@mmerterden/multi-agent-pipeline 11.3.2 → 11.5.0

package/install/copilot.mjs

@@ -22,7 +22,9 @@ import {
   copyFile,
   countFiles,
   ensureDir,
+  ensureRealDir,
   isDryRun,
+  removePipelineAgentFiles,
   wipeDir,
   writeFile,
 } from "./_common.mjs";
@@ -61,17 +63,55 @@ export function installCopilot(ctx) {
   installSkills({ pipelineSrc, dest: COPILOT_SKILLS, indexOnly, useSymlinks, platformFlag });
 }
 
+/** Start of the pipeline-managed span in copilot-instructions.md. */
+export const INSTRUCTIONS_START_MARKER = "# Multi-Agent Development Pipeline";
+
+/**
+ * Explicit end marker written after the pipeline section (v11.4.1+). Updates
+ * replace only the start..end span, so anything the user appends AFTER the
+ * pipeline section survives. Pre-marker files fall back to
+ * `legacyTrailingContent` bounding.
+ */
+export const INSTRUCTIONS_END_MARKER =
+  "<!-- multi-agent-pipeline:copilot-instructions:end -->";
+
+/**
+ * Legacy files (written before the end marker existed) have no explicit
+ * terminator. Bound the pipeline span at the next top-level "# " heading
+ * after the start marker when one exists OUTSIDE fenced code blocks (the
+ * pipeline body carries bash comments like "# Bootstrap once ..." inside
+ * fences that must not be mistaken for headings); otherwise the span runs
+ * to EOF, which matches the pre-marker behavior.
+ *
+ * @param {string} section - file content from the start marker onward
+ * @returns {string} user content trailing the pipeline span ("" if none)
+ */
+export function legacyTrailingContent(section) {
+  const lines = section.split("\n");
+  let inFence = false;
+  for (let i = 1; i < lines.length; i++) {
+    if (/^\s*(```|~~~)/.test(lines[i])) {
+      inFence = !inFence;
+      continue;
+    }
+    if (!inFence && /^# /.test(lines[i])) return lines.slice(i).join("\n");
+  }
+  return "";
+}
+
 function writeInstructionsFile(path) {
   const pipelineSection = generateCopilotInstructions();
+  const managedBlock =
+    pipelineSection.trimEnd() + "\n\n" + INSTRUCTIONS_END_MARKER + "\n";
 
   if (!existsSync(path)) {
-    writeFile(path, pipelineSection + "\n");
+    writeFile(path, managedBlock);
     console.log("    -> Created copilot-instructions.md with pipeline");
     return;
   }
 
   let existing = readFileSync(path, "utf-8");
-  const marker = "# Multi-Agent Development Pipeline";
+  const marker = INSTRUCTIONS_START_MARKER;
 
   // Drift cleanup (v5.6.2): detect pre-v5.0 pipeline sections that predate
   // the stable marker and strip them. These blocks ("## Multi-Agent Task
@@ -103,12 +143,26 @@ function writeInstructionsFile(path) {
   }
 
