
+    </ThemeProvider>
+  ));
+}
+
+test("Dashboard shows user", () => {
+  renderWithContext(() => <Dashboard />);
+  // ...
+});
+```
+
+### Testing Async Components
+
+```tsx
+import { render, waitFor, screen } from "@solidjs/testing-library";
+
+test("Loads user data", async () => {
+  render(() => <UserProfile userId="123" />);
+
+  expect(screen.getByText(/loading/i)).toBeInTheDocument();
+
+  await waitFor(() => {
+    expect(screen.getByText("John Doe")).toBeInTheDocument();
+  });
+});
+```
+
+## Error Handling Patterns
+
+### Global Error Handler
+
+```tsx
+function App() {
+  return (
+    <ErrorBoundary
+      fallback={(err, reset) => (
+        <ErrorPage error={err} onRetry={reset} />
+      )}
+    >
+      <Suspense fallback={<AppLoader />}>
+        <Router>
+          {/* Routes */}
+        </Router>
+      </Suspense>
+    </ErrorBoundary>
+  );
+}
+```
+
+### Async Error Handling
+
+```tsx
+function DataComponent() {
+  const [data] = createResource(fetchData);
+
+  return (
+    <Switch>
+      <Match when={data.loading}>
+        <Loading />
+      </Match>
+      <Match when={data.error}>
+        <Error error={data.error} onRetry={() => refetch()} />
+      </Match>
+      <Match when={data()}>
+        {(data) => <Content data={data()} />}
+      </Match>
+    </Switch>
+  );
+}
+```
+
+## Accessibility Patterns
+
+### Focus Management
+
+```tsx
+function Modal(props: ParentProps<{ isOpen: boolean; onClose: () => void }>) {
+  let dialogRef: HTMLDivElement;
+  let previousFocus: HTMLElement | null;
+
+  createEffect(() => {
+    if (props.isOpen) {
+      previousFocus = document.activeElement as HTMLElement;
+      dialogRef.focus();
+    } else if (previousFocus) {
+      previousFocus.focus();
+    }
+  });
+
+  return (
+    <Show when={props.isOpen}>
+      <Portal>
+        <div
+          ref={dialogRef!}
+          role="dialog"
+          aria-modal="true"
+          tabIndex={-1}
+          onKeyDown={(e) => e.key === "Escape" && props.onClose()}
+        >
+          {props.children}
+        </div>
+      </Portal>
+    </Show>
+  );
+}
+```
+
+### Live Regions
+
+```tsx
+function Notifications() {
+  const [message, setMessage] = createSignal("");
+
+  return (
+    <div
+      role="status"
+      aria-live="polite"
+      aria-atomic="true"
+      class="sr-only"
+    >
+      {message()}
+    </div>
+  );
+}
+```
--- a/profiles/opencode/skill/spec-planner/SKILL.md
+++ b/profiles/opencode/skill/spec-planner/SKILL.md
@@ -0,0 +1,223 @@
+---
+name: spec-planner
+description: Dialogue-driven spec development through skeptical questioning and iterative refinement. Triggers: "spec this out", feature planning, architecture decisions, "is this worth it?" questions, RFC/design doc creation, work scoping. Invoke Librarian for unfamiliar tech/frameworks/APIs.
+---
+
+# Spec Planner
+
+Produce implementation-ready specs through rigorous dialogue and honest trade-off analysis.
+
+## Core Philosophy
+
+- **Dialogue over deliverables** - Plans emerge from discussion, not assumption
+- **Skeptical by default** - Requirements are incomplete until proven otherwise
+- **Second-order thinking** - Consider downstream effects and maintenance burden
+
+## Workflow Phases
+
+```
+CLARIFY --[user responds]--> DISCOVER --[done]--> DRAFT --[complete]--> REFINE --[approved]--> DONE
+   |                            |                   |                      |
+   +--[still ambiguous]--<------+-------------------+----[gaps found]------+
+```
+
+**State phase at end of every response:**
+```
+---
+Phase: CLARIFY | Waiting for: answers to questions 1-4
+```
+
+---
+
+## Phase 1: CLARIFY (Mandatory)
+
+**Hard rule:** No spec until user has responded to at least one round of questions.
+
+1. **STOP.** Do not proceed to planning.
+2. Identify gaps in: scope, motivation, constraints, edge cases, success criteria
+3. Ask 3-5 pointed questions that would change the approach. USE YOUR QUESTION TOOL. 
