docs(agent-skill): existing installs that stored off are switched on once

The changeset, CLAUDE.md, the invariants, the agent control plan, both READMEs
and the wiki's Codeman Skill and Settings Reference pages said an install whose
App Settings were saved on an earlier version stays off until switched on. They
now say the first 1.50.0 start switches a stored off on once, and that turning
it off afterwards sticks. The changeset marks it "Behaviour change:", says the
migration cannot tell a chosen off from the old default, and tells users to
reload a tab left open from before the upgrade before saving App Settings in
it. CLAUDE.md lists the marker file among the data dir's state files, and the
invariants record why it stores true, why the marker is its own file, and
where it runs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/agent-control-plan.md

@@ -11,7 +11,10 @@ guard and the Part 3 deferrals).
 **Update 2026-11-08 (1.50.0)**: `agentSkillEnabled` is now **on by default** (owner decision:
 "enable the codeman skill by default"), the flip §2.2 planned for after dogfooding. An absent
 key means on in both readers (server `getAgentSkillEnabled()` and the App Settings switch, both
-`!== false`); an explicit false stays off. To keep users' repositories clean, every managed copy
+`!== false`); an explicit false is off. Existing installs that stored off are switched on once at
+the first 1.50.0 start (every App Settings Save up to 1.49.0 wrote `false`); turning it off
+afterwards sticks (`src/web/agent-skill-default-migration.ts`, a "Behaviour change" in the
+release notes). To keep users' repositories clean, every managed copy
 now carries a `.gitignore` of `*` (written once with `wx`, removed by uninstall only when it is
 the last file left). Turning the setting off still sweeps nothing. The sections below record the
 original default-off decision as it was made.
@@ -690,9 +693,9 @@ Built to the §2.6 file list, mirroring the statusLine mechanism throughout:
 | ----- | ----- |
 | `applyAgentSkill(casePath, enabled)` + `installAgentSkillInto` / `removeAgentSkillFrom` | `src/hooks-config.ts` |
 | `codeman skill install` / `skill uninstall` (`--global` default, `--case <name>`) | `src/cli.ts` |
-| `agentSkillEnabled` (SYNCED, default OFF; ON since 1.50.0) | `schemas.ts` (`SettingsUpdateSchema`), `getAgentSkillEnabled()` on `ConfigPort`/`server.ts`, checkbox in `index.html` + `settings-ui.js` |
+| `agentSkillEnabled` (SYNCED, default OFF; ON since 1.50.0) | `schemas.ts` (`SettingsUpdateSchema`), `getAgentSkillEnabled()` on `ConfigPort`/`server.ts`, checkbox in `index.html` + `settings-ui.js`; the one-time 1.50.0 boot migration of a stored false in `src/web/agent-skill-default-migration.ts` |
 | Injection call sites (Claude mode only) | `POST /api/sessions` next to `refreshStaleCodemanHooks`; `POST /api/quick-start` after the case-create/self-heal blocks (local + docker cases; remote skipped, its path lives on another host) |
-| Tests | `test/agent-skill.test.ts` (unit, incl. the self-ignoring `.gitignore` against real git since 1.50.0), `test/quick-start.test.ts` (real server: default-off at first, default-on since 1.50.0 incl. a partial PUT and an explicit false, injection on create, shell-mode skipped), `test/agent-skill-setting-ui.test.ts` (the App Settings switch reads an absent key as on) |
+| Tests | `test/agent-skill.test.ts` (unit, incl. the self-ignoring `.gitignore` against real git since 1.50.0), `test/quick-start.test.ts` (real server: default-off at first, default-on since 1.50.0 incl. a partial PUT and an explicit false, injection on create, shell-mode skipped), `test/agent-skill-setting-ui.test.ts` (the App Settings switch reads an absent key as on, and a device blob holding the old false follows the server), `test/agent-skill-default-migration.test.ts` (the boot migration: once per data dir, marker outside settings.json) |
 
 Decisions worth keeping:
 

docs/architecture-invariants.md

@@ -167,7 +167,7 @@ Spawn commands are pinned as literal strings in `test/cli-registry-spawn-golden.
 
