@mmerterden/multi-agent-pipeline 11.5.0 → 12.1.0

package/CHANGELOG.md

@@ -14,6 +14,81 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ---
 
+## [12.1.0] - 2026-07-21
+
+### Security
+- **`agent-guard.sh` is now wired by the default installer** (was opt-in via the setup template). A plain `install` now OS-enforces the two load-bearing git gates on every `Bash` tool call: no AI/assistant attribution in commit messages, and no force-push to a protected branch (`main`/`master`/`develop`).
+- **Force-push protection now fails CLOSED.** A detected force-push that can't be tokenized, or a bare force-push while the current branch can't be confirmed non-protected, is blocked rather than allowed. (The general guard stays fail-open; only the data-loss path is fail-closed.)
+- **Multi-repo clone hardening.** `cmd_prepare` disables git's `ext::`/`fd::` remote helpers (`protocol.ext.allow=never`, `protocol.fd.allow=never`) and ends options with `--`, closing an arbitrary-command-execution / option-injection vector on repo URLs sourced from `.gitmodules` suggestions. Local/file/https/ssh clones are unaffected.
+
+### Changed
+- **Node floor raised to 20** (`.nvmrc`, `engines.node` → `>=20.0.0`). Node 18 was EOL and untested by CI; the matrix already covers 20/22.
+
+### Refactored
+- **Token-cost pricing is now a single source.** The per-Mtok cost formula, previously copy-pasted across ~6 bash/mjs scripts, lives in `cost-lib.sh` (bash) + `_cost.mjs` (Node), both reading the shared `cost-table.json`. Zero runtime dependencies preserved.
+
+### Added
+- **`smoke-source-parity.sh`** — guards feature-set drift between the two source trees (`commands/multi-agent/<name>` vs `skills/shared/core/multi-agent-<name>`); fails if a feature exists in one tree but not the other.
+
+### Docs
+- Refreshed post-v12 doc drift: `SECURITY.md` + `ROADMAP.md` support/version markers → 12.x; `docs/features.md` smoke-suite count `10` → `100+`; ADR index now lists 0008 and 0008 carries a v10.7.0 amendment (the `_adapters.mjs` module was removed); `CONTRIBUTING.md` coverage claim clarified (local-only) and the stale phase-docs path corrected to `pipeline/multi-agent-refs/phases/`.
+
+---
+
+## [12.0.0] - 2026-07-20
+
+Command rename (breaking), a full-cleanup uninstall mode, outputLanguage-aware
+picker descriptions, worktree residue cleanup, and cleanup-command hardening.
+
+### Breaking
+
+- **`/multi-agent:delete` renamed to `/multi-agent:uninstall`.** The old name is
+  gone (no alias). The Copilot twin is now `multi-agent-uninstall`. Command
+  count stays 38; the canonical inventory, sync list, help, and cross-cli
+  contract were updated. Per the versioning policy a renamed command forces a
+  major bump.
+
+### Added
+
+- **`uninstall --all-data` full-cleanup mode.** Standard uninstall still keeps
+  settings + logs; `--all-data` additionally removes
+  `multi-agent-preferences.json` and the entire `~/.claude/logs/multi-agent/`
+  tree (task logs, state, metrics, audit). Tokens, `CLAUDE.md`, and the
+  user-owned `rules/` are preserved in both modes. The slash command asks a
+  scope picker (Standard vs Full cleanup) before the double confirmation.
+- **outputLanguage-aware slash-command descriptions.** Every command ships an
+  English `description` plus a `description-tr`; when `outputLanguage=tr`, the
+  installer and the `/multi-agent:language` toggle swap the installed
+  `~/.claude` descriptions to Turkish (reversible via a `description-en`
+  sidecar). Repo and npm files stay English; `/multi-agent:sync` normalizes and
+  gates the round trip so localized text can never leak back into the repo.
+  New `localize-commands.mjs` + `smoke-description-tr.sh`.
+- **`/multi-agent:garbage-collect` worktree phase.** New `gc-worktrees.sh`
+  (dry-run by default) prunes stale worktree admin entries, removes orphan
+  `.worktrees/*` dirs no longer registered as worktrees, unstages gitlink
+  ("Subproject commit") residue from a pre-guard `git add -A`, and ensures the
+  `.worktrees/` `info/exclude` guard. Registered worktrees are never touched.
+- **Worktree residue guard on creation.** Phase 0 (single- and multi-repo) and
+  the Copilot core skill now append `.worktrees/` to the clone-local
+  `.git/info/exclude` before every `worktree add`, so a blanket `git add -A`
+  can no longer record `.worktrees/{id}` gitlinks into shared branches.
+- **update-check reaches npx-only installs.** The installer stamps
+  `~/.claude/.pipeline-version` (and the Copilot equivalent); `update-check.sh`
+  falls back to it when no repo clone is present, so users who never cloned the
+  repo still see the "update available" prompt. Uninstall removes the marker.
+
+### Changed / hardened
+
+- **`/multi-agent:purge` now runs a real backend** (`purge.sh`): dry-run by
+  default, every `rm` target resolved strictly inside `<repo>/.worktrees/`,
+  refuses `/`, `$HOME`, and the project root; main worktree and
+  main/master/develop always preserved. `--delete-remote` gates remote-branch
+  deletion behind `--yes`.
+- **`prune-logs.sh` / `gc-tmp.sh` hardened**: safe id/path validation, the
+  audit trail + metrics corpus never removed, containment guards on deletion
+  roots. New/expanded smokes: `smoke-purge.sh`, plus prune-logs and gc-tmp
+  coverage.
+
 ## [11.5.0] - 2026-07-16
 