+4. **Wait for responses**
+
+**IMPORTANT: Always use the `question` tool to ask clarifying questions.** Do NOT output questions as freeform text. The question tool provides structured options and better UX. Example:
+
+```
+question({
+  questions: [{
+    header: "Scope",
+    question: "Which subsystems need detailed specs?",
+    options: [
+      { label: "VCS layer", description: "jj-lib + gix unified interface" },
+      { label: "Review workflow", description: "GitHub PR-style local review" },
+      { label: "Event system", description: "pub/sub + persistence" }
+    ],
+    multiple: true
+  }]
+})
+```
+
+| Category | Example |
+|----------|---------|
+| Scope | "Share where? Social media? Direct link? Embed?" |
+| Motivation | "What user problem are we actually solving?" |
+| Constraints | "Does this need to work with existing privacy settings?" |
+| Success | "How will we know this worked?" |
+
+**Escape prevention:** Even if request seems complete, ask 2+ clarifying questions. Skip only for mechanical requests (e.g., "rename X to Y").
+
+**Anti-patterns to resist:**
+- "Just give me a rough plan" -> Still needs scope questions
+- "I'll figure out the details" -> Those details ARE the spec
+- Very long initial request -> Longer != clearer; probe assumptions
+
+**Transition:** User answered AND no new ambiguities -> DISCOVER
+
+---
+
+## Phase 2: DISCOVER
+
+**After clarification, before planning:** Understand existing system.
+
+Launch explore subagents in parallel:
+
+```
+Task(
+  subagent_type="explore",
+  description="Explore [area name]",
+  prompt="Explore [area]. Return: key files, abstractions, patterns, integration points."
+)
+```
+
+| Target | What to Find |
+|--------|--------------|
+| Affected area | Files, modules that will change |
+| Existing patterns | How similar features are implemented |
+| Integration points | APIs, events, data flows touched |
+
+**If unfamiliar tech involved**, invoke Librarian:
+
+```
+Task(
+  subagent_type="librarian",
+  description="Research [tech name]",
+  prompt="Research [tech] for [use case]. Return: recommended approach, gotchas, production patterns."
+)
+```
+
+**Output:** Brief architecture summary before proposing solutions.
+
+**Transition:** System context understood -> DRAFT
+
+---
+
+## Phase 3: DRAFT
+
+Apply planning framework from [decision-frameworks.md](./references/decision-frameworks.md):
+
+1. **Problem Definition** - What are we solving? For whom? Cost of not solving?
+2. **Constraints Inventory** - Time, system, knowledge, scope ceiling
+3. **Solution Space** - Simplest -> Balanced -> Full engineering solution
+4. **Trade-off Analysis** - See table format in references
+5. **Recommendation** - One clear choice with reasoning
+
+Use appropriate template from [templates.md](./references/templates.md):
+- **Quick Decision** - Scoped technical choices
+- **Feature Plan** - New feature development  
+- **ADR** - Architecture decisions
+- **RFC** - Larger proposals
+
+**Transition:** Spec produced -> REFINE
+
+---
+
+## Phase 4: REFINE
+
+Run completeness check:
+
+| Criterion | Check |
+|-----------|-------|
+| Scope bounded | Every deliverable listed; non-goals explicit |
+| Ambiguity resolved | No "TBD" or "to be determined" |
+| Acceptance testable | Each criterion pass/fail verifiable |
+| Dependencies ordered | Clear what blocks what |
+| Types defined | Data shapes specified (not "some object") |
+| Effort estimated | Each deliverable has S/M/L/XL |
+| Risks identified | At least 2 risks with mitigations |
+| Open questions | Resolved OR assigned owner |
+
+**If any criterion fails:** Return to dialogue. "To finalize, I need clarity on: [failing criteria]."
+
+**Transition:** All criteria pass + user approval -> DONE
+
+---
+
+## Phase 5: DONE
+
+### Final Output
+
+```
+=== Spec Complete ===
+
+Phase: DONE
+Type: <feature plan | architecture decision | refactoring | strategy>
+Effort: <S/M/L/XL>
+Status: Ready for task breakdown
+
+Discovery:
+- Explored: <areas investigated>
+- Key findings: <relevant architecture/patterns>
+
+Recommendation:
+<brief summary>
+
+Key Trade-offs:
+- <what we're choosing vs alternatives>
+
+Deliverables (Ordered):
+1. [D1] (effort) - depends on: -
+2. [D2] (effort) - depends on: D1
+
+Open Questions:
+- [ ] <if any remain> -> Owner: [who]
+```
+
+### Write Spec to File (MANDATORY)
+
+1. Derive filename from feature/decision name (kebab-case)
+2. Write spec to `specs/<filename>.md`
+3. Confirm: `Spec written to: specs/<filename>.md`
+
+---
+
+## Effort Estimates
+
+| Size | Time | Scope |
+|------|------|-------|
+| **S** | <1 hour | Single file, isolated change |
+| **M** | 1-3 hours | Few files, contained feature |
+| **L** | 1-2 days | Cross-cutting, multiple components |
+| **XL** | >2 days | Major refactor, new system |
+
+## Scope Control
+
+When scope creeps:
+1. **Name it:** "That's scope expansion. Let's finish X first."
+2. **Park it:** "Added to Open Questions. Revisit after core spec stable."
+3. **Cost it:** "Adding Y changes effort from M to XL. Worth it?"
