@mmerterden/multi-agent-pipeline 20.29.0 → 20.33.0

package/pipeline/skills/shared/core/multi-agent-autopilot-on/SKILL.md

@@ -162,25 +162,23 @@ Render `templates/multi-agent-autopilot.plist.template` and show the resolved
 "Configure only" is a real answer and the safe default to offer first: the queue
 can be watched with `autopilot-status` for a while before anything runs.
 
-On **Start**:
+On **Start**, load the schedule and the awake agent with the same script the
+office panel's `POST /v1/autopilot/on` calls, naming every repo selected in step 3:
 
 ```bash
-launchctl bootstrap "gui/$(id -u)" "$HOME/Library/LaunchAgents/com.multi-agent.autopilot.plist" 2>/dev/null \
-  || launchctl load "$HOME/Library/LaunchAgents/com.multi-agent.autopilot.plist"
+node "$HOME/.claude/scripts/autopilot-control.mjs" on --repo <owner/name> [--repo <owner/name>...]
 ```
 
-Then the awake agent, rendered from
-`templates/multi-agent-autopilot-awake.plist.template` with the `awake.display`
-answer saved above:
-
-```bash
-. "$HOME/.claude/lib/autopilot-state.sh"
-node "$(ma_ap_asset scripts/autopilot-awake.mjs)" install
-```
-
-A non-zero exit means launchd refused the job: say so, with its path, and say
-the Mac may sleep between ticks until it is fixed. The schedule itself stays on.
-"Configure only" installs neither.
+It keeps exactly those repos in `config.json`, probes their credentials again
+(`autopilot-arming.mjs probeCredentials`), renders
+`templates/multi-agent-autopilot.plist.template` with its seven placeholders
+(NODE, TICK, LABEL, ROOT, INTERVAL, HOME, CLAUDE), loads it with `launchctl
+bootstrap` (falling back to `load`) and installs the awake agent with the
+`awake.display` answer saved above. `scheduled: false` with probe problems means
+nothing was loaded; say so with the problems. Exit 1 with `launchd refused`
+means launchd refused the job: say so, with its path, and say the Mac may sleep
+between ticks until it is fixed. "Configure only" is `--configure-only`, which
+saves the selection and installs neither.
 
 ### 9. Report what is now true
 

package/pipeline/skills/shared/core/multi-agent-office-off/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: multi-agent-office-off
+description: "Close the office panel and stop its local server. Use when done with the panel."
+user-invocable: true
+metadata:
+  language: en
+---
+
+# multi-agent-office-off
+
+1. `node "$HOME/.copilot/scripts/office-control.mjs" off --json`
+2. Report in `outputLanguage`: whether a server was `stopped`, and the
+   `remote` line as given. A panel that was already closed is not an error.
+
+Only the recorded server is signalled, and only when its token file, command
+and start time still match.

package/pipeline/skills/shared/core/multi-agent-office-on/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: multi-agent-office-on
+description: "Open the office: a local browser page that shows runs and agents live and drives the ecosystem (new runs, jobs, PRs, keys, memory, system, cleanup). Use when you want to watch or drive runs from a browser."
+user-invocable: true
+metadata:
+  language: en
+---
+
+# multi-agent-office-on
+
+Starts (or reuses) the local contract server with the installed panel page
+and opens the browser at `/office` with a one-time code in the URL fragment
+(10 seconds, one use), which the page trades for the token.
+
+1. `node "$HOME/.copilot/scripts/office-control.mjs" on --json`
+2. Report in `outputLanguage`: `url` (it carries no code), whether the server
+   was started or `reused`, and that it runs until `/multi-agent-office-off`
+   stops it. If `opened` is false, say to run it again from a desktop session.
+
+Never print the token, read the token file or pass `--print-token`. The server
+listens on 127.0.0.1 only; remote access is not part of this installation.

package/pipeline/skills/shared/core/multi-agent-office-status/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: multi-agent-office-status
+description: "Whether the office panel is running, its URL (never the token) and its last actions. Use when unsure if the panel is open."
+user-invocable: true
+metadata:
+  language: en
+---
+
+# multi-agent-office-status
+
+1. `node "$HOME/.copilot/scripts/office-control.mjs" status --json`
+2. Report in `outputLanguage`: `running`, `url` and `idleMinutes`; the
+   `remote` line as given ("not available in this installation" unless a
+   separate remote layer is installed); `pairedDevices`; `recentActions`
+   (route, step, status, when; never a request body).
+
+Never print the token or read the token file.

package/pipeline/skills/shared/core/multi-agent-prune-logs/SKILL.md

@@ -17,7 +17,10 @@ whole task dirs, with optional age / project / task filters.
 Backed by `$HOME/.claude/scripts/prune-logs.sh`. Safe by default: it previews
 and deletes nothing until you confirm. The audit trail (`audit.jsonl` +
 rotations) and the metrics corpus (`metrics.jsonl`, `metrics-summary.md`) live
-at the log-root top level and are never removed; `.counter` files survive too.
+at the log-root top level and are never removed; `.counter` files survive too. A run that can still be resumed (its `agent-state.json` status is not
+finished, abandoned or cancelled) keeps its log however old it is, and
+so does a folder written in the last 10 minutes; `--task` names one dir and
+bypasses both.
 