 Further detail: `stop`/`blocked` now fire for **`claude` and `deepseek`** (`shell` installs no hooks either); asking for one explicitly on any other mode is a 400 and the default set silently drops them. `deepseek` qualifies because the DeepSeek Harness TUI REPORTS idle/working/blocked to its supervisor and Codeman is that supervisor (`deepseek-status-shim.ts`), so its signals are definitive rather than inferred, and `hooksAvailableForMode()` in `session-wait-registry.ts` is the one place that rule lives (see the External CLI modes section for the per-session `statusReporting` wrinkle and the two dsh traps baked into the skill preamble: boot `idle` landing ~300 ms before the composer paints, and `sendwait` asking for `wait:"stop,exit"`). That is also why `deepseek` is the one non-claude mode the skill drives like claude: `spawn_workers alpha beta:deepseek` is a mixed fleet in one call, and `sendwait`/`last_text` need no variant. ⚠️ **`blocked` alone has a second source**: a CLI with no hook for it can declare the dialogs it blocks on (`capabilities.workDetect.blockedLine`, codex), and `blockedSignalAvailable()` (hooks OR that field) is the rule for that one signal; `stop` stays hooks-only, since nothing on a screen says a turn ended. A screen-read `blocked` is a LEVEL the server keeps reading (`Session.screenBlocked`), so the wait route answers it immediately (`currentSignalForWait()`) when the caller asked for `blocked`, and only then: such a pane is also `idle`, and `until=idle` must keep answering `idle`. See [Screen-read blocked dialogs](#screen-read-blocked-dialogs-codex).
 