   if (existing.includes(marker)) {
-    const before = existing.split(marker)[0].trimEnd();
-    writeFile(path, before + "\n\n" + pipelineSection + "\n");
+    const startIdx = existing.indexOf(marker);
+    const before = existing.slice(0, startIdx).trimEnd();
+    const fromStart = existing.slice(startIdx);
+    // Replace only the start..end span. User content appended AFTER the
+    // pipeline section (below the end marker, or below the next top-level
+    // heading in legacy files) is preserved.
+    const endIdx = fromStart.indexOf(INSTRUCTIONS_END_MARKER);
+    const trailing =
+      endIdx >= 0
+        ? fromStart.slice(endIdx + INSTRUCTIONS_END_MARKER.length)
+        : legacyTrailingContent(fromStart);
+    let out = before.length > 0 ? before + "\n\n" : "";
+    out += managedBlock;
+    const trailingClean = trailing.replace(/^[\r\n]+/, "").trimEnd();
+    if (trailingClean.length > 0) out += "\n" + trailingClean + "\n";
+    writeFile(path, out);
     const suffix = cleaned ? " (also scrubbed pre-v5.0 drift section)" : "";
     console.log(`    -> Updated existing pipeline section in copilot-instructions.md${suffix}`);
   } else {
-    writeFile(path, existing.trimEnd() + "\n\n" + pipelineSection + "\n");
+    writeFile(path, existing.trimEnd() + "\n\n" + managedBlock);
     console.log("    -> Appended pipeline section to copilot-instructions.md");
   }
 }
@@ -117,6 +171,9 @@ function installScripts(pipelineSrc, dest, useSymlinks) {
   console.log("  [Copilot CLI] Installing scripts...");
   const scriptsSrc = join(pipelineSrc, "scripts");
   if (!existsSync(scriptsSrc)) return;
+  // Replace a --link-era symlink with a real dir before wiping/copying so the
+  // install can never land inside the developer's repo checkout.
+  if (!useSymlinks) ensureRealDir(dest);
   wipeDir(dest);
   copyDir(scriptsSrc, dest, { exclude: DEV_ONLY_SCRIPTS, useSymlinks });
   // Count files actually excluded, not the array length: DEV_ONLY_SCRIPTS mixes
@@ -133,7 +190,13 @@ function installAgents(pipelineSrc, dest, useSymlinks) {
   console.log("  [Copilot CLI] Installing agent definitions...");
   const agentsSrc = join(pipelineSrc, "agents");
   if (!existsSync(agentsSrc)) return;
-  wipeDir(dest);
+  // ~/.copilot/agents also holds user-authored agent files. Never wipe the
+  // whole dir; remove only the pipeline-shipped agent files (name set derived
+  // from the source tree so it cannot go stale), then copy the fresh set in.
+  if (!useSymlinks) {
+    ensureRealDir(dest);
+    removePipelineAgentFiles(dest, agentsSrc);
+  }
   copyDir(agentsSrc, dest, { useSymlinks });
   console.log(`    -> ${countFiles(agentsSrc)} files copied to ${dest}`);
 }
@@ -142,6 +205,7 @@ function installSchemas(pipelineSrc, dest, useSymlinks) {
   console.log("  [Copilot CLI] Installing JSON schemas...");
   const schemasSrc = join(pipelineSrc, "schemas");
   if (!existsSync(schemasSrc)) return;
+  if (!useSymlinks) ensureRealDir(dest);
   wipeDir(dest);
   copyDir(schemasSrc, dest, { useSymlinks });
   console.log(`    -> ${countFiles(schemasSrc)} files copied to ${dest}`);
@@ -151,6 +215,7 @@ function installLib(pipelineSrc, dest, useSymlinks) {
   console.log("  [Copilot CLI] Installing shell libraries...");
   const libSrc = join(pipelineSrc, "lib");
   if (!existsSync(libSrc)) return;
+  if (!useSymlinks) ensureRealDir(dest);
   wipeDir(dest);
   copyDir(libSrc, dest, { useSymlinks });
   console.log(`    -> ${countFiles(libSrc)} files copied to ${dest}`);
@@ -160,6 +225,10 @@ function installSkills(opts) {
   const { pipelineSrc, dest, indexOnly, useSymlinks, platformFlag } = opts;
   console.log("  [Copilot CLI] Installing skills...");
 
+  // Same symlink guard as the other owned trees: never prune or copy through
+  // a --link-era symlink into the repo checkout.
+  if (!useSymlinks) ensureRealDir(dest);
+
   if (indexOnly) {
     try {
       mkdirSync(dest, { recursive: true });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "11.3.2",
+  "version": "11.5.0",
   "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",
@@ -18,7 +18,8 @@
     "test:unit": "node --test test/*.test.mjs",
     "test:smoke": "node pipeline/scripts/run-smokes.mjs",
     "lint:skills": "node pipeline/scripts/lint-skills.mjs",
-    "test:coverage": "c8 --reporter=text --reporter=lcov node --test test/*.test.mjs && c8 report",
+    "test:quick": "node --test test/*.test.mjs && node pipeline/scripts/lint-skills.mjs",
+    "test:coverage": "c8 --check-coverage --reporter=text --reporter=lcov node --test test/*.test.mjs && c8 report",
     "lint": "eslint .",
     "lint:fix": "eslint . --fix",
     "format": "prettier --write \"**/*.{js,mjs,json,md,yml}\" --ignore-path .gitignore",
@@ -69,17 +70,10 @@
     "README.md",
     "CHANGELOG.md",
     "LICENSE",
-    "!pipeline/scripts/figma-placeholder-map.json",
-    "!pipeline/scripts/sync-figma-source.sh",
-    "!pipeline/scripts/import-figma-skills.sh",
-    "!pipeline/scripts/smoke-figma-skill-import.sh",
     "!pipeline/scripts/smoke-figma-config-schema.sh",
     "!pipeline/scripts/smoke-personal-data.sh",
     "!pipeline/scripts/smoke-install-leak-gate.sh",
-    "!pipeline/scripts/README-figma-smokes.md",
-    "!pipeline/scripts/.last-figma-sync-plan.json",
-    "!docs/GENERICITY-REVIEW.md",
-    "!docs/STABILITY-FIX-PLAN.md"
+    "!docs/internal/**"
   ],
   "devDependencies": {
     "@eslint/js": "^10.0.1",

