@mmerterden/multi-agent-pipeline 12.4.0 → 12.6.0

package/pipeline/skills/.skills-index.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": "1.0.0",
-  "skillCount": 189,
+  "skillCount": 193,
   "entries": [
     {
       "name": "accessibility-compliance-accessibility-audit",
@@ -794,6 +794,15 @@
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-create-jira/SKILL.md"
     },
+    {
+      "name": "multi-agent-design-check",
+      "description": "Mock-mode vs Figma design audit (iOS / Android, local-only). Pick repo + module, gate on mock support, enumerate every state driver into a countable target set, build Debug in a worktree, launch in mock mode, fetch Figma variants, compare each pixel + px-spacing + typography + color, and export a si",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-design-check/SKILL.md"
+    },
     {
       "name": "multi-agent-dev",
       "description": "Fast development mode: Init → Dev (Opus) → Test → Commit → Report. Analysis, planning, and review phases are skipped.",
@@ -848,6 +857,15 @@
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-finish/SKILL.md"
     },
+    {
+      "name": "multi-agent-forget",
+      "description": "Remove a saved /multi-agent routine (created by /multi-agent:save): deletes its local-only command and its registry entry. Asks which one and confirms.",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-forget/SKILL.md"
+    },
     {
       "name": "multi-agent-garbage-collect",
       "description": "Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before deleting.",
@@ -958,7 +976,7 @@
     },
     {
       "name": "multi-agent-refactor",
-      "description": "Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, draft one plan, take approval, develop, then ask whether to sync.",
+      "description": "Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research the companion dev-toolkit MCP server against current MCP practice, draft one plan, take approval, develop, then ask whether to sync.",
       "platform": null,
       "group": "core",
       "triggerKeywords": [],
@@ -1001,6 +1019,24 @@
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-review-jira/SKILL.md"
     },
+    {
+      "name": "multi-agent-routines",
+      "description": "List your saved /multi-agent routines (from /multi-agent:save) with what each one does, rendered in outputLanguage.",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-routines/SKILL.md"
+    },
+    {
+      "name": "multi-agent-save",
+      "description": "Save a recurring job as a reusable /multi-agent:<name> command. Reviews the conversation + your CLAUDE.md for candidate routines, you pick one and name it; stored local-only, never synced.",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-save/SKILL.md"
+    },
     {
       "name": "multi-agent-scan",
       "description": "Skill security scan: walks local skill directories against a tiered pattern catalog.",
@@ -1048,7 +1084,7 @@
     },
     {
       "name": "multi-agent-sync",
-      "description": "One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, and website.",
+      "description": "One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, website, and the dev-toolkit MCP server.",
       "platform": null,
       "group": "core",
       "triggerKeywords": [],

package/pipeline/skills/shared/README.md

@@ -2,11 +2,11 @@
 
 Single source of truth for skills delivered to both Claude Code (`~/.claude/skills/`) and Copilot CLI (`~/.copilot/skills/`) by the installer.
 
-**Total:** 189 skills (41 core + 148 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
+**Total:** 193 skills (45 core + 148 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
 
 ## Directory layout
 
-- **`core/`**  -  41 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
+- **`core/`**  -  45 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
 - **`external/`**  -  148 iOS / Android / generic skills imported from the upstream skill library. Mirrors of third-party guidance.
 - Install destination stays flat: both trees flatten into `~/.claude/skills/` and `~/.copilot/skills/`. See ADR-0006 for the rationale.
 
@@ -14,7 +14,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 
 ## Categories
 