+
+**Hard rule:** If scope changes, re-estimate and flag explicitly.
+
+## References
+
+| File | When to Read |
+|------|--------------|
+| [templates.md](./references/templates.md) | Output formats for plans, ADRs, RFCs |
+| [decision-frameworks.md](./references/decision-frameworks.md) | Complex multi-factor decisions |
+| [estimation.md](./references/estimation.md) | Breaking down work, avoiding underestimation |
+| [technical-debt.md](./references/technical-debt.md) | Evaluating refactoring ROI |
+
+## Integration
+
+| Agent | When to Invoke |
+|-------|----------------|
+| **Librarian** | Research unfamiliar tech, APIs, frameworks |
+| **Oracle** | Deep architectural analysis, complex debugging |
--- a/profiles/opencode/skill/spec-planner/references/decision-frameworks.md
+++ b/profiles/opencode/skill/spec-planner/references/decision-frameworks.md
@@ -0,0 +1,75 @@
+# Decision Frameworks
+
+## Reversibility Matrix
+
+| Decision Type | Approach |
+|---------------|----------|
+| **Two-way door** (easily reversed) | Decide fast, learn from outcome |
+| **One-way door** (hard to reverse) | Invest time in analysis |
+
+Most decisions are two-way doors. Don't over-analyze.
+
+## Cost of Delay
+
+```
+Daily Cost = (Value Delivered / Time to Deliver) x Risk Factor
+```
+
+Use when prioritizing:
+- High daily cost -> Do first
+- Low daily cost -> Can wait
+
+## RICE Scoring
+
+| Factor | Question | Scale |
+|--------|----------|-------|
+| **R**each | How many users affected? | # users/period |
+| **I**mpact | How much per user? | 0.25, 0.5, 1, 2, 3 |
+| **C**onfidence | How sure are we? | 20%, 50%, 80%, 100% |
+| **E**ffort | Person-weeks | 0.5, 1, 2, 4, 8+ |
+
+```
+RICE = (Reach x Impact x Confidence) / Effort
+```
+
+## Technical Decision Checklist
+
+Before committing to a technical approach:
+
+- [ ] Have we talked to someone who's done this before?
+- [ ] What's the simplest version that teaches us something?
+- [ ] What would make us reverse this decision?
+- [ ] Who maintains this in 6 months?
+- [ ] What's our rollback plan?
+
+## When to Build vs Buy vs Adopt
+
+| Signal | Build | Buy | Adopt (OSS) |
+|--------|-------|-----|-------------|
+| Core differentiator | Yes | No | Maybe |
+| Commodity problem | No | Yes | Yes |
+| Tight integration needed | Yes | Maybe | Maybe |
+| Team has expertise | Yes | N/A | Yes |
+| Time pressure | No | Yes | Maybe |
+| Long-term control needed | Yes | No | Maybe |
+
+## Decomposition Strategies
+
+### Vertical Slicing
+Cut features into thin end-to-end slices that deliver value:
+```
+Bad:  "Build database layer" -> "Build API" -> "Build UI"
+Good: "User can see their profile" -> "User can edit name" -> "User can upload avatar"
+```
+
+### Risk-First Ordering
+1. Identify highest-risk unknowns
+2. Build spike/proof-of-concept for those first
+3. Then build around proven foundation
+
+### Dependency Mapping
+```
+[Feature A] -depends on-> [Feature B] -depends on-> [Feature C]
+                                                      ^
+                                                 Start here
+```
--- a/profiles/opencode/skill/spec-planner/references/estimation.md
+++ b/profiles/opencode/skill/spec-planner/references/estimation.md
@@ -0,0 +1,69 @@
+# Estimation
+
+## Why Estimates Fail
+
+| Cause | Mitigation |
+|-------|------------|
+| Optimism bias | Use historical data, not gut |
+| Missing scope | List "obvious" tasks explicitly |
+| Integration blindness | Add 20-30% for glue code |
+| Unknown unknowns | Add buffer based on novelty |
+| Interruptions | Assume 60% focused time |
+
+## Estimation Techniques
+
+### Three-Point Estimation
+```
+Expected = (Optimistic + 4xMostLikely + Pessimistic) / 6
+```
+
+### Relative Sizing
+Compare to known references:
+- "This is about twice as complex as Feature X"
+- Use Fibonacci (1, 2, 3, 5, 8, 13) to reflect uncertainty
+
+### Task Decomposition
