@mmerterden/multi-agent-pipeline 16.20.0 → 16.23.0

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

@@ -31,8 +31,8 @@ Run all steps automatically:
 
 ```
 Step 1: DETECT      Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 55 sub-command skills)
-Step 2b: CODEX      Claude Code -> Codex CLI (1 router skill + 55 specs as refs + 8 agent TOML)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 51 sub-command skills)
+Step 2b: CODEX      Claude Code -> Codex CLI (1 router skill + 51 specs as refs + 8 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
 Step 4: WEBSITE     Version + phase/model counts -> {website-host} (i18n + projects.ts)
@@ -98,7 +98,7 @@ If nothing is stale -> report "All targets up to date" and stop.
 ## Codex Sync (Step 2b)
 
 This step does **not** hand-copy files. The Codex tree is a *transform* of the Claude
-tree, not a mirror: the 55 sub-command specs become reference files (Codex silently
+tree, not a mirror: the 51 sub-command specs become reference files (Codex silently
 truncates its skills block  -  see `cross-cli-contract.md` 2.6), every reference to a
 CLI-owned tree is retargeted (`agents/<persona>.md` becomes `.toml`, the dispatcher
 becomes the router skill), the 8 personas are regenerated as TOML with a model +
@@ -224,18 +224,18 @@ When invoked with the `release` argument:
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}/SKILL.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**55 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**51 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels,
-complaint-analysis, create-jira, design-check, dev, dev-autopilot, dev-local,
-dev-local-autopilot, diff-explain, feedback, forget, garbage-collect,
-graph, help, ios-coding-standard, issue, jira, kill, language, local,
-local-autopilot, log, manual-test, prune-logs, prune-prompts, purge,
-refactor, resume, resume-local, review, review-analysis, review-issue,
-review-jira, routines, save, scan, search, setup, stack, status, steer,
-store-ready, sync, test, test-accessibility, test-dark-mode,
-test-dynamic-type, test-screenshots, testflight-validation, uninstall, update
+complaint-analysis, create-jira, design-check, diff-explain, feedback,
+forget, garbage-collect, graph, help, ios-coding-standard, issue, jira,
+kill, language, local, local-autopilot, log, manual-test, prune-logs,
+prune-prompts, purge, refactor, resume, resume-local, review,
+review-analysis, review-issue, review-jira, routines, save, scan, search,
+setup, stack, status, steer, store-ready, sync, test, test-accessibility,
+test-dark-mode, test-dynamic-type, test-screenshots, testflight-validation,
+uninstall, update
 ```
 
 **NOT synced**: `refs/*`  -  Lazy-load references, Claude Code specific

package/pipeline/skills/shared/external/backlog/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: backlog
 version: 1.0.0
-description: "The engineering backlog registry for deferred-but-approved work in this codebase. Every job the user defers ('defer it', 'add it to the list', 'later', 'not now') lands HERE with its full spec, origin, and unblock condition, so deferral never means loss. Load when the user defers work, asks 'what's on the backlog / the list', says 'work the backlog' / 'pick up <item>', or when completing an item. The bundled BACKLOG.md is the registry; entries move deferred -> ready -> in-progress -> done and are never deleted."
+description: "The engineering backlog registry for deferred-but-approved work in this codebase. Every job the user defers ('defer it', 'add it to the list', 'later', 'not now') lands HERE with its full spec, origin, and unblock condition, so deferral never means loss. Load when the user defers work, asks 'what's on the backlog / the list', says 'work the backlog' / 'pick up <item>', or when completing an item. The bundled BACKLOG.md is the registry; entries move deferred -> ready -> in-progress -> done, and the registry is re-audited against live code - a rotted entry deletes, a done record retires once what it taught is re-homed in the skill that owns it. This records WHAT IS OWED; git history records what happened."
 user-invocable: true
-argument-hint: [list | add | pick <id> | done <id>]
+argument-hint: [list | add | pick <id> | done <id> | re-audit]
 allowed-tools: Read, Grep, Glob, Edit, Write
 ---
 