-- [Pipeline Orchestration](#pipeline-orchestration)  -  41
+- [Pipeline Orchestration](#pipeline-orchestration)  -  45
 - [iOS / Apple Ecosystem](#ios-apple-ecosystem)  -  88
 - [Android / Kotlin](#android-kotlin)  -  13
 - [Web / Frontend](#web-frontend)  -  10
@@ -25,7 +25,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 
 | Skill | Group | Description |
 |-------|-------|-------------|
-| [`apple-archive-compliance`](./core/apple-archive-compliance/) | `core` | Apple App Store Review compliance  -  wraps the dev-toolkit-mcp `ios_app_store_audit` tool (17-rule deep scan) with ITMS error code mapping  |
+| [`apple-archive-compliance`](./core/apple-archive-compliance/) | `core` | Apple App Store Review compliance  -  wraps the dev-toolkit-mcp `ios_app_store_audit` tool (18-rule deep scan) with ITMS error code mapping  |
 | [`google-play-compliance`](./core/google-play-compliance/) | `core` | Google Play Store publication compliance  -  bundletool + aapt2 + apksigner orchestration + 21-rule policy catalog with Play Console error c |
 | [`multi-agent`](./core/multi-agent/) | `core` | Task orchestrator: runs the full pipeline from a Jira ID or GitHub Issue URL  -  analysis → plan → TDD development → parallel review (Fable  |
 | [`multi-agent-analysis`](./core/multi-agent-analysis/) | `core` | Standalone feature-spec analysis (v3 template). Platform-agnostic concept layer with repo-driven convention extraction and per-platform Pass |
@@ -34,12 +34,14 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`multi-agent-build-optimize`](./core/multi-agent-build-optimize/) | `core` | Wrapper that dispatches to xcode-build-orchestrator on iOS repos. Benchmarks the current Xcode build, runs compilation / project / SPM analy |
 | [`multi-agent-channels`](./core/multi-agent-channels/) | `core` | Multi-channel reporter  -  Jira/Confluence/Wiki/PR description. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbuck |
 | [`multi-agent-create-jira`](./core/multi-agent-create-jira/) | `core` | Create a standards-compliant Jira issue (Task / Bug / Story): asks the type, mines project conventions, drafts from a standard template with |
+| [`multi-agent-design-check`](./core/multi-agent-design-check/) | `core` | Mock-mode vs Figma design audit (iOS / Android, local-only). Pick repo + module, gate on mock support, enumerate every state driver into a c |
 | [`multi-agent-dev`](./core/multi-agent-dev/) | `core` | Fast development mode: Init → Dev (Opus) → Test → Commit → Report. Analysis, planning, and review phases are skipped. |
 | [`multi-agent-dev-autopilot`](./core/multi-agent-dev-autopilot/) | `core` | Fastest mode: Dev (Opus) plus Autopilot. Init → Dev → Commit → Report with zero confirmations. |
 | [`multi-agent-dev-local`](./core/multi-agent-dev-local/) | `core` | Fast mode + local  -  Init → Dev(Opus) → Commit → Report, no worktree. |
 | [`multi-agent-dev-local-autopilot`](./core/multi-agent-dev-local-autopilot/) | `core` | Fastest + local  -  Dev(Opus) + autopilot, no worktree, zero interaction. |
 | [`multi-agent-diff-explain`](./core/multi-agent-diff-explain/) | `core` | 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 |
 | [`multi-agent-finish`](./core/multi-agent-finish/) | `core` | Continue already-done LOCAL work through the pipeline tail: Review → Build+Test → Commit/PR → Report (technical analysis + Jira test-scenari |
+| [`multi-agent-forget`](./core/multi-agent-forget/) | `core` | Remove a saved /multi-agent routine (created by /multi-agent:save): deletes its local-only command and its registry entry. Asks which one an |
 | [`multi-agent-garbage-collect`](./core/multi-agent-garbage-collect/) | `core` | Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before d |
 | [`multi-agent-help`](./core/multi-agent-help/) | `core` | Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatib |
 | [`multi-agent-issue`](./core/multi-agent-issue/) | `core` | List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline. |
@@ -52,17 +54,19 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`multi-agent-manual-test`](./core/multi-agent-manual-test/) | `core` | 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-te |
 | [`multi-agent-prune-logs`](./core/multi-agent-prune-logs/) | `core` | Delete per-task project logs under ~/.claude/logs/multi-agent (filter by age/project/task). Audit trail + metrics are preserved. Dry-run fir |
 | [`multi-agent-purge`](./core/multi-agent-purge/) | `core` | ⚠️ Wipes every worktree, branch, log, and state file. Irreversible; asks for double confirmation. |
-| [`multi-agent-refactor`](./core/multi-agent-refactor/) | `core` | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, draft one p |
+| [`multi-agent-refactor`](./core/multi-agent-refactor/) | `core` | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research th |
 | [`multi-agent-resume`](./core/multi-agent-resume/) | `core` | Resume a stopped or failed task from the phase where it left off. |
 | [`multi-agent-review`](./core/multi-agent-review/) | `core` | Run parallel review on a branch diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonn |
 | [`multi-agent-review-issue`](./core/multi-agent-review-issue/) | `core` | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |
 | [`multi-agent-review-jira`](./core/multi-agent-review-jira/) | `core` | Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack |
+| [`multi-agent-routines`](./core/multi-agent-routines/) | `core` | List your saved /multi-agent routines (from /multi-agent:save) with what each one does, rendered in outputLanguage. |
+| [`multi-agent-save`](./core/multi-agent-save/) | `core` | Save a recurring job as a reusable /multi-agent:<name> command. Reviews the conversation + your CLAUDE.md for candidate routines, you pick o |
 | [`multi-agent-scan`](./core/multi-agent-scan/) | `core` | Skill security scan: walks local skill directories against a tiered pattern catalog. |
 | [`multi-agent-search`](./core/multi-agent-search/) | `core` | Log search across every agent-log.md with smart ranking and filters. Optional --semantic flag queries the per-repo triage corpus. |
 | [`multi-agent-setup`](./core/multi-agent-setup/) | `core` | First-run setup wizard: keychain token discovery, Git Identity onboarding, and pipeline preparation. |
 | [`multi-agent-stack`](./core/multi-agent-stack/) | `core` | Select the active stack for this repo by enabling the matching marketplace plugin(s) in .claude/settings.json (ios/android/mobile/backend/fr |
 | [`multi-agent-status`](./core/multi-agent-status/) | `core` | Show every multi-agent task's ID, phase, branch, and status. |
-| [`multi-agent-sync`](./core/multi-agent-sync/) | `core` | One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, and website. |
+| [`multi-agent-sync`](./core/multi-agent-sync/) | `core` | One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, website, and the dev-toolkit MCP server. |
 | [`multi-agent-test`](./core/multi-agent-test/) | `core` | UI Bug Hunter  -  iOS Simulator (simctl) + Android Emulator (adb). Auto-detects platform. Screenshot + tap + analyze on the booted device. T |
 | [`multi-agent-uninstall`](./core/multi-agent-uninstall/) | `core` | Uninstall the pipeline from Claude Code + Copilot CLI. Keychain access tokens are always left untouched; --all-data also clears pipeline set |
 | [`multi-agent-update`](./core/multi-agent-update/) | `core` | Update the pipeline to the latest version: git pull, install, migrate. |