 Full-project refactor round: 20 verified defect fixes (install lifecycle, shell

package/docs/adr/0007-multi-tool-adapter-framework.md

@@ -64,7 +64,7 @@ Each adapter exports a `{ name, install, uninstall }` contract. New adapters are
 
 ### Token-preserving uninstall
 
-Every install path has a documented opposite via `npx @mmerterden/multi-agent-pipeline uninstall` (or `delete` alias). Slash command: `/multi-agent:delete` with a Copilot CLI peer `multi-agent-delete`.
+Every install path has a documented opposite via `npx @mmerterden/multi-agent-pipeline uninstall`. Slash command: `/multi-agent:uninstall` (renamed from `:delete` in v12.0.0) with a Copilot CLI peer `multi-agent-uninstall`. A `--all-data` flag extends it to also clear pipeline settings and the log root; tokens are never touched.
 
 The uninstaller is **contractually forbidden** from touching:
 
@@ -94,7 +94,7 @@ Positive:
 Negative / costs:
 
 - 6 adapters means 6 places where the format mapping can drift from upstream tool changes. Mitigation: round-trip smoke tests for each adapter exercise install + uninstall on every PR.
-- `--all-tools` writes ~900 files (174 cursor + ~50 windsurf concat + 173 cline + 161 copilot-chat + 161 continue + 1 zed) into the user's repo. Acceptable — `.gitignore` patterns already cover most of these (`.cursor/`, `.continue/`, `.clinerules/`), and `:delete` cleans them all in one step.
+- `--all-tools` writes ~900 files (174 cursor + ~50 windsurf concat + 173 cline + 161 copilot-chat + 161 continue + 1 zed) into the user's repo. Acceptable: `.gitignore` patterns already cover most of these (`.cursor/`, `.continue/`, `.clinerules/`), and `:uninstall` cleans them all in one step.
 - Per-tool format drift across tool versions (e.g. Cursor's `.mdc` format changes in 2027) requires per-adapter maintenance. Insulated from the orchestrator: bumping a Tier 2/3 tool format never touches Phase 1-7 logic.
 
 ## Alternatives Considered

package/docs/adr/0008-installer-modularization-and-secret-leak-defense.md

@@ -2,6 +2,8 @@
 
 **Status:** Accepted · 2026-04-27 (v8.0.0)
 
+> **Amended v10.7.0:** the `_adapters.mjs` module and its third-party adapter dispatch were removed when the pipeline narrowed to Claude Code + Copilot CLI (see ADR 0007). `install/` now ships **8** modules, not 9; the module list below records the v8.0.0 decision as it shipped at the time.
+
 ## Context
 