@@ -13,14 +13,17 @@ allowed-tools: Read, Grep, Glob, Edit, Write
 > **Bundled:** [BACKLOG.md](BACKLOG.md) - the registry. The heart of this skill.
 > **Iron rule:** moving a job onto this list is a MOVE, never a rewrite - the FULL spec
 > travels verbatim. A compressed one-liner is a loss; the point of the backlog is that
-> deferring costs nothing later.
+> deferring costs nothing later. The registry stays honest in the other direction too:
+> entries are re-audited against live code, and an entry whose named types or premises
+> no longer exist is DELETED, never left readable as live.
 
 ## When to load
 
 - The user defers work: "defer it", "add it to the list", "later", "not now", "backlog this".
 - The user asks about it: "what's on the backlog", "what's on the list", "what's owed".
 - The user works it: "work the backlog", "pick up <id>", "do the next one".
-- An item completes: mark it done (never delete).
+- An item completes: mark it done, and retire the record once what it taught has a home.
+- A staleness signal arrives (a rename, a deleted subject, a doubted claim): re-audit.
 
 ## The registry contract
 
@@ -28,7 +31,7 @@ Every entry in `BACKLOG.md` carries, verbatim:
 
 - **id** - short stable slug (`kebab-case`), assigned on add.
 - **title** - one line.
-- **state** - `deferred` -> `ready` -> `in-progress` -> `done`. Entries only move forward; nothing is deleted.
+- **state** - `deferred` -> `ready` -> `in-progress` -> `done`. Entries move forward; they leave the registry only by the two rules below (rot, or a re-homed done record), never by being quietly rewritten.
 - **origin** - where it came from (the task/PR/finding/conversation that spawned it).
 - **spec** - the FULL description, verbatim from when it was deferred. Not a summary.
 - **unblock** - the condition that makes it actionable (a dependency, a decision, a date). `deferred` items without an unblock condition are just `ready`.
@@ -42,7 +45,8 @@ Prefer an append-only markdown table or section list in `BACKLOG.md`; never over
 | `list` | Show entries grouped by state (ready first, then deferred, then in-progress; done collapsed). |
 | `add` | Capture the deferred job with its full spec + origin + unblock condition. Assign an id. |
 | `pick <id>` | Move `ready`/`deferred` -> `in-progress`; surface the full spec so work resumes with zero context loss. |
-| `done <id>` | Move -> `done`. Keep the entry (it becomes the record of what was owed and delivered). |
+| `done <id>` | Move -> `done` with the evidence (PR/commit + date). The record RETIRES from the registry once what it taught is written into the skill or doc that owns it - git history is the archive of what was owed and delivered. A done entry kept past that point is a second place for the same truth to rot. |
+| `re-audit` | Verify every entry's named types, paths and claims against LIVE code (binary-safe: `LC_ALL=C grep -a`, so a repo with binary blobs does not silently return nothing). A subject that no longer exists deletes its entry; a changed fact restates it. **Numbers move by measurement, never by edit** - a count adjusted to match an impression reads as evidence and is worse than no count. |
 
 ## Why keep it whole
 

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`.
 
-**211 skills** across 2 groups.
+**207 skills** across 2 groups.
 