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

@@ -73,7 +73,9 @@ Lib scripts (`~/.claude/lib/`):
 | `kill [id]` | Delete worktree (logs preserved). Confirm first |
 | `clear-logs` | Clean global log directory. Keep counter |
 | `purge` | Worktree + logs + counter  -  full reset (double confirm) |
-| `review` | Review current diff only (lightweight, no worktree) |
+| `review [#N\|repo#N\|PR-url\|branch]` | Parallel review of a PR or branch diff; with no input (interactive) lists open GitHub + Bitbucket PRs to multi-select. Posts per-finding inline comments + approve/needs-work on PRs. No worktree. |
+| `review-jira [KEY\|url]` | Grade a Jira issue's readiness for the pipeline (scope / AC / repro / design / API / stack), then post the gaps as a Jira comment. Read-only on code. |
+| `review-issue [#N\|repo#N\|url]` | Grade a GitHub issue's readiness for the pipeline, then post the gaps as an issue comment. Read-only on code. |
 | `analysis ["<feature>"]` | Standalone feature-spec analizi: Figma / Swagger / Confluence / Jira / repo girdileri sabit 7-bölümlük şablona dökülür, humanizer'dan geçer, Local/Confluence/Jira hedef(ler)ine post edilir. Worktree veya commit yok. Dev'e zincirleme yok. |
 | `build-optimize` | iOS-only Xcode build performance wrapper. Vendored `xcode-build-orchestrator`'a dispatch eder; benchmark + compilation / project / SPM analyzer'lar + recommend-first plan `.build-benchmark/optimization-plan.md`. Non-iOS stack'lerde fail-fast. |
 | `channels [PR-url\|#N\|Jira-url\|Jira-id] [--channels pr,jira,confluence,wiki] [--content normal,test,auto-diff,note] [--message "..."]` | Post task report to multi-select channels (PR description, Jira comment, Confluence page, Wiki pages) with multi-select content sources. Humanizer pass per-channel. Bitbucket PR updates use reviewer-preserving PUT. Phase 7 delegates to this command; also invocable post-hoc for fixes made outside the pipeline. No worktree. |
@@ -111,6 +113,8 @@ This command uses lazy loading for token efficiency. Read the relevant sub-file
 | `sync` | `$HOME/.claude/commands/multi-agent/sync/SKILL.md` |
 | `clear-logs` | Handled inline  -  scan + delete agent-log.md/agent-state.json files |
 | `review` | `$HOME/.claude/commands/multi-agent/review/SKILL.md` |
+| `review-jira` | `$HOME/.claude/commands/multi-agent/review-jira/SKILL.md` (loads `$HOME/.claude/multi-agent-refs/readiness-review.md`) |
+| `review-issue` | `$HOME/.claude/commands/multi-agent/review-issue/SKILL.md` (loads `$HOME/.claude/multi-agent-refs/readiness-review.md`) |
 | `analysis` | `$HOME/.claude/commands/multi-agent/analysis/SKILL.md` |
 | `build-optimize` | `$HOME/.claude/commands/multi-agent/build-optimize/SKILL.md` |
 | `local` | `$HOME/.claude/commands/multi-agent/local/SKILL.md` |

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

@@ -20,7 +20,7 @@ Phase 7: Report     → Jira / Wiki + log + knowledge/memory
 
 `--dev local` skips Phase 1 (Analysis), Phase 2 (Planning + Approval Gate), Phase 4 (Review), and Phase 5 (User Test  -  local/autopilot variants skip the interactive test gate). It differs from `--dev` on two axes: no git worktree is created (development happens directly on the current branch in `$PROJECT_ROOT`), and the interactive User Test phase is skipped.
 
-> **Want the quality tail afterwards?** Since this mode skips Review + Test, run [`/multi-agent:finish`](./finish.md) on the same branch when you're done to add parallel review, a build+test success gate, PR, and a Jira technical-analysis + test-scenario comment  -  without re-developing.
+> **Want the quality tail afterwards?** Since this mode skips Review + Test, run [`/multi-agent:finish`](../finish/SKILL.md) on the same branch when you're done to add parallel review, a build+test success gate, PR, and a Jira technical-analysis + test-scenario comment  -  without re-developing.
 