package/pipeline/skills/shared/core/apple-archive-compliance/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: apple-archive-compliance
 language: en
-description: "Apple App Store Review compliance  -  wraps the dev-toolkit-mcp `ios_app_store_audit` tool (17-rule deep scan) with ITMS error code mapping + EN/TR humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 4 Security Auditor (catalog cross-ref on Info.plist / PrivacyInfo / entitlements diffs), /multi-agent:review (PR citation), /multi-agent:channels (PR body auto-augmentation). Wiring enforced by smoke-compliance-skills.sh."
+description: "Apple App Store Review compliance  -  wraps the dev-toolkit-mcp `ios_app_store_audit` tool (18-rule deep scan) with ITMS error code mapping + EN/TR humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 4 Security Auditor (catalog cross-ref on Info.plist / PrivacyInfo / entitlements diffs), /multi-agent:review (PR citation), /multi-agent:channels (PR body auto-augmentation). Wiring enforced by smoke-compliance-skills.sh."
 user-invocable: true
 argument-hint: '[archive-path] [--threshold=error|warning|info] [--format=markdown|json] [--lang=en|tr]   -  no-arg: picks most recent .xcarchive from ~/Library/Developer/Xcode/Archives/'
 ---
 
 # apple-archive-compliance  -  Apple App Store Review Compliance Skill
 
-Pre-submission compliance check for iOS `.xcarchive` bundles. Wraps the [`ios_app_store_audit`](https://github.com/mmerterden/dev-toolkit-mcp) MCP tool (17-rule deep audit shipped inside `@mmerterden/dev-toolkit-mcp` v2.4+) and humanizes its JSON output into actionable Turkish / English markdown reports. Catches rejection-causing issues (ITMS error codes, App Store Review Guideline violations) **before** uploading to App Store Connect.
+Pre-submission compliance check for iOS `.xcarchive` bundles. Wraps the [`ios_app_store_audit`](https://github.com/mmerterden/dev-toolkit-mcp) MCP tool (18-rule deep audit shipped inside `@mmerterden/dev-toolkit-mcp` v2.9.0+) and humanizes its JSON output into actionable Turkish / English markdown reports. Catches rejection-causing issues (ITMS error codes, App Store Review Guideline violations) **before** uploading to App Store Connect.
 
 **This skill does NOT reimplement the rule engine**  -  it invokes the MCP tool and maps its output through a knowledge catalog. Rule logic stays in dev-toolkit-mcp's `tools/ios-app-store-audit/`; this skill is the orchestration + humanization layer.
 
@@ -25,12 +25,12 @@ Pre-submission compliance check for iOS `.xcarchive` bundles. Wraps the [`ios_ap
 
 ### Prerequisite detection
 
-The 17-rule scan is provided by the `ios_app_store_audit` tool in `@mmerterden/dev-toolkit-mcp` ≥ v2.4. Two invocation modes:
+The 18-rule scan is provided by the `ios_app_store_audit` tool in `@mmerterden/dev-toolkit-mcp` ≥ v2.9.0. Two invocation modes:
 