+1. Break into tasks <=4 hours
+2. If can't decompose, spike first
+3. Sum tasks + 20% integration buffer
+
+## Effort Multipliers
+
+| Factor | Multiplier |
+|--------|------------|
+| New technology | 1.5-2x |
+| Unclear requirements | 1.3-1.5x |
+| External dependencies (waiting on others) | 1.2-1.5x |
+| Legacy/undocumented code | 1.3-2x |
+| Production deployment | 1.2x |
+| First time doing X | 2-3x |
+| Context switching (other priorities) | 1.3x |
+| Yak shaving risk (unknown unknowns) | 1.5x |
+
+## Hidden Work Checklist
+
+Always include time for:
+- [ ] Code review (20% of dev time)
+- [ ] Testing (30-50% of dev time)
+- [ ] Documentation (10% of dev time)
+- [ ] Deployment/config (varies)
+- [ ] Bug fixes from testing (20% buffer)
+- [ ] Interruptions / competing priorities
+
+## When to Re-Estimate
+
+Re-estimate when:
+- Scope changes materially
+- Major unknown becomes known
+- Actual progress diverges >30% from estimate
+
+## Communicating Estimates
+
+**Good:** "1-2 weeks, confidence 70%-main risk is the third-party API integration"
+
+**Bad:** "About 2 weeks"
+
+Always include:
+1. Range, not point estimate
+2. Confidence level
+3. Key assumptions/risks
--- a/profiles/opencode/skill/spec-planner/references/technical-debt.md
+++ b/profiles/opencode/skill/spec-planner/references/technical-debt.md
@@ -0,0 +1,94 @@
+# Technical Debt
+
+## Debt Categories
+
+| Type | Example | Urgency |
+|------|---------|---------|
+| **Deliberate-Prudent** | "Ship now, refactor next sprint" | Planned paydown |
+| **Deliberate-Reckless** | "We don't have time for tests" | Accumulating risk |
+| **Inadvertent-Prudent** | "Now we know a better way" | Normal learning |
+| **Inadvertent-Reckless** | "What's layering?" | Learning curve |
+
+## When to Pay Down Debt
+
+**Pay now when:**
+- Debt is in path of upcoming work
+- Cognitive load slowing every change
+- Bugs recurring in same area
+- Onboarding time increasing
+
+**Defer when:**
+- Area is stable, rarely touched
+- Bigger refactor coming anyway
+- Time constrained on priority work
+- Code may be deprecated
+
+## ROI Framework
+
+```
+Debt ROI = (Time Saved Per Touch x Touches/Month x Months) / Paydown Cost
+```
+
+| ROI | Action |
+|-----|--------|
+| >3x | Prioritize immediately |
+| 1-3x | Plan into upcoming work |
+| <1x | Accept or isolate |
+
+## Refactoring Strategies
+
+### Strangler Fig
+1. Build new alongside old
+2. Redirect traffic incrementally
+3. Remove old when empty
+
+Best for: Large system replacements
+
+### Branch by Abstraction
+1. Create abstraction over old code
+2. Implement new behind abstraction
+3. Switch implementations
+4. Remove old
+
+Best for: Library/dependency swaps
+
+### Parallel Change (Expand-Contract)
+1. Add new behavior alongside old
+2. Migrate callers incrementally
+3. Remove old behavior
+
+Best for: API changes
+
+### Mikado Method
+1. Try the change
+2. When it breaks, note prerequisites
+3. Revert
+4. Recursively fix prerequisites
+5. Apply original change
+
+Best for: Untangling dependencies
+
+## Tracking Debt
+
+Minimum viable debt tracking:
+```markdown
+## Tech Debt Log
+
+| ID | Description | Impact | Area | Added |
+|----|-------------|--------|------|-------|
+| TD-1 | No caching layer | Slow queries | /api | 2024-01 |
+```
+
+Review monthly. Prune resolved items.
+
+## Communicating Debt to Stakeholders
+
+**Frame as investment, not cleanup:**
+- "This will reduce bug rate by ~30%"
+- "Deployment time goes from 2 hours to 20 minutes"
+- "New features in this area take 2x longer than they should"
+
+**Avoid:**
+- "The code is messy"
+- "We need to refactor"
+- Technical jargon without business impact
--- a/profiles/opencode/skill/spec-planner/references/templates.md
+++ b/profiles/opencode/skill/spec-planner/references/templates.md
@@ -0,0 +1,161 @@
+# Output Templates
+
+## Quick Decision
+
+For scoped technical choices with clear options.