 ## When to use it
 

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

@@ -107,7 +107,9 @@ Status & Resume:
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Post multi-channel report (Jira / Confluence / Wiki / PR description)
-  /multi-agent:review         Parallel review of current diff only (no full pipeline)
+  /multi-agent:review         Parallel review of a PR or branch diff; no URL -> pick open GitHub/Bitbucket PRs
+  /multi-agent:review-jira    Grade a Jira issue's pipeline-readiness -> comment the gaps on it
+  /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps on it
   /multi-agent:analysis ["analysis-name"]  Feature-spec analysis (Figma + Swagger + Confluence + repos) → per-platform v3 doc (23-section Full / 7-section Lite)
   /multi-agent:analysis-resolve [doc]      Resolve Section 20 open questions of an analysis doc, one at a time with source-labeled candidates
   /multi-agent:build-optimize iOS-only Xcode build perf wrapper → benchmark + analyze + recommend-first .build-benchmark/optimization-plan.md
@@ -319,7 +321,9 @@ Status & Resume:
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Multi-channel rapor gönder (Jira / Confluence / Wiki / PR description)
-  /multi-agent:review         Sadece mevcut diff'i paralel review et (full pipeline yok)
+  /multi-agent:review         PR veya branch diff'ini paralel review et; URL yoksa -> açık GitHub/Bitbucket PR'larını seçtir
+  /multi-agent:review-jira    Jira maddesinin pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
+  /multi-agent:review-issue   GitHub issue'nun pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
   /multi-agent:analysis ["analysis-name"]  Feature-spec analizi (Figma + Swagger + Confluence + repolar) → platform başına v3 doküman (23 bölüm Full / 7 bölüm Lite)
   /multi-agent:analysis-resolve [doc]      Analiz dokümanının Bölüm 20 açık sorularını kaynak etiketli adaylarla teker teker çözer
   /multi-agent:build-optimize iOS-only Xcode build performance wrapper → benchmark + analiz + recommend-first .build-benchmark/optimization-plan.md

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

@@ -1,6 +1,6 @@
 ---
 description: "Run parallel review on a branch's diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state."
-argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted, the current branch is used."
+argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted (interactive), open GitHub + Bitbucket PRs are listed for multi-select; autopilot falls back to the current branch."
 ---
 
 # multi-agent review  -  Review Only Mode
@@ -11,7 +11,8 @@ Skip Phase 0-3 and review a diff only. Five input shapes, two providers:
 
 | Input | Resolution | PR action? |
 |---|---|---|
-| (empty) | Current branch (`HEAD` vs `origin/develop`) | No (chat only) |
+| (empty), interactive | **PR picker** - list open GitHub + Bitbucket PRs, multi-select which to review | Yes (per selected PR) |
+| (empty), autopilot / no PRs found | Current branch (`HEAD` vs `origin/develop`) | No (chat only) |
 | `feature/foo` | Named local branch | No (chat only) |
 | `#1250` | PR number on the current repo | Yes |
 | `repo#1250` | PR on a specific repo (GitHub `org/repo`) | Yes |
@@ -40,7 +41,8 @@ trap 'rm -f /tmp/multi-agent-review-${TASK_ID}-*' EXIT
 # Pseudocode  -  orchestrator implements this:
 input="$ARGUMENTS"
 case "$input" in
-  "")                              kind=branch; provider=local; ref=$(git rev-parse --abbrev-ref HEAD) ;;
+  "")                              kind=pick   # interactive: go to Step 1a PR picker; autopilot/no-PRs falls back to branch (see 1a)
+                                   ;;
   https://github.com/*/pull/*)     kind=pr; provider=github; org_repo=<extracted>; pr_number=<extracted> ;;
   https://bitbucket.*/projects/*/repos/*/pull-requests/*)
                                    kind=pr; provider=bitbucket-server
@@ -60,6 +62,35 @@ Save to `agent-state.review.input = { kind, provider, ref?, orgRepo?, bbServerHo
 
 When `provider=github` and the diff is fetched in Step 2, also persist `agent-state.review.headCommitSha`  -  GitHub inline-comment posts (`POST /repos/{o}/{r}/pulls/{n}/comments`) require `commit_id`. Bitbucket Server's anchor API does not.
 
+### 1a. No-input PR picker  -  interactive only
+
+Reached when `kind=pick` (empty input). Skipped entirely in autopilot: autopilot with no ref goes straight to branch mode (`kind=branch; provider=local; ref=$(git rev-parse --abbrev-ref HEAD)`) so nothing prompts.
+
+**List open PRs across both providers** (a provider contributes nothing if its token/CLI is absent - never hard-fail on one provider):
+
+```bash
+# GitHub: current repo's open PRs + the user's own/requested open PRs across repos.
+gh pr list --state open --json number,title,url,headRefName,author,updatedAt 2>/dev/null   # current repo
+gh search prs --state open --review-requested=@me --json number,title,url,repository,updatedAt 2>/dev/null
+gh search prs --state open --author=@me           --json number,title,url,repository,updatedAt 2>/dev/null
+
+# Bitbucket Server: for each configured bitbucket repo (prefs recentRepos / dev-context),
+# resolve creds via credential-store (see Step 2 bitbucket block) then:
+#   GET https://$host/rest/api/1.0/projects/$KEY/repos/$slug/pull-requests?state=OPEN&role=REVIEWER
+```
+
+Merge into one deduped list, each row labeled with its provider and PR URL; sort by `updatedAt` desc. If the merged list is EMPTY -> tell the user "no open PRs found", fall back to branch mode, and continue.
+
+**Select** - follow `$HOME/.claude/multi-agent-refs/picker-contract.md` (breadcrumb narrator line before the prompt), then `AskUserQuestion` `multiSelect: true`:
+
+```
+question (outputLanguage): "Hangi PR('lar)ı review edeyim?"
+header   (English):        "Review PRs"
+options: one per open PR -> label "#<N> <short title>", description (outputLanguage): "<repo> · <provider> · <headRef>"
+```
+
+Each selected option maps back to a full `agent-state.review.input` descriptor (provider + orgRepo / bb coordinates + prNumber + raw URL), exactly as Step 1 would have parsed an explicit URL. Then **loop Steps 2-7 once per selected PR** (independent review + post each). If the user selects none, fall back to branch mode.
+
 ### 2. Fetch the diff  -  kind-aware
 