 Unlike `/multi-agent:purge` (which wipes worktrees, branches, logs, and state
 together), this only removes log dirs and leaves your worktrees and branches

package/pipeline/skills/shared/core/multi-agent-review/SKILL.md

@@ -20,6 +20,25 @@ Skip Phase 0-3 and review a diff only. Input shapes: a PR (`#N`, `repo#N`, GitHu
 
 ## Steps
 
+0. **Session id and tracker record.** A pipeline run passes its own `TASK_ID`; a standalone review seeds a `review-` one and registers a tracker record, so the review shows wherever runs are read (the office panel, `multi-agent-status`):
+
+   ```bash
+   : "${TASK_ID:=review-$(date +%s)-$$}"
+   case "$TASK_ID" in review-*)
+     S="${LOGS_ROOT:-$HOME/.claude/logs/multi-agent}/$TASK_ID"; mkdir -p "$S"
+     printf '{"taskId":"%s","mode":"review","status":"in_progress","currentPhase":0}' "$TASK_ID" \
+       | node "$HOME/.copilot/scripts/write-state.mjs" "$S/agent-state.json" >/dev/null
+     export MULTI_AGENT_TASK_ID="$TASK_ID"
+     bash "$HOME/.copilot/scripts/phase-tracker.sh" init "$TASK_ID"
+     for p in "0:Input" "1:Diff" "2:Reviewers" "3:Triage" "4:Report"; do
+       bash "$HOME/.copilot/scripts/phase-tracker.sh" add "${p%%:*}" "${p#*:}"
+     done
+     bash "$HOME/.copilot/scripts/phase-tracker.sh" update 0 in_progress ;;
+   esac
+   ```
+
+   The steps map to tracker steps as in `$HOME/.claude/multi-agent-refs/review-standalone-tracker.md` (1/1a is 0, 2 is 1, 3-4 are 2, 5 is 3, 6-7 are 4), each call prefixed `MULTI_AGENT_TASK_ID=<the review- id> MULTI_AGENT_STRICT_TASK_ID=1`; there is no task widget, so call `phase-tracker.sh render` after each change. After step 7 close the record with `"status":"complete","currentPhase":4` through the same `write-state.mjs` call.
+
 1. **Resolve the input** (`{kind, provider}`):
    - PR URL / `#N` / `repo#N` -> `kind=pr` (`github` or `bitbucket-server`).
    - branch name -> `kind=branch` (local).

package/pipeline/skills/shared/core/multi-agent-scenario-audit/SKILL.md

@@ -53,7 +53,9 @@ Read the candidate lines it returns. A term nothing matched is listed under
 
 ## Step 3 - Verdict
 
-Write `/tmp/ma-verdicts.json`: `[{id, status, citations, searched, note}]`.
+Write the verdicts to a file in a folder of this run's own
+(`VERDICTS="$(mktemp -d)/verdicts.json"`, never a fixed `/tmp` name another
+user or a second audit could share): `[{id, status, citations, searched, note}]`.
 
 | Status | When | Needs |
 |---|---|---|
@@ -64,7 +66,7 @@ Write `/tmp/ma-verdicts.json`: `[{id, status, citations, searched, note}]`.
 
 ```bash
 node "$HOME/.claude/scripts/scenario-audit.mjs" verify --csv "<scenarios.csv>" \
-  --verdicts /tmp/ma-verdicts.json --repo "<repo>" --lang "<outputLanguage>"
+  --verdicts "$VERDICTS" --repo "<repo>" --lang "<outputLanguage>"
 ```
 
 ## Step 4 - Report

package/pipeline/skills/shared/core/multi-agent-serve/SKILL.md

@@ -59,5 +59,7 @@ environment `launch.json` declares; the client starts the process.
 `POST /v1/runs/{id}/answer` accepts only an option the run's pending question
 offered. `POST /v1/runs/{id}/kill` and `POST /v1/gc` act only on a second
 request carrying the single-use confirm token the first one returned, and a
-kill never deletes the remote branch or the logs. Autopilot can be turned off
-over HTTP, never on.
+kill never deletes the remote branch or the logs. Autopilot on, a stack change
+and a routine removal take the same two steps, accept no browser origin but
+the server's own page, and are tagged `local-only` for any future remote
+carrier.