-**Packaging as the `skills/codeman` agent skill.** The primitives are packaged as the `skills/codeman` agent skill, installable three ways: via `codeman skill install [--case <name>]` / `skill uninstall`; as a Claude Code plugin from the repo's own marketplace (`/plugin marketplace add Ark0N/Codeman` + `/plugin install codeman@codeman`, see the root-files note in CLAUDE.md); or auto-injected into a case on session create behind `agentSkillEnabled` (SYNCED, default ON since 1.50.0, default OFF before). ⚠️ An ABSENT key means on in BOTH readers, the server's `getAgentSkillEnabled()` and the App Settings switch (both `!== false`): a page that showed an absent key as off would write `false` on the next Save of any other setting. Only an explicit false is off, so an install whose App Settings were saved on 1.49.0 or earlier (which wrote the old default) stays off until the user turns it on. Turning it off sweeps nothing. ⚠️ Every managed copy ignores itself in git, which is what makes the default safe in a user's repository: `installAgentSkillInto()` writes `<copy>/.gitignore` holding `*` FIRST (so a `git status` mid-install never lists it), with `wx` (a file already there is the user's and is never overwritten; a symlink at the name is refused), and outside the content list `readAgentSkillSource()` compares, so it never appears in `skills/codeman/` or the plugin mirror. A copy injected before 1.50.0 gains it on its next install (`refreshed`). `removeAgentSkillFrom()` deletes it only when it is the last entry left and holds exactly `*`, so a user's extra files there stay ignored. The repository's own `.gitignore` and `info/exclude` are never touched for it (the managed-worktree exclude in git-worktrees.ts is a separate, older line and still added). Measured against Claude Code 2.1.319: its skill discovery runs `git check-ignore` only on directories at or above `.claude/skills` (the nested-skills walk), never on a skill folder or its SKILL.md, and a `*` inside `codeman/` ignores the folder's contents, not the folder, so the skill still loads; codex 0.162 has no gitignore check on skills. Checked live on 2026-11-08 with the ignore file in place: Claude Code 2.1.319 (`--debug` reports `project: 1`), Codex 0.162 (app-server `skills/list`), OpenCode 1.3.0 (`opencode debug skill`) and Grok 1.0.52 (`grok --trust inspect`) all list `codeman`; agy, dsh, gemini and omp were not measured. ⚠️ Install and uninstall refuse (`symlink`) a link at the copy, at its `skills/` parent, and at a folder INSIDE the copy (`reference/`, `agentSkillSubdirIsSymlink()`): a cloned repository can commit one and a Docker case's container can plant one in the bind-mounted workspace, and a write or unlink of `reference/<name>.md` through it lands wherever it points (measured: install overwrote a file there, uninstall deleted it). The check runs once before the first write; a link swapped in after it is not covered. ⚠️ WHERE it lands is registry data, `capabilities.agentSkillDir` (absent with `agentSkillInjection: true` = `.claude/skills`): `.claude/skills/codeman` for claude, `.agents/skills/codeman` for every other CLI that takes it (pi does not: a project skill triggers its trust prompt). `agentSkillDir` is a CLOSED enum (`AGENT_SKILL_DIRS`, schema.ts) because `clis.json` can set it and it decides where the server writes. The per-session preamble is seeded for every local session whose CLI takes the skill, and `codeman skill uninstall --case` removes the copy from every distinct registry directory (`registryAgentSkillDirs()`, cli.ts). ⚠️ Plugin skills are namespaced, so a Claude Code holding BOTH the plugin and a user-level or per-case copy lists the skill twice, `codeman` and `codeman:codeman` (measured 2026-09-14: neither shadows the other, both work); the docs tell users to pick one route, and since the per-case injection is on by default, a plugin user turns that setting off.
+**Packaging as the `skills/codeman` agent skill.** The primitives are packaged as the `skills/codeman` agent skill, installable three ways: via `codeman skill install [--case <name>]` / `skill uninstall`; as a Claude Code plugin from the repo's own marketplace (`/plugin marketplace add Ark0N/Codeman` + `/plugin install codeman@codeman`, see the root-files note in CLAUDE.md); or auto-injected into a case on session create behind `agentSkillEnabled` (SYNCED, default ON since 1.50.0, default OFF before). ⚠️ An ABSENT key means on in BOTH readers, the server's `getAgentSkillEnabled()` and the App Settings switch (both `!== false`): a page that showed an absent key as off would write `false` on the next Save of any other setting. Only an explicit false is off. Existing installs that stored off are switched on once at the first 1.50.0 start; turning it off afterwards sticks. Every App Settings Save up to 1.49.0 wrote `false` (the switch loaded an absent key as off and Save sends the whole form), so without that the default would never reach anyone who had ever saved. ⚠️ The migration (`migrateAgentSkillDefault()`, `web/agent-skill-default-migration.ts`) runs from `WebServer.start()` before the first settings read (and the 2 s `readSettings()` cache, which it drops after a write) and before listen, never in test mode, and writes only through `mutateSettingsFile()`; a `settings.json` that does not parse is left alone with one log line and no marker, so the next start after the fix tries again. It cannot tell a deliberate off from the old default (accepted, a "Behaviour change" in the release notes). ⚠️ It stores `true` rather than deleting the key: `loadAppSettingsFromServer()` overwrites only the synced keys the server HAS, so every device that saved on 1.49 would keep its own `false`, show the switch off and write `false` back on its next Save (`true` also wins in a browser still running a cached settings-ui.js); for a server with no key the page drops the device's copy too. ⚠️ Its "done" marker is its own file, `agent-skill-default-migrated.json` in the data dir via `dataPath()`, checked before anything is read and written only after the settings write landed (a crash between the two is harmless: the next start finds `true`). Never a settings key: `GET /api/settings` never returns it, so no Save can send it back (the `.strict()` `SettingsUpdateSchema` would 400) or drop it (which would re-arm the migration and switch a later off back on), and it is outside `CONFIG_BACKUP_FILES`, so a restored settings.json, even a pre-1.50 one holding `false`, stays as restored. One data dir is one server, so in multi-user mode it runs once for the server. A device whose pages were all loaded before the upgrade still holds the old `false` in its localStorage blob until a page load refreshes it, and an App Settings Save from such a page writes that back (accepted; the release note says to reload). Tests: `test/agent-skill-default-migration.test.ts`, `test/agent-skill-setting-ui.test.ts`. Turning it off sweeps nothing. ⚠️ Every managed copy ignores itself in git, which is what makes the default safe in a user's repository: `installAgentSkillInto()` writes `<copy>/.gitignore` holding `*` FIRST (so a `git status` mid-install never lists it), with `wx` (a file already there is the user's and is never overwritten; a symlink at the name is refused), and outside the content list `readAgentSkillSource()` compares, so it never appears in `skills/codeman/` or the plugin mirror. A copy injected before 1.50.0 gains it on its next install (`refreshed`). `removeAgentSkillFrom()` deletes it only when it is the last entry left and holds exactly `*`, so a user's extra files there stay ignored. The repository's own `.gitignore` and `info/exclude` are never touched for it (the managed-worktree exclude in git-worktrees.ts is a separate, older line and still added). Measured against Claude Code 2.1.319: its skill discovery runs `git check-ignore` only on directories at or above `.claude/skills` (the nested-skills walk), never on a skill folder or its SKILL.md, and a `*` inside `codeman/` ignores the folder's contents, not the folder, so the skill still loads; codex 0.162 has no gitignore check on skills. Checked live on 2026-11-08 with the ignore file in place: Claude Code 2.1.319 (`--debug` reports `project: 1`), Codex 0.162 (app-server `skills/list`), OpenCode 1.3.0 (`opencode debug skill`) and Grok 1.0.52 (`grok --trust inspect`) all list `codeman`; agy, dsh, gemini and omp were not measured. ⚠️ Install and uninstall refuse (`symlink`) a link at the copy, at its `skills/` parent, and at a folder INSIDE the copy (`reference/`, `agentSkillSubdirIsSymlink()`): a cloned repository can commit one and a Docker case's container can plant one in the bind-mounted workspace, and a write or unlink of `reference/<name>.md` through it lands wherever it points (measured: install overwrote a file there, uninstall deleted it). The check rLine truncated
 