 **branch mode:**
@@ -252,7 +283,8 @@ Standalone `/multi-agent:review` runs use phase id 4 (matches Phase 4 Review in
 
 | Input | Mode | PR action |
 |---|---|---|
-| no args | branch (current) | none  -  chat only |
+| no args (interactive) | PR picker (open GitHub + Bitbucket PRs, multi-select) | inline comments + approve/needs-work, per selected PR |
+| no args (autopilot / no PRs) | branch (current) | none  -  chat only |
 | `feature/foo` | branch (named) | none  -  chat only |
 | `#N`, `repo#N`, GitHub PR URL | pr (github) | inline comments + approve/needs-work |
 | Bitbucket Server PR URL | pr (bitbucket-server) | inline comments + approve/needs-work |

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

@@ -0,0 +1,22 @@
+---
+description: "Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as an issue comment. Read-only on code."
+argument-hint: "[#N | repo#N | GitHub issue URL]  -  optional; with no argument, pick from open issues"
+---
+
+# multi-agent review-issue  -  GitHub issue readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing GitHub issue for pipeline-readiness and comments the gaps back onto it so the reporter can fix them before a real `/multi-agent` run. No worktree, no branch, no code commits, no pipeline chaining.
+
+## Flow
+
+Read `$HOME/.claude/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = github**:
+
+1. Resolve the item: `#N`, `repo#N` (`org/repo#N`), or a GitHub issue URL. With no argument, offer the picker reusing the `issue` command's list (`gh issue list`) and single-select one.
+2. Fetch + base maturity via `$HOME/.claude/lib/issue-fetcher.sh` (`gh issue view`; reuse its `maturity` output; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps), reusing the maturity blocker-vs-warning severity contract.
+5. Confirm, then post the gap list as an issue comment via `$HOME/.claude/multi-agent-refs/channels/issue-comment.md` (`gh issue comment "$N" --repo "$org/$repo" --body-file <file>`). Autopilot auto-posts.
+
+Non-negotiables: verdict content + comment body follow `prefs.global.outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes/Fixes`) per `channels/issue-comment.md`. No label change, no assignment, no issue creation, no auto-close.

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

@@ -0,0 +1,22 @@
+---
+description: "Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as a Jira comment. Read-only on code."
+argument-hint: "[JIRA-KEY | Jira URL]  -  optional; with no argument, pick from your open Jira issues"
+---
+
+# multi-agent review-jira  -  Jira readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing Jira issue for pipeline-readiness and comments the gaps back onto it so the reporter can fix them before a real `/multi-agent` run. No worktree, no branch, no code commits, no pipeline chaining. This is the inverse of `/multi-agent:create-jira`.
+
+## Flow
+
+Read `$HOME/.claude/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = jira**:
+
+1. Resolve the item: `KEY-123` or a `.../browse/KEY-123` URL. With no argument, offer the picker reusing the `jira` command's issue list (assignee=currentUser, open) and single-select one.
+2. Fetch + base maturity via `$HOME/.claude/lib/issue-fetcher.sh` (reuse its `maturity` output; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps), reusing the maturity blocker-vs-warning severity contract.
+5. Confirm, then post the gap list as a Jira comment via `$HOME/.claude/multi-agent-refs/channels/jira.md` (`POST /rest/api/2/issue/{id}/comment`, Bearer token via `credential-store.sh`, UTF-8 verbatim, markdown->wiki). Autopilot auto-posts.
+
+Non-negotiables: verdict content + comment body follow `prefs.global.outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes`) per `channels/issue-comment.md`. No status change, no assignment, no issue creation.