 | Group | Name | Platform | Description |
 |-------|------|----------|-------------|
@@ -101,17 +101,13 @@
 | core | `multi-agent-complaint-analysis` |  -  | Customer-complaint triage. Ingests complaints (paste, csv/xlsx/txt/json file, Jira issue, Confluence URL), fetches Graylog evidence per trx/ |
 | core | `multi-agent-create-jira` |  -  | Create a standards-compliant Jira issue (Task / Bug / Story): asks the type, mines project conventions, drafts from a standard template with |
 | core | `multi-agent-design-check` |  -  | Mock-mode vs Figma design audit (iOS / Android, local-only). Pick repo + module, gate on mock support, enumerate every state driver into a c |
-| core | `multi-agent-dev` |  -  | Removed in v16.0.0. Depth is a question the run asks, not a command name: start /multi-agent and answer Short. Invoke only to see that redir |
-| core | `multi-agent-dev-autopilot` |  -  | Removed in v16.0.0 and not replaced: an unsupervised run is always the full pipeline now. Invoke only to be pointed at /multi-agent:autopilo |
-| core | `multi-agent-dev-local` |  -  | Removed in v16.0.0. Its worktree-free twin is /multi-agent:local, which asks the same depth question; answer Short there. Invoke only to see |
-| core | `multi-agent-dev-local-autopilot` |  -  | Retired alongside its worktree twin in v16.0.0, with nothing standing in for it. Invoke only to be pointed at /multi-agent:local-autopilot o |
 | core | `multi-agent-diff-explain` |  -  | Map Phase 4 triage findings to branch diff lines. Read-only post-hoc command, used after review to answer 'which finding lines up with which |
 | core | `multi-agent-feedback` |  -  | Send one message to the maintainer: a bug, an idea or a question. Only the text you type is sent - no logs, no repo names, no paths. Shows t |
 | core | `multi-agent-forget` |  -  | Remove a saved /multi-agent routine (created by /multi-agent:save): deletes its local-only command and its registry entry. Asks which one an |
 | core | `multi-agent-garbage-collect` |  -  | Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before d |
 | core | `multi-agent-graph` |  -  | Build and query this repo's code graph: a deterministic, LLM-free map of symbols, imports and references used to narrow Phase 1's Explore sc |
 | core | `multi-agent-help` |  -  | Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatib |
-| core | `multi-agent-ios-coding-standard` |  -  | Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to dev/dev-l |
+| core | `multi-agent-ios-coding-standard` |  -  | Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to /multi-ag |
 | core | `multi-agent-issue` |  -  | List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline. Use when a GitHub issue should be picked up and s |
 | core | `multi-agent-jira` |  -  | List open Jira issues, pick one, and launch the multi-agent pipeline. Use when a Jira issue should be picked up and started without knowing  |
 | core | `multi-agent-kill` |  -  | Stop the given task, then remove its worktree and branch. Asks for confirmation. Use when a running or stuck task should be stopped and its  |

package/pipeline/commands/multi-agent/dev/SKILL.md

@@ -1,17 +0,0 @@
----
-description: "Removed in v16.0.0. Depth is a question the run asks, not a command name: start /multi-agent and answer Short. Invoke only to see that redirect."
-description-tr: "v16.0.0'da kaldırıldı. Pipeline derinliği artık komut adı değil: /multi-agent çalıştırıp derinlik sorusunda Kısa seçin."
----
-
-# multi-agent dev  -  Removed in v16.0.0
-
-Until v16.0.0, `--dev` and the four `dev-*` commands existed only to express one boolean: skip Analysis and Planning. That boolean is now a question, asked once at Phase 0 Step 7.5, where the recommendation can come from the detected `taskType`.
-
-```
-/multi-agent:dev has been removed. Run /multi-agent and choose Short at the
-depth question - same pipeline, one picker step earlier.
-```
-
-Print the line above, then continue at the named entry with the same `$ARGUMENTS`. Do not run any phase from this file: it carries no tracker contract and no phase set.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