 Two pressures collided during the v7.x line:

package/docs/adr/README.md

@@ -17,6 +17,7 @@ Format: lightly adapted from [Michael Nygard's ADR template](https://cognitect.c
 | [0005](./0005-lazy-phase-docs.md)      | Lazy-loaded phase docs with per-phase token budget | Accepted |
 | [0006](./0006-skills-core-external-split.md) | `shared/core/` vs `shared/external/` source org    | Accepted |
 | [0007](./0007-multi-tool-adapter-framework.md) | Multi-tool adapter framework + token-preserving uninstall | Superseded by v10.7.0 (adapters removed; Claude Code + Copilot CLI only) |
+| [0008](./0008-installer-modularization-and-secret-leak-defense.md) | Installer modularization + secret-leak defense | Accepted (amended v10.7.0: adapter module removed) |
 
 ## Writing a New ADR
 

package/docs/features.md

@@ -201,11 +201,11 @@ All critical state files are schema-validated at read and write time:
 
 ### Smoke Test Suites
 
-10 suites: add-detail (14 body-preservation assertions), review-triage (validator exit codes), prefs (schema round-trip), state (agent-state lifecycle), metrics (telemetry emission), sync (instruction parity), secret-scan (hook patterns), phase-banner (terminal UI), token-budget (per-phase limits), phase-tracker (progress tracking).
+100+ suites, auto-discovered from `smoke-*.sh` (no hardcoded list). Representative: add-detail (body-preservation assertions), review-triage (validator exit codes), prefs (schema round-trip), state (agent-state lifecycle), metrics (telemetry emission), sync (instruction parity), secret-scan (hook patterns), phase-banner (terminal UI), token-budget (per-phase limits), phase-tracker (progress tracking).
 
 ### Adversarial Eval Fixtures
 
-10 fixtures that test triage resilience against adversarial reviewer output: over-rejection, hallucinated findings, contradictions, invalid JSON, schema violations, duplicate findings, scope creep, empty results, timeout simulation, and combined edge cases.
+Adversarial fixtures that test triage resilience against adversarial reviewer output: over-rejection, hallucinated findings, contradictions, invalid JSON, schema violations, duplicate findings, scope creep, empty results, timeout simulation, and combined edge cases.
 
 ### Sync Parity Check
 

package/install/claude.mjs

@@ -15,9 +15,11 @@
  */
 
 import { existsSync, readFileSync, readdirSync, rmSync, statSync, writeFileSync } from "fs";
-import { join } from "path";
+import { join, dirname } from "path";
 import { execSync } from "child_process";
 
+import { localizeCommands } from "../pipeline/scripts/localize-commands.mjs";
+
 import {
   copyDir,
   copyFile,
@@ -117,6 +119,28 @@ function installCommands(pipelineSrc, dest, useSymlinks) {
   if (restored > 0) {
     console.log(`    -> preserved ${restored} local-only alias wrapper(s)`);
   }
+  localizeCommandDescriptions(pipelineSrc, ownedCmdDir);
+}
+
+// Picker descriptions follow prefs.global.outputLanguage: files shipping a
+// description-tr frontmatter line get their description swapped in the
+// INSTALLED tree only (repo and npm package stay English; /multi-agent:sync
+// restores English before mirroring back). Failure is non-fatal.
+function localizeCommandDescriptions(pipelineSrc, ownedCmdDir) {
+  if (isDryRun()) return;
+  try {
+    const home = dirname(dirname(ownedCmdDir));
+    const prefsPath = join(home, "multi-agent-preferences.json");
+    if (!existsSync(prefsPath)) return;
+    const prefs = JSON.parse(readFileSync(prefsPath, "utf-8"));
+    if (prefs?.global?.outputLanguage !== "tr") return;
+    const changed = localizeCommands(ownedCmdDir, "apply");
+    if (changed > 0) {
+      console.log(`    -> localized ${changed} command description(s) to outputLanguage=tr`);
+    }
+  } catch {
+    // advisory only - installed tree simply stays English
+  }
 }
 
 // Snapshot single-level command dirs whose SKILL.md declares `local-only: true`
@@ -450,6 +474,32 @@ export function configureSettings(home) {
       settingsChanged = true;
     }
 