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

@@ -55,7 +55,7 @@ Run every step automatically:
 ```
 Step 1: PLATFORM    Detect macOS / Linux / Windows (Git Bash / WSL); export PLATFORM env
 Step 1.5: DETECT    Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 36 sub-command skills)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 38 sub-command skills)
 Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub, bash -n on all sh)
 Step 3c: PLUGINS    pipeline shared/external -> multi-agent-plugins marketplace (rebuild knowledge/,
                      bump changed plugins' patch version, commit + push the plugins repo)
@@ -126,7 +126,7 @@ If nothing is stale → report "All targets up to date" and stop.
      grep -rl "^local-only: true" ~/multi-agent-pipeline/pipeline/commands/ 2>/dev/null \
        && { echo "ABORT: local-only wrapper leaked into pipeline/commands"; exit 1; } || true
      # backstop: no corporate marketplace/skill reference in the synced tree
-     grep -rniE "ai-ios-engineering-toolkit:(create-ui-component|evolve-ui-component|component-wiki|figma-setup|resource-utility)" \
+     grep -rniE "ai-ios-engineering-toolkit:(create-ui-component|evolve-ui-component|fix-bug|branch-and-pr|backlog|code-connect|figma-utility|resource-utility|component-wiki|component-docs|figma-setup)" \
        ~/multi-agent-pipeline/pipeline/commands/ 2>/dev/null \
        && { echo "ABORT: corporate reference leaked into pipeline/commands"; exit 1; } || true
      ```
@@ -239,13 +239,13 @@ This runs on the Claude <-> Copilot axis — the two CLIs the pipeline supports
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}/SKILL.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**36 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**38 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, create-jira, delete, dev,
 dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
 help, issue, jira, kill, language, local,
-local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review,
+local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review, review-issue, review-jira,
 scan, search, setup, stack, status, sync, test, update
 ```
 

package/pipeline/lib/account-resolver.sh

@@ -63,10 +63,23 @@ except Exception:
 
 # 1. Pull every credential entry that looks like one of our token services.
 #    Includes token entries AND username entries (BB needs the user keychain key).
-#    Uses cross-platform credential-store wrapper (macOS/Windows/Linux backends).
-services=$("$HOME/.claude/lib/credential-store.sh" list 2>/dev/null \
-  | grep -E '_(Github|Jira|Bitbucket|Confluence)_[A-Za-z]+_(Token|Json|Username)$|_Github_Auth_Token$|_Github_Access_Token$|_Jira_Access_Token$|_Bitbucket_Access_Token$|_Bitbucket_Username$|_Confluence_Access_Token$' \
-  || true)
+#    Uses cross-platform credential-store wrapper (macOS/Windows/Linux backends),
+#    located via the shared resolver (repo checkout or either install tree)  -
+#    never a hardcoded path. A missing helper degrades to an empty inventory.
+# A pre-set CRED_STORE (tests, custom installs) is honored as-is.
+if [ -z "${CRED_STORE:-}" ]; then
+  # shellcheck disable=SC1090,SC1091
+  . "$(cd "$(dirname "$0")" && pwd)/credential-store-resolver.sh" 2>/dev/null \
+    || . "$HOME/.claude/lib/credential-store-resolver.sh" 2>/dev/null \
+    || . "$HOME/.copilot/lib/credential-store-resolver.sh" 2>/dev/null \
+    || true
+fi
+services=""
+if [ -n "${CRED_STORE:-}" ]; then
+  services=$("$CRED_STORE" list 2>/dev/null \
+    | grep -E '_(Github|Jira|Bitbucket|Confluence)_[A-Za-z]+_(Token|Json|Username)$|_Github_Auth_Token$|_Github_Access_Token$|_Jira_Access_Token$|_Bitbucket_Access_Token$|_Bitbucket_Username$|_Confluence_Access_Token$' \
+    || true)
+fi
 
 # 2. Compute unique prefixes (everything before the provider segment).
 prefixes=$(printf '%s\n' "$services" \
@@ -114,14 +127,6 @@ emit_accounts() {
       [ $match -eq 0 ] && continue
     fi
 
-    # Provider list
-    local prov_json=""
-    [ -n "$gh_token" ]   && prov_json="${prov_json}\"github\","
-    [ -n "$jira_token" ] && prov_json="${prov_json}\"jira\","
-    [ -n "$bb_token" ]   && prov_json="${prov_json}\"bitbucket\","
-    [ -n "$conf_token" ] && prov_json="${prov_json}\"confluence\","
-    prov_json="${prov_json%,}"
-
     # Work-account heuristic: bitbucket+jira together indicates corporate.
     local is_work="false"
     if [ -n "$bb_token" ] && [ -n "$jira_token" ]; then
@@ -134,18 +139,18 @@ emit_accounts() {
 