package/pipeline/skills/shared/core/multi-agent-stack/SKILL.md

@@ -100,13 +100,21 @@ for ARG in "$@"; do
 done
 ```
 
-After resolving `$ON`, edit `.claude/settings.json` (create `{ "enabledPlugins": {} }` if absent) so that:
-- every plugin in `$ON` is set to `true`,
-- every stack toolkit **not** in `$ON` is set to `false` (leave non-`@multi-agent-plugins` entries untouched),
-- `ai-common-toolkit@multi-agent-plugins` and `ai-analyst-toolkit@multi-agent-plugins` are always `true`,
-- every `ai-*-engineering-toolkit@multi-agent-plugins` key is **deleted** (retired names).
+Then write it with the one writer of these rules (the office panel's
+`POST /v1/stack` calls the same script):
 
-Use the Read + Edit/Write tools (JSON must stay valid). Then print the resulting `enabledPlugins` block and run step 5 (Copilot/Codex refresh offer).
+```bash
+node "$HOME/.claude/scripts/stack-toggle.mjs" set --repo "$PWD" "$@" --json
+```
+
+`stack-toggle.mjs` applies the write rules above (selection `true`, every other
+stack toolkit `false`, `ai-common-toolkit` and `ai-analyst-toolkit` always
+`true`, retired `ai-*-engineering-toolkit` keys deleted, `xcode-integration@xcode-apple`
+following `ios` when the Apple marketplace is linked, every other key kept),
+writes the file atomically and prints the resulting `enabledPlugins`. It refuses
+an empty selection and an unknown stack (exit 1) and never hand-edits the JSON.
+`stack-toggle.mjs status --repo "$PWD" --json` is the read for status mode.
+Then print the resulting `enabledPlugins` block and run step 5 (Copilot/Codex refresh offer).
 
 ## Notes
 

package/pipeline/skills/shared/core/multi-agent-steer/SKILL.md

@@ -70,18 +70,19 @@ is being replaced.
    and `$INSTRUCTION` the text from step 3:
 
    ```bash
-   printf '{"pendingSteer":{"text":%s,"at":"%s","appliedAt":null,"appliedPhase":null}}' \
-     "$(node -e 'process.stdout.write(JSON.stringify(process.argv[1]))' "$INSTRUCTION")" \
-     "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
-     | node $HOME/.claude/scripts/write-state.mjs "$STATE_FILE"
+   node "$HOME/.claude/scripts/steer-run.mjs" "$STATE_FILE" --text "$INSTRUCTION"
    ```
 
-   The instruction is JSON-encoded by `node -e`, not by hand: it is arbitrary
-   user text, and a quote or newline in it would otherwise produce invalid JSON
-   or, worse, a payload that merges into fields nobody meant to touch.
+   `steer-run.mjs` takes the same lock `write-state.mjs` owns and merges
+   `pendingSteer` (`text`, `at`, `appliedAt: null`, `appliedPhase: null`) into
+   the state; the instruction is passed as one argument and JSON-encoded by the
+   script, never by hand, so a quote or newline in it cannot produce invalid
+   JSON or a payload that merges into other fields. It refuses a finished run
+   (exit 1) and prints the unconsumed instruction it replaced, if any. The
+   office panel's `POST /v1/runs/{id}/steer` calls the same function.
 
-   Exit 2 (lock timeout) → the task is mid-write. Retry once, then report it
-   rather than forcing the write.
+   Exit 2 (usage) or a lock timeout → the task is mid-write. Retry once, then
+   report it rather than forcing the write.
 
 6. **Confirm**: `🧭 Steer queued for #N  -  applies at the entry to Phase {N+1}`
 

package/pipeline/skills/shared/core/multi-agent-sync/SKILL.md

@@ -33,7 +33,7 @@ Run all steps automatically:
 ```
 Step 0: DOCTOR      node $HOME/.claude/scripts/doctor.mjs  -  exit 2 or 4 STOPS the sync
 Step 1: DETECT      Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 66 sub-command skills)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 69 sub-command skills)
 Step 2b: CODEX      Claude Code -> Codex CLI (1 router skill + sub-command specs as refs + agent TOML)
 Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub)
 Step 3d: DEV-TOOLKIT Companion MCP server -> detect movement, ship gates, commit + publish
@@ -229,14 +229,14 @@ When invoked with the `release` argument:
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}/SKILL.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**66 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**69 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-jira, analysis-resolve, autopilot, autopilot-off,
 autopilot-on, autopilot-status, bug-bash, build-optimize, channels, complaint-analysis,
 create-jira, design-check, diff-explain, doctor, estimate, feedback, forget,
 garbage-collect, graph, help, ios-coding-standard, issue, jira, kill,
-language, log, manual-test, model, postmortem, prune-logs,
+language, log, manual-test, model, office-off, office-on, office-status, postmortem, prune-logs,
 prune-prompts, purge, refactor, research, resume, review,
 review-analysis, review-issue, review-jira, route-off, route-on,
 route-status, routines, save, scaffold, scan, scenario-audit, search,

package/pipeline/skills/shared/core/multi-agent-test-gen/SKILL.md

@@ -43,9 +43,32 @@ Scripts: `test-gen-gate.mjs` (artefact, handle and write gates),
 ## Step 1 - Prepare
 