+    // agent-guard.sh: the second load-bearing gate - blocks AI/assistant
+    // attribution in commit messages and force-push to a protected branch.
+    // Like pre-commit-check.sh it self-filters on the Bash command via stdin
+    // JSON, so the matcher is the tool name "Bash". Wired by default (was
+    // previously opt-in via the setup template, leaving force-push and
+    // attribution unguarded on a plain install).
+    const isAgentGuardEntry = (h) =>
+      Array.isArray(h.hooks) &&
+      h.hooks.some(
+        (sub) => typeof sub.command === "string" && sub.command.includes("agent-guard.sh"),
+      );
+    if (!settings.hooks.PreToolUse.some(isAgentGuardEntry)) {
+      settings.hooks.PreToolUse.push({
+        matcher: "Bash",
+        hooks: [
+          {
+            type: "command",
+            command: "bash $HOME/.claude/scripts/agent-guard.sh",
+            timeout: 10,
+            statusMessage: "Checking commit/push safety (attribution + force-push)...",
+          },
+        ],
+      });
+      settingsChanged = true;
+    }
+
     if (settingsChanged && isDryRun()) {
       console.log(`    [dry-run] would update ${SETTINGS_PATH} (hooks + env)`);
     } else if (settingsChanged) {

package/install/index.mjs

@@ -11,9 +11,12 @@
 import { dirname } from "path";
 import { fileURLToPath } from "url";
 
+import { readFileSync } from "fs";
+import { join } from "path";
+
 import { installClaude } from "./claude.mjs";
 import { installCopilot } from "./copilot.mjs";
-import { setDryRun } from "./_common.mjs";
+import { setDryRun, writeFile } from "./_common.mjs";
 import { sendInstallTelemetry } from "./_telemetry.mjs";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
@@ -95,6 +98,10 @@ export async function runInstall(argv) {
   if (forClaude) installClaude(installerCtx);
   if (forCopilot) installCopilot(installerCtx);
 
+  // Version marker: update-check.sh falls back to this for npx-only installs
+  // that have no pipeline repo clone to read a version from.
+  writeVersionMarkers({ home: HOME, forClaude, forCopilot });
+
   if (dryRun) {
     console.log("");
     console.log("  Dry-run complete — nothing was written. Re-run without --dry-run to install.");
@@ -108,6 +115,32 @@ export async function runInstall(argv) {
   sendInstallTelemetry({ packageRoot: PIPELINE_ROOT, flags });
 }
 
+/**
+ * Stamp the installed package version into each target so the advisory
+ * update check works without a repo clone. Failure is non-fatal.
+ *
+ * @param {{home: string, forClaude: boolean, forCopilot: boolean}} opts
+ */
+export function writeVersionMarkers({ home, forClaude, forCopilot }) {
+  let version;
+  try {
+    version = JSON.parse(readFileSync(join(PIPELINE_ROOT, "package.json"), "utf-8")).version;
+  } catch {
+    return;
+  }
+  if (!version) return;
+  const targets = [];
+  if (forClaude) targets.push(join(home, ".claude", ".pipeline-version"));
+  if (forCopilot) targets.push(join(home, ".copilot", ".pipeline-version"));
+  for (const target of targets) {
+    try {
+      writeFile(target, `${version}\n`);
+    } catch {
+      // advisory only - never fail the install over the marker
+    }
+  }
+}
+
 /**
  * @param {string[]} flags
  * @returns {"ios"|"android"|"all"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "11.5.0",
+  "version": "12.1.0",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code and Copilot CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",
@@ -58,7 +58,7 @@
     "url": "https://github.com/mmerterden/multi-agent-pipeline/issues"
   },
   "engines": {
-    "node": ">=18.0.0"
+    "node": ">=20.0.0"
   },
   "files": [
     "index.js",

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

@@ -1,5 +1,6 @@
 ---
 description: "Task orchestrator  -  full pipeline via Jira ID + branch or GitHub Issue URL: analysis, plan, TDD development, parallel review + Fable triage (CLI-aware: 2-model on Claude Code, 3-model on Copilot CLI), commit, log"
+description-tr: "Görev orkestratörü - Jira ID + branch veya GitHub Issue URL ile tam pipeline: analiz, plan, TDD geliştirme, paralel review + Fable triyajı (CLI'ya göre: Claude Code'da 2, Copilot CLI'da 3 model), commit, log"
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, NotebookEdit, Skill
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Standalone feature-spec analysis. Platform-agnostic concept layer with repo-driven convention extraction (Phase 1c) and per-platform Pass B render. 23 main sections + 3 footer in Full mode; 7 sections in Lite mode (auto for small features). Collects Figma / Swagger / Confluence / Jira / Standards (Confluence + Wiki + local file) / Firebase / repo inputs. Stops after emit - does not chain into /multi-agent:dev."
+description-tr: "Bağımsız özellik-spesifikasyonu analizi. Repo'dan konvansiyon çıkarımıyla (Faz 1c) platform-bağımsız kavram katmanı ve platform başına Pass B render. Full modda 23 ana + 3 dipnot bölümü; Lite modda 7 bölüm (küçük işlerde otomatik). Figma / Swagger / Confluence / Jira / Standartlar (Confluence + Wiki + yerel dosya) / Firebase / repo girdilerini toplar. Çıktıyı üretince durur - /multi-agent:dev'e zincirlenmez."
 argument-hint: "[\"<analysis-name>\"] [--lite | --full] [--no-cache] [--preview-conventions]"
 ---
 