     # Hosts: per-account override (prefs.global.accounts[].jiraHost) wins; falls
     # back to global.hosts.{jira,bitbucket}; otherwise null. No hardcoded values.
-    local jira_host="null" bb_host="null"
+    local jira_host="" bb_host=""
     local per_jira per_bb
     per_jira=$(account_host_override "$short_id" "jiraHost")
     per_bb=$(account_host_override "$short_id" "bitbucketHost")
     if [ -n "$jira_token" ]; then
-      if   [ -n "$per_jira" ];        then jira_host="\"$per_jira\""
-      elif [ -n "$prefs_jira_host" ]; then jira_host="\"$prefs_jira_host\""
+      if   [ -n "$per_jira" ];        then jira_host="$per_jira"
+      elif [ -n "$prefs_jira_host" ]; then jira_host="$prefs_jira_host"
       fi
     fi
     if [ -n "$bb_token" ]; then
-      if   [ -n "$per_bb" ];        then bb_host="\"$per_bb\""
-      elif [ -n "$prefs_bb_host" ]; then bb_host="\"$prefs_bb_host\""
+      if   [ -n "$per_bb" ];        then bb_host="$per_bb"
+      elif [ -n "$prefs_bb_host" ]; then bb_host="$prefs_bb_host"
       fi
     fi
 
@@ -185,12 +190,45 @@ emit_accounts() {
     [ $first -eq 0 ] && printf ','
     first=0
 
-    printf '{"id":"%s","label":"%s","prefix":"%s","providers":[%s],"tokens":{"github":"%s","jira":"%s","bitbucket":"%s","confluence":"%s"},"userKeys":{"bitbucket":"%s"},"users":{"github":"%s"},"jiraHost":%s,"bitbucketHost":%s,"isWork":%s}' \
-      "$short_id" "$label" "$prefix" "$prov_json" \
-      "$gh_token" "$jira_token" "$bb_token" "$conf_token" \
-      "$bb_user_key" \
-      "$gh_user" \
-      "$jira_host" "$bb_host" "$is_work"
+    # Build the entry with python3 from env vars  -  printf-interpolated JSON
+    # has zero escaping, so a quote or backslash in a keychain service name
+    # would corrupt the whole array. Values cross into python via the
+    # environment, never via string interpolation.
+    ACC_ID="$short_id" ACC_LABEL="$label" ACC_PREFIX="$prefix" \
+    ACC_GH_TOKEN="$gh_token" ACC_JIRA_TOKEN="$jira_token" \
+    ACC_BB_TOKEN="$bb_token" ACC_CONF_TOKEN="$conf_token" \
+    ACC_BB_USER_KEY="$bb_user_key" ACC_GH_USER="$gh_user" \
+    ACC_JIRA_HOST="$jira_host" ACC_BB_HOST="$bb_host" ACC_IS_WORK="$is_work" \
+    python3 - <<'PY'
+import json, os
+
+def env(name):
+    return os.environ.get(name, "")
+
+providers = []
+if env("ACC_GH_TOKEN"):   providers.append("github")
+if env("ACC_JIRA_TOKEN"): providers.append("jira")
+if env("ACC_BB_TOKEN"):   providers.append("bitbucket")
+if env("ACC_CONF_TOKEN"): providers.append("confluence")
+
+print(json.dumps({
+    "id":        env("ACC_ID"),
+    "label":     env("ACC_LABEL"),
+    "prefix":    env("ACC_PREFIX"),
+    "providers": providers,
+    "tokens": {
+        "github":     env("ACC_GH_TOKEN"),
+        "jira":       env("ACC_JIRA_TOKEN"),
+        "bitbucket":  env("ACC_BB_TOKEN"),
+        "confluence": env("ACC_CONF_TOKEN"),
+    },
+    "userKeys": {"bitbucket": env("ACC_BB_USER_KEY")},
+    "users":    {"github": env("ACC_GH_USER")},
+    "jiraHost":      env("ACC_JIRA_HOST") or None,
+    "bitbucketHost": env("ACC_BB_HOST") or None,
+    "isWork":        env("ACC_IS_WORK") == "true",
+}, ensure_ascii=False), end="")
+PY
   done <<< "$prefixes"
   printf ']'
 }

package/pipeline/lib/channels-multi-repo.sh

@@ -26,6 +26,11 @@ STATE="${2:-}"
 }
 [ ! -f "$STATE" ] && { echo "ERR: state file not found: $STATE" >&2; exit 2; }
 
+# count_matches: single-line numeric grep -c (the bare `grep -c || echo 0`
+# idiom emits "0" twice on zero matches and breaks the -le comparisons below).
+# shellcheck source=count-lib.sh disable=SC1091
+. "$(cd "$(dirname "$0")" && pwd)/count-lib.sh"
+
 # --- Helpers ----------------------------------------------------------------
 # Extract the targets array from agent-state.json. Output: TSV with columns
 # repoName, prUrl, isPrimary (1/0). One target per row.
@@ -156,7 +161,7 @@ do_render_jira() {
   local urls
   urls=$(all_pr_urls | tr ' ' '\n' | grep -v '^$' || true)
   local count
-  count=$(printf '%s\n' "$urls" | grep -c . || echo 0)
+  count=$(printf '%s\n' "$urls" | count_matches .)
 