 **A. Native MCP tool call** (preferred when running inside an MCP-aware editor):
 
 ```text
-mcp__dev_toolkit__ios_app_store_audit({
+mcp__dev-toolkit__ios_app_store_audit({
   archive_path: "<path>",
   rules: "all"          // "all" | "core" | "deep" | csv of ruleIDs
 })
@@ -88,7 +88,7 @@ fi
 RULES="${RULES:-all}"  # all | core | deep | csv of ruleIDs
 
 # Mode A  -  native MCP call (replaces this whole block when running inside Claude Code / Copilot CLI):
-#   mcp__dev_toolkit__ios_app_store_audit({ archive_path: "$ARCHIVE_PATH", rules: "$RULES" })
+#   mcp__dev-toolkit__ios_app_store_audit({ archive_path: "$ARCHIVE_PATH", rules: "$RULES" })
 # Mode B  -  direct Node invocation (fallback):
 node -e "
 import('@mmerterden/dev-toolkit-mcp/tools/ios-app-store-audit/index.js').then(async m => {
@@ -107,7 +107,7 @@ VIOLATIONS=$(jq -c '.violations[]' /tmp/archiveguard-$$.json)
 
 **Cache filename:** writes `/tmp/archiveguard-$$.json` so `/multi-agent:channels` and the skill's downstream consumers can pick it up via the `find /tmp -name 'archiveguard-*.json'` glob.
 
-## 17-Rule Catalog
+## 18-Rule Catalog
 
 Apple App Store Review Guidelines + ITMS upload error codes that the underlying scanner enforces. Rule IDs match the source-of-truth IDs in `dev-toolkit-mcp/tools/ios-app-store-audit/rules/<ruleID>.js` (stable across versions).
 
@@ -130,6 +130,7 @@ Apple App Store Review Guidelines + ITMS upload error codes that the underlying
 | 15 | `production-hygiene` |  -  | `print()` / `NSLog()` / `debugPrint()` symbol presence + mock/test JSON files shipped in bundle | warning |
 | 16 | `duplicate-resource` |  -  | Same asset under multiple paths (bloats bundle) | info |
 | 17 | `dead-reference` |  -  | Files referenced in Xcode proj but absent from archive | warning |
+| 18 | `sdk-floor` | ITMS-90725 | `DTSDKName` / `DTPlatformVersion` major ≥ 26 and `DTXcode` ≥ 2600 (iOS 26 / Xcode 26 floor, in force since 2026-04-28) | error |
 
 ## Severity mapping for consumers
 
@@ -256,12 +257,12 @@ If `:test "store-ready"` ran recently and its JSON is cached, channels command's
 multi-agent-test "store-ready" --format=json --auto-pick
 
 # Direct MCP tool call (any MCP-aware editor)
-mcp__dev_toolkit__ios_app_store_audit({ archive_path: "~/Library/Developer/Xcode/Archives/2026-04-21/MyApp.xcarchive", rules: "all" })
+mcp__dev-toolkit__ios_app_store_audit({ archive_path: "~/Library/Developer/Xcode/Archives/2026-04-21/MyApp.xcarchive", rules: "all" })
 ```
 