package/pipeline/commands/multi-agent/analysis-resolve/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "Resolve the Section 20 Risks and Open Questions of an analysis v3 document one row at a time. Proposes up to 3 source-labeled answer candidates per row (from evidence / from repo / AI reasoned), merges the chosen answer into the target body section, and updates the doc in place with a Section 23 changelog bump. Companion to /multi-agent:analysis - same Locked decisions apply (citation discipline, humanizer punctuation, no MCP, no auto-commit). Optional sibling propagation for per-platform file sets."
+description-tr: "Analiz v3 dokümanının Bölüm 20 Riskler ve Açık Sorular satırlarını tek tek çözer. Satır başına en fazla 3 kaynak-etiketli cevap adayı önerir (kanıttan / repodan / AI çıkarımı), seçilen cevabı ilgili gövde bölümüne işler ve dokümanı Bölüm 23 changelog artışıyla yerinde günceller. /multi-agent:analysis'in eşlikçisi - aynı Kilitli kararlar geçerli (alıntı disiplini, humanizer noktalama, MCP yok, otomatik commit yok). Platform bazlı dosya setleri için isteğe bağlı kardeş yayılımı."
 argument-hint: "[path/to/analysis/<feature>-<platform>.md] [--autonomous]"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Launch any task in autopilot mode: skips every confirmation, runs end-to-end autonomously."
+description-tr: "Herhangi bir görevi autopilot modunda başlatır: tüm onayları atlar, uçtan uca otonom çalışır."
 argument-hint: '"task"  -  issue URL, Jira ID, free-text, or #id (for resume)'
 ---
 

package/pipeline/commands/multi-agent/build-optimize/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "Thin wrapper that dispatches to xcode-build-orchestrator on iOS projects. Benchmarks current Xcode build, runs compilation / project / SPM analyzers, produces a recommend-first optimization plan, and re-benchmarks after the developer approves changes."
+description-tr: "iOS projelerinde xcode-build-orchestrator'a delege eden ince sarmalayıcı. Mevcut Xcode build'ini ölçer, derleme / proje / SPM analizlerini koşar, önce-öneri yaklaşımlı bir optimizasyon planı üretir ve geliştirici onayından sonra yeniden ölçer."
 argument-hint: "(none - operates on current repo)"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Multi-channel reporter  -  Jira/Confluence/Wiki/PR description/Board status. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbucket PR PUT, GitHub Projects v2 board status move. Phase 7 delegates to this skill; users can invoke post-hoc by Jira ID / PR URL / branch."
+description-tr: "Çok kanallı raporlayıcı - Jira/Confluence/Wiki/PR açıklaması/Board durumu. Çoklu kanal + içerik seçimi, humanizer geçişi, reviewer'ı koruyan Bitbucket PR PUT, GitHub Projects v2 board durum taşıma. Faz 7 bu skill'e delege eder; Jira ID / PR URL / branch ile sonradan da çağrılabilir."
 argument-hint: '<Jira-id | PR-url | #N | Jira-url> [--channels pr,jira,confluence,wiki,board] [--content normal,technical,test,auto-diff,note] [--message "..."] [--message-file path] [--board-status <key>] [--dry-run] [--append] [--ready]'
 allowed-tools: Read, Write, Edit, Bash, Grep, WebFetch, AskUserQuestion
 ---