   if [ "$count" -le 1 ]; then
     cat "$body_file"
@@ -179,7 +184,7 @@ do_render_conf() {
   local urls
   urls=$(all_pr_urls | tr ' ' '\n' | grep -v '^$' || true)
   local count
-  count=$(printf '%s\n' "$urls" | grep -c . || echo 0)
+  count=$(printf '%s\n' "$urls" | count_matches .)
 
   if [ "$count" -le 1 ]; then
     cat "$body_file"

package/pipeline/lib/count-lib.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# count-lib.sh  -  shared counting helper for pipeline shell scripts.
+#
+# Why: `grep -c` prints "0" AND exits 1 when nothing matches, so the common
+# idiom `$(grep -c pattern file || echo 0)` emits TWO lines ("0" plus the
+# fallback "0"). That breaks arithmetic (`$((x + 0\n0))` is a syntax error)
+# and numeric comparisons (`[ "0\n0" -le 1 ]` silently evaluates false).
+#
+# count_matches guarantees single-line numeric output in every case:
+#   - match count when grep succeeds
+#   - "0" when nothing matches or grep itself errors (missing file, ...)
+#
+# Usage (same arguments as grep -c, file or stdin):
+#   n=$(count_matches -E 'pattern' "$file")
+#   n=$(printf '%s\n' "$blob" | count_matches .)
+#
+# Source from a sibling script:
+#   . "$(cd "$(dirname "$0")" && pwd)/count-lib.sh"
+
+count_matches() {
+  local n
+  n=$(grep -c "$@" 2>/dev/null) || true
+  case "$n" in
+    '' | *[!0-9]*) n=0 ;;
+  esac
+  printf '%s\n' "$n"
+}

package/pipeline/lib/credential-store.sh

@@ -8,6 +8,9 @@
 # Subcommands:
 #   get <key>            Read secret value to stdout (empty + exit 1 if missing)
 #   set <key> <value>    Store secret (overwrites if exists)
+#   set <key> -          Same, but read the secret from stdin. Preferred:
+#                        keeps the secret off this script's argv (visible to
+#                        ps). A literal "-" value cannot be stored this way.
 #   delete <key>         Remove secret
 #   list                 List all keys (one per line)
 #   platform             Print detected platform: macos | windows | linux | unknown
@@ -124,7 +127,11 @@ if (\$c) { \$c.GetNetworkCredential().Password }
 
 do_set() {
   local key="${1:-}" val="${2:-}"
-  [ -z "$key" ] && { echo "usage: $0 set <key> <value>" >&2; exit 3; }
+  [ -z "$key" ] && { echo "usage: $0 set <key> <value|->" >&2; exit 3; }
+  # "-" means: read the secret from stdin (keeps it off argv).
+  if [ "$val" = "-" ]; then
+    val=$(cat)
+  fi
   if delegate_to_python; then
     # Pass the value via stdin to keep it out of process listings / shell history.
     printf '%s' "$val" | python3 "$KEYCHAIN_PY" set "$key" -
@@ -132,7 +139,15 @@ do_set() {
   fi
   case "$PLATFORM" in
     macos)
-      security add-generic-password -s "$key" -a "${USER:-claude}" -w "$val" -U >/dev/null 2>&1
+      # `security -i` reads the add command from stdin, so the secret never
+      # lands on the `security` argv (visible to ps). printf is a bash
+      # builtin, so no argv exposure there either. Double quotes/backslashes
+      # are escaped for security's interactive tokenizer.
+      local key_sec val_sec
+      key_sec=${key//\\/\\\\}; key_sec=${key_sec//\"/\\\"}
+      val_sec=${val//\\/\\\\}; val_sec=${val_sec//\"/\\\"}
+      printf 'add-generic-password -U -s "%s" -a "%s" -w "%s"\n' \
+        "$key_sec" "${USER:-claude}" "$val_sec" | security -i >/dev/null 2>&1
       ;;
     linux)
       require_cmd secret-tool "Install libsecret-tools (see doctor)."
@@ -140,11 +155,13 @@ do_set() {
       ;;
     windows)
       # Escape single quotes for PowerShell single-quoted strings ('' = literal ').
-      local key_esc="${key//\'/\'\'}" val_esc="${val//\'/\'\'}"
-      # CredentialManager module: New-StoredCredential
-      ps_run "
+      local key_esc="${key//\'/\'\'}"
+      # The secret is piped via stdin ([Console]::In) so it never appears on
+      # the PowerShell argv (visible to process listings).
+      printf '%s' "$val" | ps_run "
 \$ErrorActionPreference='Stop'
-\$pwd = ConvertTo-SecureString '$val_esc' -AsPlainText -Force
+\$raw = [Console]::In.ReadToEnd()
+\$pwd = ConvertTo-SecureString \$raw -AsPlainText -Force
 New-StoredCredential -Target '$key_esc' -UserName '${USER:-${USERNAME:-claude}}' -SecurePassword \$pwd -Persist LocalMachine | Out-Null
 " >/dev/null
       ;;