 Injection is ADD-ONLY at create, marker-owned (`applyAgentSkill` in `hooks-config.ts` never touches an unmarked user copy) and refuses symlinks (this repo's own `.claude/skills/codeman` is a symlink to the source, which the injector must never write through). ⚠️ Claude Code loads a same-named USER-LEVEL skill (`~/.claude/skills/codeman`, written once by `codeman skill install` with no `--case`) over the per-case copy, and nothing used to refresh it: a stale Aug-9 user copy shadowed every fresh injection (2026-08-14: agents ran the old recipes, spawned workers serially and lost their lineage arcs), so session create now also refreshes a marker-owned user copy (`refreshUserAgentSkill`; refresh-only, never installs, foreign/symlink refused).
 

docs/wiki/Codeman-Skill.md

@@ -76,8 +76,9 @@ Codeman-managed copy in that case, whichever CLI's directory it sits in). It nev
 
 To stop the Web UI copy, turn **App Settings → Agents & CLIs → All agent CLIs → Codeman Agent
 Skill** off. It is on by default since 1.50.0: a settings file without the setting means on,
-and only switching it off turns it off. An install whose App Settings were saved on an
-earlier version stored the old default (off), so there it stays off until you switch it on.
+and only switching it off turns it off. Existing installs that stored off are switched on
+once at the first 1.50.0 start (every App Settings save on an earlier version stored the old
+default, off, whether or not you touched this switch); turning it off afterwards sticks.
 
 Turning the web UI setting off **does not remove copies it already injected**, because
 a sweep at session start would pull the skill out from under other live sessions sharing

docs/wiki/Settings-Reference.md

@@ -202,7 +202,7 @@ instead of its native cloud backend. See [Custom Model Endpoints](Custom-Model-E
 | Ralph / Todo Tracker             | Enables the Ralph loop surfaces.                                                               |
 | Agent Teams                      | Experimental teams. Also needs the CLI's own environment flag.                                 |
 | Pin tab names on the CLI         | Launches every Claude session with `--name` set to its tab name, so Claude Code's prompt label and `/resume` list match your tabs. Claude then stops generating its own titles for those sessions, and a rename in Codeman holds only until the next turn. Synced, off by default; applies from the next session start or respawn. |
-| Codeman Agent Skill              | Under **All agent CLIs**. Injects the agent skill into each new session's case, where that session's CLI looks for skills (every CLI except Pi, GitHub Copilot and a plain shell). On by default since 1.50.0; the copy ignores itself in git, so your repository never lists it. Off stops new copies but removes none (`codeman skill uninstall --case <name>` does). See [The Codeman Skill](Codeman-Skill). |
+| Codeman Agent Skill              | Under **All agent CLIs**. Injects the agent skill into each new session's case, where that session's CLI looks for skills (every CLI except Pi, GitHub Copilot and a plain shell). On by default since 1.50.0; existing installs that stored off are switched on once at the first 1.50.0 start, and turning it off afterwards sticks. The copy ignores itself in git, so your repository never lists it. Off stops new copies but removes none (`codeman skill uninstall --case <name>` does). See [The Codeman Skill](Codeman-Skill). |
 | Remote auto-reconnect            | Reattaches dropped remote SSH sessions. On by default.                                         |
 | Nice priority / value            | Runs agent processes at a lower CPU priority.                                                  |
 | Default Codex model              | Model for new local Codex sessions; empty uses Codex's own config. Letters, digits, `.` `_` `-` `/` only. |