package/pipeline/commands/multi-agent/create-jira/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "Create a standards-compliant Jira issue (Task / Bug / Story): asks the type, mines project conventions, drafts from a standard template with auto-sizing sections, full preview + explicit approval before create."
+description-tr: "Standartlara uygun Jira issue oluşturur (Task / Bug / Story): türü sorar, proje konvansiyonlarını çıkarır, otomatik boyutlanan bölümlerle standart şablondan taslak hazırlar, oluşturmadan önce tam önizleme + açık onay alır."
 argument-hint: "[\"<free-text description>\"] [figma-url] [swagger-url]  -  all optional, asked interactively when missing"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Fast development mode: Init → Dev (Opus) → Test → Commit → Report. Analysis, planning, and review phases are skipped."
+description-tr: "Hızlı geliştirme modu: Init → Dev (Opus) → Test → Commit → Report. Analiz, planlama ve review fazları atlanır."
 ---
 
 # multi-agent dev  -  Fast Development Mode (--dev)

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

@@ -1,5 +1,6 @@
 ---
 description: "Fastest mode: Dev (Opus) plus Autopilot. Init → Dev → Commit → Report with zero confirmations."
+description-tr: "En hızlı mod: Dev (Opus) + Autopilot. Init → Dev → Commit → Report, sıfır onay."
 ---
 
 # multi-agent dev autopilot  -  Fastest Path

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

@@ -1,5 +1,6 @@
 ---
 description: "Fast mode + local  -  Init → Dev(Opus) → Commit → Report, no worktree."
+description-tr: "Hızlı mod + lokal - Init → Dev(Opus) → Commit → Report, worktree yok."
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, Skill
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Fastest + local  -  Dev(Opus) + autopilot, no worktree, zero interaction."
+description-tr: "En hızlı + lokal - Dev(Opus) + autopilot, worktree yok, sıfır etkileşim."
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, WebFetch, Skill
 ---
 

package/pipeline/commands/multi-agent/diff-explain/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "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 code change'."
+description-tr: "Faz 4 triyaj bulgularını branch diff satırlarına eşler. Review sonrası kullanılan salt-okunur komut: hangi bulgu hangi kod değişikliğine denk geliyor sorusunu cevaplar."
 argument-hint: "[#task-id | --triage <path> | --state <path>] [--branch <name>] [--base <name>]"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Continue already-done LOCAL work through the pipeline tail: Review → Build+Test → Commit/PR → Report (technical analysis + Jira test-scenario comment). No dev phase."
+description-tr: "Halihazırda bitmiş LOKAL işi pipeline kuyruğundan geçirir: Review → Build+Test → Commit/PR → Report (teknik analiz + Jira test-senaryosu yorumu). Dev fazı yok."
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, Skill
 ---
 

package/pipeline/commands/multi-agent/garbage-collect/SKILL.md

@@ -1,5 +1,6 @@
 ---
-description: "Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before deleting."
+description: "Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) and worktree residue (orphan .worktrees dirs, gitlink index entries) from past runs. Dry-run first; confirms before deleting."
+description-tr: "Geçmiş çalışmalardan kalan /tmp scratch'ini (picker durumu, review diff'leri, kanal payload'ları, analiz taslakları) ve worktree kalıntılarını (sahipsiz .worktrees klasörleri, gitlink index kayıtları) süpürür. Önce dry-run; silmeden önce onay alır."
 argument-hint: "[--older-than=<minutes>] [--yes]  -  dry-run unless confirmed"
 ---
 
@@ -48,11 +49,36 @@ deletes nothing until you confirm.
 5. **Report**  -  echo the `══ garbage-collect: removed N item(s), freed ~X ══`
    summary line.
 
+6. **Worktree residue sweep (second phase)**  -  when the current directory is
+   a git repo, also preview worktree leftovers:
+
+   ```bash
+   bash $HOME/.claude/scripts/gc-worktrees.sh ${ARGUMENTS}
+   ```
+
+   This covers: stale worktree admin entries (`git worktree prune`, applied
+   immediately  -  it only drops bookkeeping for dirs that are already gone),
+   orphan `.worktrees/*` dirs no longer registered as worktrees, gitlink
+   residue in the index (`.worktrees/{id}` recorded as a "Subproject commit"
+   entry by a pre-guard `git add -A`), and a missing `.worktrees/` line in
+   `.git/info/exclude`. Registered, healthy worktrees are NEVER touched  -
+   those belong to `/multi-agent:finish` / `/multi-agent:kill`.
+
+   - Output says `nothing to do` -> skip silently, no question.
+   - Otherwise surface a second `AskUserQuestion` (in `outputLanguage`):
+     `question`: "Apply the listed worktree cleanups?" (include the dry-run
+     lines), `header`: "Worktrees", options `{ label: "Apply cleanups" }` /
+     `{ label: "Cancel", description: "Keep everything, change nothing" }`.
+   - On confirm, re-run with `--yes` and echo its summary line. If a gitlink
+     was unstaged, remind the user the removal still needs a commit.
+
 ## Notes
 