+
+```
+## Decision: [choice]
+
+**Why:** [1-2 sentences]
+**Trade-off:** [what we're giving up]
+**Revisit if:** [trigger conditions]
+```
+
+## Feature Plan (Implementation-Ready)
+
+For new feature development. **Complete enough for task decomposition.**
+
+```
+## Feature: [name]
+
+### Problem Statement
+**Who:** [specific user/persona]
+**What:** [the problem they face]
+**Why it matters:** [business/user impact]
+**Evidence:** [how we know this is real]
+
+### Proposed Solution
+[High-level approach in 2-3 paragraphs]
+
+### Scope & Deliverables
+| Deliverable | Effort | Depends On |
+|-------------|--------|------------|
+| [D1]        | S/M/L  | -          |
+| [D2]        | S/M/L  | D1         |
+
+### Non-Goals (Explicit Exclusions)
+- [Thing people might assume is in scope but isn't]
+
+### Data Model
+[Types, schemas, state shapes that will exist or change]
+
+### API/Interface Contract
+[Public interfaces between components-input/output/errors]
+
+### Acceptance Criteria
+- [ ] [Testable statement 1]
+- [ ] [Testable statement 2]
+
+### Test Strategy
+| Layer | What | How |
+|-------|------|-----|
+| Unit | [specific logic] | [approach] |
+| Integration | [boundaries] | [approach] |
+
+### Risks & Mitigations
+| Risk | Likelihood | Impact | Mitigation |
+|------|------------|--------|------------|
+
+### Trade-offs Made
+| Chose | Over | Because |
+|-------|------|---------|
+
+### Open Questions
+- [ ] [Question] -> Owner: [who decides]
+
+### Success Metrics
+- [Measurable outcome]
+```
+
+## Architecture Decision Record (ADR)
+
+For significant architecture decisions that need documentation.
+
+```
+## ADR: [title]
+
+**Status:** Proposed | Accepted | Deprecated | Superseded
+**Date:** [date]
+
+### Context
+[What forces are at play]
+
+### Decision
+[What we're doing]
+
+### Consequences
+- [+] [Benefit]
+- [-] [Drawback]
+- [~] [Neutral observation]
+```
+
+## RFC (Request for Comments)
+
+For larger proposals needing broader review.
+
+```
+## RFC: [title]
+
+**Author:** [name]
+**Status:** Draft | In Review | Accepted | Rejected
+**Created:** [date]
+
+### Summary
+[1-2 paragraph overview]
+
+### Motivation
+[Why are we doing this?]
+
+### Detailed Design
+[Technical details]
+
+### Alternatives Considered
+| Option | Pros | Cons | Why Not |
+|--------|------|------|---------|
+
+### Migration/Rollout
+[How we get from here to there]
+
+### Open Questions
+- [ ] [Question]
+```
+
+## Handoff Artifact
+
+When spec is complete, produce final summary for task decomposition:
+
+```
+# [Feature Name] - Implementation Spec
+
+**Status:** Ready for task breakdown
+**Effort:** [total estimate]
+**Approved by:** [human who approved]
+**Date:** [date]
+
+## Deliverables (Ordered)
+
+1. **[D1]** (S) - [one-line description]
+   - Depends on: -
+   - Files likely touched: [paths]
+   
+2. **[D2]** (M) - [one-line description]
+   - Depends on: D1
+   - Files likely touched: [paths]
+
+## Key Technical Decisions
+- [Decision]: [choice] because [reason]
+
+## Data Model
+[Copy from spec]
+
+## Acceptance Criteria
+1. [Criterion 1]
+2. [Criterion 2]
+
+## Open Items (Non-Blocking)
+- [Item] -> Owner: [who]
+
+---
+*Spec approved for task decomposition.*
+```
--- a/profiles/opencode/skill/vcs-detect/SKILL.md
+++ b/profiles/opencode/skill/vcs-detect/SKILL.md
@@ -1,70 +0,0 @@
---
-name: vcs-detect
-description: Detect whether the current project uses jj (Jujutsu) or git for version control. Run this BEFORE any VCS command to use the correct tool.
---
-
-# VCS Detection Skill
-
-Detect the version control system in use before running any VCS commands.
-
-## Why This Matters
-
- jj (Jujutsu) and git have different CLIs and workflows
- Running `git` commands in a jj repo (or vice versa) causes errors
- Some repos use jj with git colocated (both `.jj/` and `.git/` exist)
-
-## Detection Logic
-
-Both `jj root` and `git rev-parse --show-toplevel` walk up the filesystem to find repo root.
-
-**Priority order:**
-
-1. `jj root` succeeds → jj (handles colocated too)
-2. `git rev-parse` succeeds → git
-3. Both fail → no VCS
-
-## Detection Command
-
-```bash
-if jj root &>/dev/null; then echo "jj"
-elif git rev-parse --show-toplevel &>/dev/null; then echo "git"
-else echo "none"
-fi
-```
-
-## Command Mappings
-
-| Operation | git | jj |
-|-----------|-----|-----|
-| Status | `git status` | `jj status` |
-| Log | `git log` | `jj log` |
-| Diff | `git diff` | `jj diff` |
-| Commit | `git commit` | `jj commit` / `jj describe` |
-| Branch list | `git branch` | `jj branch list` |
-| New branch | `git checkout -b <name>` | `jj branch create <name>` |
-| Push | `git push` | `jj git push` |
-| Pull/Fetch | `git pull` / `git fetch` | `jj git fetch` |
-| Rebase | `git rebase` | `jj rebase` |
-
-## Usage
-
-Before any VCS operation:
-
-1. Run detection command
-2. Use appropriate CLI based on result
-3. If `none`, warn user directory is not version controlled
-
-## Example Integration
-
-```
-User: Show me the git log
-Agent: [Runs detection] -> Result: jj
-Agent: [Runs `jj log` instead of `git log`]
-```
-
-## Colocated Repos
-
-When both `.jj/` and `.git/` exist, the repo is "colocated":
- jj manages the working copy
- git is available for compatibility (GitHub, etc.)