 1. Repo: `--repo`, else the current directory; confirm it in one line.
-   Platform: `--platform`, else detect as `multi-agent-test` does. Run id
-   `tg-<timestamp>`; `RUN="$HOME/.claude/logs/test-gen/<repo>/<timestamp>"`,
-   created with `mkdir -p "$RUN"`.
+   Platform: `--platform`, else detect as `multi-agent-test` does. One
+   timestamp names the run everywhere: `TS="$(date +%Y%m%d%H%M%S)"`, run id
+   `tg-$TS`, `RUN="$HOME/.claude/logs/test-gen/<repo>/$TS"`, created with
+   `mkdir -p "$RUN"`.
+   Register the run so its progress shows wherever runs are read (the office
+   panel, `multi-agent-status`), with one step per stage below:
+
+   ```bash
+   TG_ID="tg-$TS"
+   S="${LOGS_ROOT:-$HOME/.claude/logs/multi-agent}/$TG_ID"; mkdir -p "$S"
+   printf '{"taskId":"%s","mode":"test-gen","status":"in_progress","currentPhase":0}' "$TG_ID" \
+     | node "$HOME/.copilot/scripts/write-state.mjs" "$S/agent-state.json" >/dev/null
+   export MULTI_AGENT_TASK_ID="$TG_ID"
+   bash "$HOME/.copilot/scripts/phase-tracker.sh" init "$TG_ID"
+   for p in "0:Prepare" "1:Inventory" "2:Discovery" "3:Handles" "4:Tests" "5:Report"; do
+     bash "$HOME/.copilot/scripts/phase-tracker.sh" add "${p%%:*}" "${p#*:}"
+   done
+   bash "$HOME/.copilot/scripts/phase-tracker.sh" update 0 in_progress
+   ```
+
+   Each step below starts with `update <N> in_progress` and ends with
+   `update <N> completed` (Step 5 and Step 6 share step 4), every call prefixed
+   `MULTI_AGENT_TASK_ID=<the tg- id, written out> MULTI_AGENT_STRICT_TASK_ID=1`.
+   There is no task widget here: call `phase-tracker.sh render` after each
+   change, and close the record with `"status":"complete","currentPhase":5`
+   through the same `write-state.mjs` call when the report is written.
 2. Toolkit: `test_results_classify`, `coverage_gap` and `ui_locator_codegen`
    need `@mmerterden/multi-agent-toolkit-mcp` >= v3.25.0. Check the tool list
    once. Each missing tool has a fallback in `stages.md` (classify from the

package/pipeline/skills/skills-index.md

@@ -3,7 +3,7 @@
 > Auto-generated by `pipeline/scripts/build-skills-index.mjs`  -  do not hand-edit.
 > Regenerate with `node pipeline/scripts/build-skills-index.mjs`.
 
-**234 skills** across 2 groups.
+**237 skills** across 2 groups.
 
 | Group | Name | Platform | Description |
 |-------|------|----------|-------------|
@@ -130,6 +130,9 @@
 | core | `multi-agent-log` |  -  | Show the agent-log.md for the given task. With no ID, shows the most recent task. Use when asked what a task did, or to read its log. |
 | core | `multi-agent-manual-test` |  -  | Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 3 user-test step, standalone (the UI Bug Hunter lives a |
 | core | `multi-agent-model` |  -  | Turn the top model rung on or off and keep the cost ledger's pricing in step with it. Use when asked to enable or disable Fable, or which mo |
+| core | `multi-agent-office-off` |  -  | Close the office panel and stop its local server. Use when done with the panel. |
+| core | `multi-agent-office-on` |  -  | Open the office: a local browser page that shows runs and agents live and drives the ecosystem (new runs, jobs, PRs, keys, memory, system, c |
+| core | `multi-agent-office-status` |  -  | Whether the office panel is running, its URL (never the token) and its last actions. Use when unsure if the panel is open. |
 | core | `multi-agent-postmortem` |  -  | Post-mortem of a run from its session transcripts: loops, stalls, root-cause hypotheses on file:line, fixes. Read-only, redacted. Use when a |
 | core | `multi-agent-prune-logs` |  -  | Delete per-task project logs under ~/.claude/logs/multi-agent (filter by age/project/task). Audit trail + metrics are preserved. Dry-run fir |
 | core | `multi-agent-prune-prompts` |  -  | Zero-base prompt review: measure the always-on instruction footprint, classify every rule block, propose keep/trial-removal/delete; applies  |