 - An in-flight analysis keeps its drafts in `/tmp/analysis-<slug>-<timestamp>/`
   and `/multi-agent:resume` re-uses them. If a run is paused at
   `awaiting_output_decision`, pass `--older-than=<minutes>` so fresh drafts are
   spared, or finish the run first.
-- This only touches `/tmp` scratch. Persistent per-task logs live under
-  `~/.claude/logs/multi-agent/` and are cleaned by `/multi-agent:prune-logs`.
+- The /tmp phase only touches `/tmp` scratch; the worktree phase only touches
+  the current repo's `.worktrees/` residue and index. Persistent per-task logs
+  live under `~/.claude/logs/multi-agent/` and are cleaned by
+  `/multi-agent:prune-logs`.

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

@@ -1,5 +1,6 @@
 ---
 description: "Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatibility)."
+description-tr: "Multi-agent pipeline kullanım kılavuzu - prefs.global.outputLanguage'e göre EN veya TR render edilir (geriye uyumluluk için promptLanguage'e düşer)."
 ---
 
 # multi-agent help
@@ -126,7 +127,7 @@ Setup & Maintenance:
   /multi-agent:stack <id>     Select stack by enabling the matching marketplace plugin(s) (ios / android / mobile / backend / frontend / fullstack / all)
   /multi-agent:sync           Sync ecosystem (Claude Code + Copilot CLI + pipeline + website)
   /multi-agent:update         Pull latest pipeline + reinstall + run migrations
-  /multi-agent:delete         Uninstall pipeline from every CLI (Keychain tokens left intact, double confirm)
+  /multi-agent:uninstall      Uninstall pipeline from every CLI (--all-data also clears settings + logs; Keychain tokens always intact, double confirm)
 
 ------------------------------------------------------------
 
@@ -340,7 +341,7 @@ Setup & Maintenance:
   /multi-agent:stack <id>         Stack'i eşleşen marketplace plugin'i etkinleştirerek seç (ios / android / mobile / backend / frontend / fullstack / all)
   /multi-agent:sync               Ekosistemi senkronize et (Claude Code + Copilot CLI + pipeline + website)
   /multi-agent:update             En son pipeline'ı çek + reinstall + migration çalıştır
-  /multi-agent:delete             Pipeline'ı tüm CLI'lerden kaldır (Keychain token dokunulmaz, çift onay)
+  /multi-agent:uninstall          Pipeline'ı tüm CLI'lerden kaldır (--all-data ayar + logları da siler; Keychain token her zaman dokunulmaz, çift onay)
 
 ------------------------------------------------------------
 

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

@@ -1,5 +1,6 @@
 ---
 description: "List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline."
+description-tr: "Atanmamış GitHub issue'larını listeler, birini seçtirir, otomatik atar ve multi-agent pipeline'ı başlatır."
 argument-hint: "[autopilot]  -  optional: run the pipeline without confirmations"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "List open Jira issues, pick one, and launch the multi-agent pipeline."
+description-tr: "Açık Jira issue'larını listeler, birini seçtirir ve multi-agent pipeline'ı başlatır."
 argument-hint: "[autopilot]  -  optional: run the pipeline without confirmations"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Stop the given task, then remove its worktree and branch. Asks for confirmation."
+description-tr: "Verilen görevi durdurur, ardından worktree'sini ve branch'ini kaldırır. Onay ister."
 argument-hint: "#id  -  task ID to delete (e.g. #2)"
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Toggle outputLanguage (assistant explanations). promptLanguage is fixed to English. External payloads stay English."
+description-tr: "outputLanguage'i değiştirir (asistan açıklamaları). promptLanguage İngilizce sabittir. Dış payload'lar İngilizce kalır."
 argument-hint: "[en|tr]  -  sets outputLanguage; omit for interactive picker; use 'output en|tr' for explicit form"
 ---
 
@@ -16,7 +17,9 @@ Two-axis language preference for the pipeline:
 
 **Why promptLanguage is fixed:** Pipeline picker UI, confirmation prompts, and error messages are authored in English to keep tooling consistent across CLIs. Mixing Turkish prompts into otherwise-English skill output looks inconsistent. Only the assistant's free-form replies follow `outputLanguage`.
 