 ### Phase 4 Security Auditor (catalog cross-ref, no binary invocation)
 
-When a Phase 4 review diff touches iOS release-relevant paths (`Info.plist`, `PrivacyInfo.xcprivacy`, `*.entitlements`, `AppDelegate.swift`, `project.pbxproj`), the security-auditor persona loads this skill's 17-rule catalog and cites matching ruleIDs next to its findings. No binary invocation at review time  -  catalog reads are free.
+When a Phase 4 review diff touches iOS release-relevant paths (`Info.plist`, `PrivacyInfo.xcprivacy`, `*.entitlements`, `AppDelegate.swift`, `project.pbxproj`), the security-auditor persona loads this skill's 18-rule catalog and cites matching ruleIDs next to its findings. No binary invocation at review time  -  catalog reads are free.
 
 ```
 # Example finding from Phase 4 Security Auditor (wired in v5.8.1):
@@ -313,3 +314,4 @@ The appended section is structured:
 - **v5.8.1**  -  3 additional consumer surfaces wired (Phase 4 Security Auditor cross-ref, `/multi-agent:review` citation, `/multi-agent:channels` PR-body auto-augmentation). Regression-locked by `smoke-compliance-skills.sh` (45 assertions).
 - **v6.0.0**  -  `language: en` frontmatter tag; 4-consumer Examples section expanded.
 - **v8.4.0**  -  Migrated off the standalone ArchiveGuard Swift binary. Backend is now the `ios_app_store_audit` tool inside `@mmerterden/dev-toolkit-mcp` ≥ v2.4 (full Node port of the 17 rules). All four consumer surfaces unchanged; rule IDs and JSON output shape preserved for backward compatibility. Rule catalog now points to `dev-toolkit-mcp/tools/ios-app-store-audit/rules/`. ArchiveGuard repo deprecated.
+- **Unreleased**  -  Catalog grows to 18 rules: adds `sdk-floor` (ITMS-90725, iOS 26 / Xcode 26 build floor in force since 2026-04-28), which nothing previously checked. `embedded-sdk`'s missing-framework-privacy-manifest finding moves from a `5.1.1` WARNING to `ITMS-91061` ERROR, an enforced rejection since 2025-02-12  -  archives that used to pass with a warning now fail. Requires `@mmerterden/dev-toolkit-mcp` ≥ v2.9.0.

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

@@ -0,0 +1,248 @@
+---
+name: multi-agent-design-check
+language: en
+description: "Mock-mode vs Figma design audit (iOS / Android, local-only). Pick repo + module, gate on mock support, enumerate every state driver into a countable target set, build Debug in a worktree, launch in mock mode, fetch Figma variants, compare each pixel + px-spacing + typography + color, and export a side-by-side annotated report (HTML + PDF + Confluence) to ~/DesignChecks. A coverage gate fails the run when a target is neither audited nor skipped with a reason."
+user-invocable: true
+argument-hint: '[scope]  -  empty = whole module; screen name; screen@variant; Figma URL(s); --resume'
+---
+
+# multi-agent-design-check  -  Mock-mode vs Figma design audit
+
+Local, on-device design-conformance auditor. Runs the app in a **mock mode** on a simulator / emulator and compares each screen (and every mock variant the build exposes) against its Figma design at the **pixel + geometry + typography + color** level, then produces a detailed report.
+
+**Local-only**: no CI/CD, no cron, no commits, no PR. Read-only audit; writes a report to `~/DesignChecks/`. The worktree only isolates the Debug build.
+
+> **Language**: `promptLanguage=en` always (this spec stays English). `outputLanguage` applies to conversational lines and the human-readable report - pass it to `design_report` as `report.lang` (engine defaults to English, ships `en` + `tr` packs, per-key `report.labels` overrides). `ask_choice` labels/headers, branch names, paths, code identifiers stay English.
+
+## Scope  -  `$ARGUMENTS`
+
+The scope decides which **inventory targets** (Phase 0 step 5) the run must audit. It never changes how thoroughly each target is audited.
+
+| Form | Example | Scope |
+|------|---------|-------|
+| empty / `module` | (no argument) | Every target in the module's inventory |
+| screen name | `boarding-pass` | Every target whose `screen` matches (case/separator-insensitive) |
+| `screen@variant` | `boarding-pass@expired` | One target |
+| target id | `scenario-case:boardingpassoutcome-expired` | One target, exactly |
+| Figma URL(s) | `https://figma.com/design/…?node-id=1-2` | Only the frames those URLs name |
+| `--resume` | `--resume` | The unaudited remainder of the most recent run for this repo + module |
+| combinations | `seat-map summary@semi-success` | Union of the above, space- or newline-separated |
+
+A scope matching **no** inventory target is an error, not an empty run: print the closest inventory ids and halt.
+
+**Whole-module is the default, and it is meant to finish.** The inventory prices each target (`cost: relaunch | in-app`) and batches them into a run `plan`, so a 50-target module is typically about a dozen relaunches rather than fifty  -  a full audit is one sitting, not a project. Scope exists for resuming an interrupted run and for re-checking one screen after a fix, **not** for trimming an audit down to what feels affordable. The coverage gate applies to the **scoped** set, so a deliberate scoped run is never penalised for out-of-scope targets, and `--resume` closes the remainder.
+
+## Pipeline
+
+```
+Phase 0: Init & Gate  → repo + module picker, platform detect, MOCK FEASIBILITY GATE, SCENARIO INVENTORY, scope resolve, report dir, worktree
+Phase 1: Build & Launch → Debug build in worktree, boot device, install, launch in mock mode