- **Always prefer jj commands** in colocated repos
--- a/profiles/overseer.nix
+++ b/profiles/overseer.nix
@@ -0,0 +1,5 @@
+{pkgs, ...}: {
+	home.packages = with pkgs; [
+		overseer
+	];
+}
--- a/profiles/packages.nix
+++ b/profiles/packages.nix
@@ -27,8 +27,6 @@ with pkgs;
 		hledger
 		htop
 		hyperfine
-		jj-ryu
-		jj-starship
 		jq
 		killall
 		lsof
@@ -47,7 +45,6 @@ with pkgs;
 		tree-sitter
 		unzip
 		vivid
-		watchman
 		zip
 	]
 	++ lib.optionals stdenv.isDarwin [
@@ -55,6 +52,7 @@ with pkgs;
 		alcove
 		dockutil
 		mas
+		openusage
 		raycast
 		tailscale
 		xcodes
--- a/profiles/starship.nix
+++ b/profiles/starship.nix
@@ -1,11 +1,11 @@
 {
 	programs.starship = {
 		enable = true;
-		enableFishIntegration = true;
+		enableNushellIntegration = true;
 		settings = {
 			add_newline = true;
 			command_timeout = 2000;
-			format = "[$directory$\{custom.scm}]($style)$character";
+			format = "$directory$git_branch$git_status$character";
 			character = {
 				error_symbol = "[✗ ](bold #e64553)";
 				success_symbol = "[❯](bold #40a02b)[❯](bold #df8e1d)[❯](bold #dc8a78)";
@@ -16,10 +16,26 @@
 				repo_root_style = "bold cyan";
 				repo_root_format = "[$repo_root]($repo_root_style)[$path]($style)[$read_only]($read_only_style) ";
 			};
-			custom.scm = {
-				when = "jj-starship detect";
-				shell = ["jj-starship" "--strip-bookmark-prefix" "cschmatzler/" "--truncate-name" "20" "--bookmarks-display-limit" "1"];
-				format = "$output ";
+			git_branch = {
+				format = "[$symbol$branch(:$remote_branch)]($style) ";
+				symbol = " ";
+				style = "bold #8839ef";
+				truncation_length = 20;
+				truncation_symbol = "…";
+			};
+			git_status = {
+				format = "([$all_status$ahead_behind]($style) )";
+				style = "bold #df8e1d";
+				conflicted = "conflict:$count ";
+				ahead = "ahead:$count ";
+				behind = "behind:$count ";
+				diverged = "ahead:$ahead_count behind:$behind_count ";
+				untracked = "new:$count ";
+				stashed = "stash:$count ";
+				modified = "mod:$count ";
+				staged = "staged:$count ";
+				renamed = "mv:$count ";
+				deleted = "del:$count ";
 			};
 		};
 	};
--- a/profiles/zoxide.nix
+++ b/profiles/zoxide.nix
@@ -1,6 +1,6 @@
 {
 	programs.zoxide = {
 		enable = true;
-		enableFishIntegration = true;
+		enableNushellIntegration = true;
 	};
 }
--- a/secrets/derek-icloud-password
+++ b/secrets/derek-icloud-password
@@ -1,35 +0,0 @@
-{
-	"data": "ENC[AES256_GCM,data:l7jYCSQE0BwYOoIMHgGOmMrWz5s=,iv:4TugFnfmzoeroq6SfRLD36gSSBHGVT6CxQE4Pyp1Ibc=,tag:HOTLlXGab05u+qREtyxAeg==,type:str]",
-	"sops": {
-		"age": [
-			{
-				"recipient": "age1njjegjjdqzfnrr54f536yl4lduqgna3wuv7ef6vtl9jw5cju0grsgy62tm",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBFTmVlZmxIMGFBbE1RYkNN\nbTh1NG5BK1JCTlZ1MzBtSS9NRXRVM3phN3lrCm9qSlpEQjFGZTBsME9ndXhYdHZv\ncW1oek5hU1pjQXhzT0cvTks3VEozdHcKLS0tIG1TUWJKSE1KRVlXMVdydjBhY1ZS\nWXRhNFA2aHZTT2pud0ZXOFpjVldKYjgKYyH7k0BW/sf3vDQLPaZoB2VHoyKmCkWy\nwTolEp4vkuzZld4KPdDW4jYL8kt8Fwa8TNlPKMUOvY0gt82pbJ1MAA==\n-----END AGE ENCRYPTED FILE-----\n"
-			},
-			{