-**Always English regardless of either field**: commit messages, PR titles/bodies, Jira comments, wiki pages, reviewer/triage system prompts, agent-log.md payloads, skill-picker / confirmation / error UI exposed by the CLI host.
+**Always English regardless of either field**: commit messages, PR titles/bodies, Jira comments, wiki pages, reviewer/triage system prompts, agent-log.md payloads, confirmation / error UI exposed by the CLI host.
+
+**Follows outputLanguage (localized at install/toggle time)**: the slash-command picker `description` shown by the CLI host autocomplete. Repo and npm files always keep the English `description:`; files shipping a `description-tr:` line get swapped in the INSTALLED `~/.claude/commands/multi-agent/` tree by `localize-commands.mjs` (reversible via a `description-en:` sidecar). `/multi-agent:sync` restores English before mirroring back to the repo.
 
 ## Invocations
 
@@ -73,6 +76,22 @@ jq --arg ol "$NEW_OUTPUT" '
 ' "$PREFS" > "$TMP" && mv "$TMP" "$PREFS"
 ```
 
+### Localize picker descriptions
+
+After a successful write, swap the installed command descriptions to match the
+new outputLanguage (repo files are never touched; the swap is reversible):
+
+```bash
+if [ "$NEW_OUTPUT" = "tr" ]; then
+  node "$HOME/.claude/scripts/localize-commands.mjs" apply
+else
+  node "$HOME/.claude/scripts/localize-commands.mjs" restore
+fi
+```
+
+Note: the CLI host caches the picker list per session; descriptions refresh on
+the next session start.
+
 ### Confirmation echo
 
 Render in the **new** outputLanguage:

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

@@ -1,5 +1,6 @@
 ---
 description: "Full pipeline in local mode  -  no worktree, runs directly on the current branch."
+description-tr: "Tam pipeline lokal modda - worktree yok, doğrudan mevcut branch üzerinde çalışır."
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, Skill
 ---
 

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

@@ -1,5 +1,6 @@
 ---
 description: "Full pipeline + local + autopilot  -  no worktree, no confirmations; runs 7 phases (User Test skipped) end-to-end on the current branch."
+description-tr: "Tam pipeline + lokal + autopilot - worktree yok, onay yok; 7 fazı (Kullanıcı Testi atlanır) mevcut branch üzerinde uçtan uca koşar."
 argument-hint: '"task"  -  issue URL, Jira ID, free-text, or #id (for resume)'
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, Skill
 ---

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

@@ -1,5 +1,6 @@
 ---
 description: "Show the agent-log.md for the given task. With no ID, shows the most recent task."
+description-tr: "Verilen görevin agent-log.md dosyasını gösterir. ID verilmezse en son görevi gösterir."
 argument-hint: "[#id]  -  optional: task ID (e.g. #3). If omitted, the most recent task is used."
 ---
 

package/pipeline/commands/multi-agent/manual-test/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 5 standalone (the UI Bug Hunter lives at /multi-agent:test)."
+description-tr: "Aktif görevin branch'ine geçer ve Xcode'da manuel test için hazırlar. Faz 5'in bağımsız hali (UI Bug Hunter /multi-agent:test'te)."
 ---
 
 # multi-agent manual-test  -  Phase 5 Manual Test Mode

package/pipeline/commands/multi-agent/prune-logs/SKILL.md

@@ -1,5 +1,6 @@
 ---
 description: "Delete per-task project logs under ~/.claude/logs/multi-agent (filter by age/project/task). Audit trail + metrics are preserved. Dry-run first; confirms before deleting."
+description-tr: "~/.claude/logs/multi-agent altındaki görev bazlı proje loglarını siler (yaş/proje/görev filtresi). Denetim izi + metrikler korunur. Önce dry-run; silmeden önce onay alır."
 argument-hint: "[--older-than=<days>] [--project=<name>] [--task=<id>] [--yes]"
 ---