+Phase 2: Figma          → fetch module frame tree, enumerate + map variants (ask when ambiguous)
+Phase 3: Drive & Compare → per plan batch: one launch → capture + flip in-app states → match → batch-ask → compare
+Phase 4: Report         → coverage gate + assemble + export HTML + PDF (+ Confluence) to ~/DesignChecks/
+```
+
+## Requirements
+
+- **iOS**: Xcode + Simulator. **Android**: Android SDK + emulator / device.
+- **MCP**: `dev-toolkit` (>= 2.8.0, for `design_scenario_inventory`, the `design_report` coverage gate, and `design_visual_compare` region alignment) + an authenticated Figma MCP (`mcp__claude_ai_Figma__*`).
+- The selected module must support a mock mode (Phase 0 gate). No mock support → halt.
+
+## Phase Tracker (mandatory)
+
+```bash
+bash $HOME/.copilot/scripts/phase-tracker.sh init "$TASK_ID"
+for p in "0:Init & Gate" "1:Build & Launch" "2:Figma" "3:Drive & Compare" "4:Report"; do
+  bash $HOME/.copilot/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
+done
+```
+Copilot / plain shell has no TaskList widget - after every state change call `phase-tracker.sh render` (prints a bordered ANSI card). Do NOT call TaskCreate here.
+
+## STOP-AND-CONFIRM
+
+Every Phase 0 / Phase 2 decision uses the `ask_choice` picker (`$HOME/.copilot/lib/ask-choice.sh`). Print a `Step <i>/<n>: <what it decides>` breadcrumb first. Confirmation required even with one option; state inheritance from a previous run is FORBIDDEN.
+
+---
+
+## Phase 0 - Init, Feasibility Gate & Inventory
+
+0. **MCP CURRENCY GATE (first, before anything expensive)** - an MCP stdio server publishes its tool list once at `initialize` and never re-reads the code, so a session bound to a process that started before the last update keeps serving the OLD tool list while still reporting "connected". Finding that out after a Debug build and a device drive wastes the run and yields a report missing the checks this spec depends on.
+
+   Assert both halves:
+
+   a. **Session** - `mcp__dev-toolkit__design_scenario_inventory` must be callable and `mcp__dev-toolkit__design_visual_compare` must accept `live_region`. Absent → the session holds a stale process.
+
+   b. **Disk** - probe the configured server, which reports what a fresh connection WOULD serve:
+   ```bash
+   printf '%s\n%s\n' \
+     '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"probe","version":"1"}}}' \
+     '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
+   | node "<dev-toolkit path>/index.js" 2>/dev/null | python3 -c "
+import sys,json
+for l in sys.stdin:
+    try: m=json.loads(l)
+    except: continue
+    if m.get('id')==1: print('version', m['result']['serverInfo']['version'])
+    if m.get('id')==2:
+        n=[t['name'] for t in m['result']['tools']]
+        print('tools', len(n), 'inventory', 'design_scenario_inventory' in n)"
+   ```
+
+   - **disk OK, session missing the tool** → **HALT**; the user must reconnect the MCP server (a stale build advertises one fewer `design_*` tool, which is the quickest tell). If a reconnect does not take, lingering server processes are the usual cause - compare `ps -o lstart=` start times against the code's mtime.
+   - **disk stale** → **HALT**; the checkout needs updating first.
+   - **both current** → continue.
+
+   Never substitute a local `node` call for a missing tool: the run would silently lose the coverage gate and region alignment, which is the exact failure this gate prevents.
+
+1. **Repo picker** - `$HOME/.copilot/multi-agent-refs/_repo-picker.md`. Account picker skipped (Figma token user-supplied) unless Confluence export needs a token.
+2. **Module picker** - `$HOME/.copilot/multi-agent-refs/_dev-context.md` (auto-suggest `.gitmodules` via `submodule-detector.sh`). Pick the module to audit (multi-module = audit each independently).
+3. **Platform detect** - `.xcodeproj`/`Package.swift`→iOS, `build.gradle*`→Android. Persist `state.platform`.
+4. **MOCK FEASIBILITY GATE** on the module path:
+   ```
+   mcp__dev-toolkit__design_mock_detect({ repo_path, platform, extra_keys })
+   ```
+   (`extra_keys` from `config mock.keys`.)
+   - `false` → **HALT** with `reason`; the module cannot be audited. Never fabricate a comparison.
+   - `"debug-only"` → warn via ask_choice (variants can't be toggled at launch; only default Debug state comparable), Continue / Cancel.
+   - `true` → persist `state.designCheck.mock` (mechanism, activation, variantsHint, evidence).
+5. **SCENARIO INVENTORY (this is the audit's target set)**:
+   ```
+   mcp__dev-toolkit__design_scenario_inventory({ repo_path, platform,
+     extra_launch_args: <config inventory.extraLaunchArgs>,
+     extra_targets:     <config inventory.extraTargets>,
+     ignore_targets:    <config inventory.ignoreTargets> })
+   ```
+   Returns `targets[]` - each `{ id, kind, label, screen, driver, cost, evidence }` - plus `plan[]`, `relaunchCount`, `groups[]`, `byKind`, `byCost`, `ignored[]`, `truncated`, `scanStrategy`. Kinds: `launch-arg`, `scenario-case`, **`prefix-code`** (a mock repository branching on the prefix of the reference the user types - usually the LARGEST group, and the one a selector-only search misses entirely), `code-scenario`, `fixture`, `deep-link`.
+
+   This list, not the agent's reading of the code and not what the UI happens to expose to tapping, is what the run is measured against. Persist verbatim to `state.designCheck.inventory`.
+   - `targetCount: 0` → warn that only the default launch state is auditable (a `debug-only` project legitimately lands here).