-				"recipient": "age187jl7e4k9n4guygkmpuqzeh0wenefwrfkpvuyhvwjrjwxqpzassqq3x67j",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA5Y2ZpWlhXUll4WUxheENj\nRjlwK2dJUjBOU1lhV1dKWFhiMlJiQ0Q2Q0VrCnJac0ppdm9URW14TUwrVUdwN2x4\ncUgxSGRTM09ORUk0VXhUcVBxS1Z2a0EKLS0tIGhOSmc2L3FKOXdqdG5Da210aXF4\nZ2h0dW45K2dlZGJQMmxneE1IbXMvWmsKkBfh09E6o2uvNegq5pZgUBWOYjREDDyg\nHEgV7G4cWJBPpBFwS1gLGyRZ0TWrmoXCqF8I22BMG6tq94AGrKqFzg==\n-----END AGE ENCRYPTED FILE-----\n"
-			},
-			{
-				"recipient": "age1dqt3znmzcgghsjjzzax0pf0eyu95h0p7kaf5v988ysjv7fl7lumsatl048",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCc1B0Ylo5K1poUXpkcFZk\neGJSQmNBVU00RTdLcTNBRUN2N3cySFE0cUdVCjNmZlpGM0VUOWdvbVQ3U1BoRWJ1\na3kwK3JxQ0IrZ0NUaW5sTmZlWmd4MncKLS0tIHozZ29UbTNPZDBjTUl3WlB2YmFs\nS0IrN3lLK2YyM0ROTERtQlppbjVOdWMKtpLveHYL4RfEpCBLt4c4R/NVg1QF+if1\nz26bWNQseIsPtlIk4GImJZhUhbr3sDY81gcl7sd8XGpze7EAVM262g==\n-----END AGE ENCRYPTED FILE-----\n"
-			},
-			{
-				"recipient": "age1ez6j3r5wdp0tjy7n5qzv5vfakdc2nh2zeu388zu7a80l0thv052syxq5e2",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBySmdCaVRYV2RjOFR4dFVx\nYmd1VlRzQmUwR1RwcTNJdTlxQnFFZXVscnlFCnRVOWQwa3VVUUlHQTF0WHBXb0FL\nMEViVXVDeWJLZnBLdWlUZTZFQVFqYlUKLS0tIHBGdXdPM2tOdzR0Qm5UT2F6dnNF\nTytWcXNYMEJSTU8xOExMK1MwQUNhdk0KVBbrhhwh+Yup+CW3Y+q9RoQ3XFjBfTLb\nzDbCZBhNx9HP7Q8mlndYPkJc3aGfpKxHpaniBLqzDKNKJ5OE4kzY3Q==\n-----END AGE ENCRYPTED FILE-----\n"
-			},
-			{
-				"recipient": "age1tlymdmaukhwupzrhszspp26lgd8s64rw4vu9lwc7gsgrjm78095s9fe9l3",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtVnl0ckE1REtQbW8ybEtF\nWG1VNkFtMUVlNk04SnIySVFvM2pkV1dTMTNNCkV6R2NzQzM4WXRIdzJrVEo4L2FX\nQ1dmV2YwNHdMMVJUNmZWRktvK2s1dUUKLS0tIE5nUXNack5meUFzcWxhOTNGLzdG\naGlVYURRK2hLK0lNNm4wYTUrdXptLzAKZgN1tY1G3Jso1+CT0LQQ4I49CgdCECpe\n1wRdgaWI8P4ep2S7QO3Vu+MuoyOgVgGJdG/HzsEAAqJ0XMSBWpeFXg==\n-----END AGE ENCRYPTED FILE-----\n"
-			},
-			{
-				"recipient": "age1h537hhl5qgew5sswjp7xf7d4j4aq0gg9s5flnr8twm2smnqyudhqmum8uy",
-				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB3YnVBeGl5akg2b3BidW5m\nMjBnWWxReTFoNTBYVm83ZkhtSHUvTmtNSGxzCk5XcmVJZ0hpRURIT09teHFzOURt\nK25JSFJCNU5mb2k4ZHBTU0Q0emFtYWMKLS0tIEtqMlFNckZmQk15Z0xoT1BrUWgv\nN0VJT1RjOG1ZOVU1UklKTm5TUEhLQmsKP03juyke7ZmLGx+BHE596d18TWVLFuUV\nP1pK0QlwtRL0l/6r7l4hXN9gJ8JU+zO5NTcLtvvHdSL188q3TX//UQ==\n-----END AGE ENCRYPTED FILE-----\n"
-			}
-		],
-		"lastmodified": "2026-01-07T19:19:41Z",
-		"mac": "ENC[AES256_GCM,data:SnMD9+jpySE35ylbHInXfsIQ/Nq6FBpunlhgJSOnYCQLE9vGc5Rtkg8cYlqFBz82Ukjk2EJafKcjDgBgTx6+JcYC8idM7yCpqyJaTx9p0nr6+p46ozqrL8lm4qF+yJRK997RjfRStLE2JsLN0SRSBFTDL0yPB6mFc/BncywVVZ0=,iv:fJ0kpgysw8eHbIIrtdyUXwWYvHyOa6kJ1wW+6NvBTxY=,tag:cqyY6qmEa0HF6u61v9VZJw==,type:str]",
-		"unencrypted_suffix": "_unencrypted",
-		"version": "3.11.0"
-	}
-}
Author	SHA1	Message	Date
Christoph Schmatzler	09cbb308d2	up Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-09 17:31:21 +00:00
Christoph Schmatzler	c120b3d4d2	opencode: add Cog memory skill	2026-02-09 17:28:35 +00:00
Christoph Schmatzler	3381945cea	opencode: add Cog MCP server	2026-02-09 17:18:36 +00:00
Christoph Schmatzler	d12aabdccc	opencode: disable oh-my-opencode commit footer and co-author	2026-02-09 17:16:58 +00:00
Christoph Schmatzler	d38a348a06	add openusage Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-09 17:15:10 +00:00
Christoph Schmatzler	42873f4d2d	opencode: add oh-my-opencode config, remove custom oracle agent	2026-02-09 15:00:24 +00:00
Christoph Schmatzler	c1bb006292	Remove mindy host and orphaned derek secret	2026-02-09 09:26:34 +00:00