package/pipeline/commands/multi-agent/dev-autopilot/SKILL.md

@@ -1,23 +0,0 @@
----
-description: "Removed in v16.0.0 and not replaced: an unsupervised run is always the full pipeline now. Invoke only to be pointed at /multi-agent:autopilot or the interactive picker."
-description-tr: "v16.0.0'da kaldırıldı, birebir karşılığı yok: gözetimsiz koşular artık her zaman tam pipeline. /multi-agent:autopilot veya /multi-agent'a yönlendirir."
----
-
-# multi-agent dev-autopilot  -  Removed in v16.0.0
-
-This one has no equivalent, and the removal is deliberate rather than a rename.
-
-Depth is a question now, and autopilot may not ask questions. That leaves one choice to make on the user's behalf, and Full is the honest default: skipping analysis and planning in a run nobody is watching is where a wrong shortcut costs the most, because there is no one there to notice what it lost.
-
-```
-/multi-agent:dev-autopilot has been removed. "Fast plus unattended" no longer
-exists as a combination.
-  1. /multi-agent:autopilot  - unattended, full pipeline (slower, more tokens)
-  2. /multi-agent            - short pipeline, but asks the depth question
-```
-
-If a cron job or script calls this name it needs editing, and the two options trade differently: option 1 stays unattended and will take longer and cost more per run, option 2 stays fast and needs a person.
-
-Print the block above and stop. Do not pick an entry on the user's behalf: the two options differ in what gets skipped and who is watching, and that is their call. Autopilot passed to this stub still stops here - a zero-interaction contract does not authorise choosing a different pipeline than the one that was asked for.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

package/pipeline/commands/multi-agent/dev-local/SKILL.md

@@ -1,17 +0,0 @@
----
-description: "Removed in v16.0.0. Its worktree-free twin is /multi-agent:local, which asks the same depth question; answer Short there. Invoke only to see that redirect."
-description-tr: "v16.0.0'da kaldırıldı. /multi-agent:local çalıştırıp derinlik sorusunda Kısa seçin."
----
-
-# multi-agent dev-local  -  Removed in v16.0.0
-
-Depth stopped being a command name in v16.0.0. `--local` is still a command, because a worktree is a real difference in where the work happens; depth is not.
-
-```
-/multi-agent:dev-local has been removed. Run /multi-agent:local and choose
-Short at the depth question - same pipeline, one picker step earlier.
-```
-
-Print the line above, then continue at the named entry with the same `$ARGUMENTS`. Do not run any phase from this file: it carries no tracker contract and no phase set.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

package/pipeline/commands/multi-agent/dev-local-autopilot/SKILL.md

@@ -1,21 +0,0 @@
----
-description: "Retired alongside its worktree twin in v16.0.0, with nothing standing in for it. Invoke only to be pointed at /multi-agent:local-autopilot or the interactive picker."
-description-tr: "v16.0.0'da kaldırıldı, birebir karşılığı yok: gözetimsiz koşular artık her zaman tam pipeline. /multi-agent:local-autopilot veya /multi-agent:local'e yönlendirir."
----
-
-# multi-agent dev-local-autopilot  -  Removed in v16.0.0
-
-Same removal as `dev-autopilot`, on the no-worktree path. Depth is a question, autopilot may not ask one, and Full is the safer answer when nobody is watching.
-
-```
-/multi-agent:dev-local-autopilot has been removed. "Fast plus unattended" no
-longer exists as a combination.
-  1. /multi-agent:local-autopilot - unattended, full pipeline, no worktree
-  2. /multi-agent:local           - short pipeline, but asks the depth question
-```
-
-If a cron job or script calls this name it needs editing, and the two options trade differently: option 1 stays unattended and will take longer and cost more per run, option 2 stays fast and needs a person.
-
-Print the block above and stop. Do not pick an entry on the user's behalf: the two options differ in what gets skipped and who is watching, and that is their call. Autopilot passed to this stub still stops here - a zero-interaction contract does not authorise choosing a different pipeline than the one that was asked for.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

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

@@ -1,19 +0,0 @@
----
-name: multi-agent-dev
-language: en
-description: "Removed in v16.0.0. Depth is a question the run asks, not a command name: start /multi-agent and answer Short. Invoke only to see that redirect."
-user-invocable: true
----
-
-# multi-agent dev  -  Removed in v16.0.0
-
-Until v16.0.0, `--dev` and the four `dev-*` commands existed only to express one boolean: skip Analysis and Planning. That boolean is now a question, asked once at Phase 0 Step 7.5, where the recommendation can come from the detected `taskType`.
-
-```
-/multi-agent:dev has been removed. Run /multi-agent and choose Short at the
-depth question - same pipeline, one picker step earlier.
-```
-
-Print the line above, then continue at the named entry with the same `$ARGUMENTS`. Do not run any phase from this file: it carries no tracker contract and no phase set.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