+   - `truncated: true` → the target set is INCOMPLETE. Say so now and pass `coverage.truncatedInventory: true` in Phase 4 so the gate fails instead of reporting a clean percentage of a partial denominator; narrow to a screen and work through the module in `--resume` steps.
+   - `ignored[]` non-empty → list what the config dropped, so a stale `ignoreTargets` cannot quietly shrink the audit.
+6. **Scope resolve** - intersect `$ARGUMENTS` with `inventory.targets`; persist `state.designCheck.scope = { argument, targetIds[] }`.
+
+   Print the resolved set grouped by screen **with its relaunch cost**: `<n> targets · <relaunchCount> relaunches`. Read the cost from `plan`, not from the target count - one relaunch serves every in-app target on that screen, so a 50-target module is typically a dozen relaunches. **Whole-module is the intended default**; ask_choice only when `relaunchCount` exceeds `config coverage.confirmAbove` (default 25), phrased as a cost estimate rather than an invitation to shrink the audit. Never offer a smaller scope as the easy path.
+7. **`--resume`** - read the most recent `~/DesignChecks/{repo}__{module}/*/run-state.json`; scope becomes that run's targets minus `covered` minus `skipped`. No previous run → say so and fall back to whole-module scope after confirmation.
+8. **Report dir** - create `~/DesignChecks/{repo}__{module}/{UTC-timestamp}/` (plus `assets/`) now and persist as `state.designCheck.reportDir`. Phase 3 writes captures, comparison images, and `run-state.json` into it, so it must exist before driving starts.
+9. **Worktree** - `{projectRoot}/{worktreeBasePath}/{taskId}` (default `.worktrees/DC-<shortId>`), never under $HOME. Prune stale locks + add `.worktrees/` to `.git/info/exclude` first.
+
+Persist `agent-state.json` (`mode: "design-check"`, platform, projectRoot, worktreePath, module, designCheck).
+
+## Phase 1 - Build & Launch (mock)
+
+1. **Debug build** in the worktree: iOS `mcp__dev-toolkit__ios_xcodebuild({ scheme, configuration: "Debug", action: "build" })`; Android `./gradlew :<module>:assembleDebug`.
+2. **Boot + install**: iOS list/boot device + `xcrun simctl install`; Android running emulator + `adb install -r`.
+3. **Deterministic state**: iOS `ios_status_bar({ preset: "clean" })`; fix appearance + locale.
+4. **Launch mock**: `mcp__dev-toolkit__design_mock_launch({ platform, bundle_id|package_name, launch_arg|intent_extra })` from Phase 0 activation. `debug-only` → just launch the Debug build. The build is installed once; Phase 3 relaunches it per target rather than rebuilding.
+
+## Phase 2 - Figma fetch & variant mapping (module-scoped)
+
+Figma **discovery** happens only here: the frame tree is fetched once and no later phase browses Figma for candidates. Phase 3 may fetch a specific node the user hands over in the 3.3 batch-ask - a targeted fetch of an already-identified frame, and the only Figma call allowed after this phase.
+
+1. Resolve the Figma URL (`$ARGUMENTS` or ask). Parse `fileKey` + `nodeId` (`-`→`:`).
+2. `mcp__claude_ai_Figma__get_metadata` → frame tree; direct child frames = candidate variants.
+3. Map each scoped target's `screen` + `label` (and `variantsHint`) → frames by similarity. Ambiguous/unmatched → deferred to the Phase 3.3 batch-ask (where the live capture can be shown); never guess. `debug-only` → single default variant.
+4. Per variant: `get_screenshot` (design PNG) + `get_design_context` (bbox, itemSpacing, paddings, fontSize/fontFamily, fills, CodeConnect name). Flatten to `figma_spec`; record `figmaFrame` size.
+
+Persist `state.designCheck.variants[]`.
+
+## Phase 3 - Drive every scoped target → capture → match → batch-ask → compare
+
+**This phase iterates `state.designCheck.scope.targetIds`  -  a finite list decided in Phase 0. It ends when every id is resolved, not when the UI stops offering new taps.** Tap-walking alone cannot reach a state needing a different launch argument, scenario case, or typed scenario code - which is exactly how a module's error / edge states go missing.
+
+### 3.1 Drive the inventory's plan, batch by batch
+
+**Follow `inventory.plan`, filtered to the scoped ids.** Each batch is one launch: the batch's relaunch target opens a screen, and every in-app target for that screen is flipped while the app is already there. Driving the plan is what makes full coverage affordable - target-by-target relaunching is what made earlier runs give up a third of the way in.
+
+Per batch: launch once with the batch's `launch` driver (or the plain mock activation for `(default launch)`) → navigate → capture the relaunch target → for each in-app target, flip its selector, let the screen re-render, capture. **No relaunch between in-app targets.**
+
+Per-target activation by `driver.type`:
+
+| `driver.type` | Activation |
+|---|---|
+| `launch-arg` | `design_mock_launch({ launch_arg: "<mock activation> <driver.launchArg>" })` - the mock switch AND the target's flag together |
+| `intent-extra` | `design_mock_launch({ intent_extra: "<mock extra> <driver.intentExtra>" })` |
+| `scenario` | Set `driver.enum` to `driver.case` through the build's debug scenario picker, then drive the flow that consumes it |
+| `code` (from `prefix-code`) | Type a reference beginning with `driver.code` at the entry field, then walk to `driver.appliesTo`. The prefix decides which fixture the mock repository returns - this is how most per-screen variants are reached |