Christoph Schmatzler	9bdaaeb295	flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-09 09:17:45 +00:00
Christoph Schmatzler	6596ec2d9b	opencode: add oracle research tools, spec-planner question tool, deny mcp-auth read	2026-02-08 17:46:29 +00:00
Christoph Schmatzler	0103aa8c16	Remove watchman package and file watcher config	2026-02-08 08:45:17 +00:00
Christoph Schmatzler	37b13cfd6a	flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-08 08:41:54 +00:00
Christoph Schmatzler	29d27dccfb	nushell: Remove deprecated use_ls_colors config option	2026-02-08 08:39:13 +00:00
Christoph Schmatzler	cca27aa971	Replace fish with nushell	2026-02-08 08:37:09 +00:00
Christoph Schmatzler	75bbb322d3	up Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-06 16:11:06 +00:00
Christoph Schmatzler	1a79b5fa9f	Update Claude model to opus 4-6	2026-02-05 18:37:52 +00:00
Christoph Schmatzler	9288aef5c7	flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-05 18:26:06 +00:00
Christoph Schmatzler	29a2dfc606	solidjs Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-05 17:08:21 +00:00
Christoph Schmatzler	2999325de9	up Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-05 14:39:06 +00:00
Christoph Schmatzler	06584ffedc	rm appsignal	2026-02-05 08:46:42 +00:00
Christoph Schmatzler	90f91bd017	rm custom profile Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-05 08:40:06 +00:00
Christoph Schmatzler	2b880be833	flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-05 08:23:11 +00:00
Christoph Schmatzler	64a5a29809	Add overseer host package for UI support	2026-02-04 20:30:26 +00:00
Christoph Schmatzler	c1bae690b3	Use local overseer binary for MCP server	2026-02-04 20:20:01 +00:00
Christoph Schmatzler	f8e912e201	Add overseer CLI for task management	2026-02-04 20:17:49 +00:00
Christoph Schmatzler	ff8650bedf	oc Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-04 20:04:32 +00:00
Christoph Schmatzler	13586f5c44	up Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-04 19:42:17 +00:00
Christoph Schmatzler	ead1e8d57c	Remove Zed editor configuration	2026-02-04 10:40:59 +00:00
Christoph Schmatzler	87d3044959	Update zed.nix	2026-02-04 10:37:58 +00:00
Christoph Schmatzler	cc2dc49511	up Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-04 10:34:12 +00:00
Christoph Schmatzler	79e72505f8	Add Zed remote development setup with vim keybindings	2026-02-04 10:17:34 +00:00
Christoph Schmatzler	21c8f95f86	flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-04 10:13:45 +00:00
Christoph Schmatzler	6a402795b9	-jj Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-03 19:51:59 +00:00
Christoph Schmatzler	f342d99650	starship: fix indentation	2026-02-03 16:57:59 +00:00
Christoph Schmatzler	9d476ee209	Add claude-code profile from llm-agents input	2026-02-03 16:53:06 +00:00
Christoph Schmatzler	88ff7d0077	starship: use readable labels for git status symbols	2026-02-03 10:38:49 +00:00
Christoph Schmatzler	d91ea80bef	update flake Signed-off-by: Christoph Schmatzler <christoph@schmatzler.com>	2026-02-03 10:31:10 +00:00
Christoph Schmatzler	682889f878	Replace jj with git, use lazygit in neovim	2026-02-03 10:26:22 +00:00
Christoph Schmatzler	f07e0be31d	flake	2026-02-03 07:09:59 +00:00
				`@@ -1 +0,0 @@`
				`{inputs}: inputs.jj-starship.overlays.default`