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

@@ -1,25 +0,0 @@
----
-name: multi-agent-dev-autopilot
-language: en
-description: "Removed in v16.0.0 and not replaced: an unsupervised run is always the full pipeline now. Invoke only to be pointed at /multi-agent:autopilot or the interactive picker."
-user-invocable: true
----
-
-# multi-agent dev-autopilot  -  Removed in v16.0.0
-
-This one has no equivalent, and the removal is deliberate rather than a rename.
-
-Depth is a question now, and autopilot may not ask questions. That leaves one choice to make on the user's behalf, and Full is the honest default: skipping analysis and planning in a run nobody is watching is where a wrong shortcut costs the most, because there is no one there to notice what it lost.
-
-```
-/multi-agent:dev-autopilot has been removed. "Fast plus unattended" no longer
-exists as a combination.
-  1. /multi-agent:autopilot  - unattended, full pipeline (slower, more tokens)
-  2. /multi-agent            - short pipeline, but asks the depth question
-```
-
-If a cron job or script calls this name it needs editing, and the two options trade differently: option 1 stays unattended and will take longer and cost more per run, option 2 stays fast and needs a person.
-
-Print the block above and stop. Do not pick an entry on the user's behalf: the two options differ in what gets skipped and who is watching, and that is their call. Autopilot passed to this stub still stops here - a zero-interaction contract does not authorise choosing a different pipeline than the one that was asked for.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

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

@@ -1,19 +0,0 @@
----
-name: multi-agent-dev-local
-language: en
-description: "Removed in v16.0.0. Its worktree-free twin is /multi-agent:local, which asks the same depth question; answer Short there. Invoke only to see that redirect."
-user-invocable: true
----
-
-# multi-agent dev-local  -  Removed in v16.0.0
-
-Depth stopped being a command name in v16.0.0. `--local` is still a command, because a worktree is a real difference in where the work happens; depth is not.
-
-```
-/multi-agent:dev-local has been removed. Run /multi-agent:local and choose
-Short at the depth question - same pipeline, one picker step earlier.
-```
-
-Print the line above, then continue at the named entry with the same `$ARGUMENTS`. Do not run any phase from this file: it carries no tracker contract and no phase set.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.

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

@@ -1,23 +0,0 @@
----
-name: multi-agent-dev-local-autopilot
-language: en
-description: "Retired alongside its worktree twin in v16.0.0, with nothing standing in for it. Invoke only to be pointed at /multi-agent:local-autopilot or the interactive picker."
-user-invocable: true
----
-
-# multi-agent dev-local-autopilot  -  Removed in v16.0.0
-
-Same removal as `dev-autopilot`, on the no-worktree path. Depth is a question, autopilot may not ask one, and Full is the safer answer when nobody is watching.
-
-```
-/multi-agent:dev-local-autopilot has been removed. "Fast plus unattended" no
-longer exists as a combination.
-  1. /multi-agent:local-autopilot - unattended, full pipeline, no worktree
-  2. /multi-agent:local           - short pipeline, but asks the depth question
-```
-
-If a cron job or script calls this name it needs editing, and the two options trade differently: option 1 stays unattended and will take longer and cost more per run, option 2 stays fast and needs a person.
-
-Print the block above and stop. Do not pick an entry on the user's behalf: the two options differ in what gets skipped and who is watching, and that is their call. Autopilot passed to this stub still stops here - a zero-interaction contract does not authorise choosing a different pipeline than the one that was asked for.
-
-This stub exists so the old name fails loudly and usefully for one minor release instead of silently doing nothing. It is deleted in the next one.