+| `code` (from `code-scenario`) | Same entry field, flow-wide code not owned by one screen |
+| `fixture` | Activate the launch arg / scenario that reads `driver.file`; when nothing does → skip with reason "fixture not reachable from any driver" |
+| `deep-link` | `ios_open_url` / `android_open_url` with `driver.url` |
+| `manual` | Config-declared: follow the config's note, or skip with that note as the reason |
+
+While a target's state is on screen, also capture the **sub-states reachable from it by tapping** - overlays, bottom sheets, modals, popups, inline errors, QR / share sheets. These cost no relaunch and belong to the target that exposed them (`<id>#<sub-label>`).
+
+Per capture: `ios_screenshot`/`android_screenshot` (save PNG into the Phase 0 report dir) + `mcp__dev-toolkit__design_ui_geometry` → append to `state.designCheck.captured[]` with the target id and a human label. **Persist `state` and `run-state.json` after every capture** so a dying run resumes from where it stopped.
+
+Unreachable target → record `{ id, reason }` in `state.designCheck.skipped[]` with a concrete reason ("scenario picker not present in this build", "needs a live PNR", "crashes on launch: <symbol>"). "Requires a scenario / prefix / launch-arg" is **not** a reason - that describes the work, and the work is this phase's job.
+
+### 3.2 Match each capture → Figma frame (auto)
+
+Resolve each captured screen's frame from the Phase 2 tree; match by structure/content; accept only a **confident** match → `pairs[]`.
+
+### 3.3 Batch-ask the user for EVERYTHING unmatched (ONE prompt, WITH the visual)
+
+Collect ALL unmatched captures into a single list and ask ONCE - never guess, never show a wrong frame. **Show each unmatched screen's captured screenshot** (attach the PNG), name the screen, ask for the Figma node-id / URL in `outputLanguage`, optionally list best-guess candidates. Each answer becomes a confirmed pair; a declined screen is a skip with reason "no Figma frame supplied".
+
+### 3.4 Compare ALL pairs in one pass
+
+```
+mcp__dev-toolkit__design_visual_compare({ figma_png, live_png, out_dir, label,
+  figma_spec, live_geometry, figma_frame, live_screen,
+  crop_top_live, tolerance_px: 2, color_tolerance: 3, max_diff_pct: 1.0 })
+```
+Collect findings (spacing/size/position px, color ΔE hex, typography), perceptualPct, images.
+
+**Bottom sheets, modals, and any partial overlay need region alignment.** Their Figma frame covers only the sheet while the capture is the whole screen; passing that pair as-is stretches a full screen onto a sheet-shaped frame, misplacing every element inside the sheet and burying the real defect in noise. For any capture whose frame is not full-screen add:
+
+```
+  live_region:     <the sheet container's {x,y,w,h} from design_ui_geometry>,
+  expected_region: <where the design puts that sheet, same units>
+```
+- `live_region` rebases the comparison onto the sheet's own box - read it from the `design_ui_geometry` element that IS the sheet container, never from a guess.
+- `expected_region` comes from the Figma frame's placement inside its parent screen frame; with it the engine emits an `inset` finding per edge.
+- `crop_top_live` is ignored when `live_region` is given (the region crop already excluded chrome).
+
+**Edge insets are defects, not tolerances.** A design showing a sheet flush to the screen edges is not satisfied by one floating in from them, and the reverse is equally wrong. Report every `inset` finding as a deviation with its px delta; never absorb a side gap as "close enough" and never raise `tolerance_px` to make one disappear. The sheet's internal content padding is measured by the normal element pairing once the region alignment is right.
+
+**Component reference** (best-effort): Code Connect atom → attach matching `*.figma.swift`/`*.figma.kt` component render.
+**Fix prompt**: compose a paste-ready developer prompt from the findings.
+
+### 3.5 Close the ledger
+
+Every scoped target id ends in exactly one bucket: **covered** (captured AND compared) or **skipped** (with a concrete reason from 3.1 / 3.3). Write `run-state.json` into the Phase 0 report dir with `{ targetIds, covered, skipped }` so `--resume` can pick up the remainder.
+
+Before leaving this phase, compare `covered.length + skipped.length` against `scope.targetIds.length`. A mismatch is a set of targets nobody decided about - go back and drive them, or record why they cannot be driven. Reaching Phase 4 with a mismatch is the worst of both worlds: the work is undone AND the run is marked incomplete.
+
+## Phase 4 - Report, coverage gate & export
+
+1. Output dir: `state.designCheck.reportDir`, already created in Phase 0, holding Phase 3's captures and comparison images. Do not mint a second timestamped dir.
+2. Assemble the report object:
+   ```
+   { project, module, platform, figmaUrl, figmaFileKey, timestamp, lang: <outputLanguage>,
+     coverage: { targets: <scoped target ids/objects>, covered: <audited ids>,
+                 skipped: [{ id, group, reason }],
+                 truncatedInventory: <inventory.truncated>,
+                 floor: <config coverage.floor, optional> },
+     variants: [{ name, figmaNodeId, perceptualPct, passed, compareSize, liveSize,
+                  images, findings, fixPrompt, componentRefs }] }
+   ```
+   Pass **ids**, not counts: the engine then names each unaccounted target instead of printing an anonymous tally. `compareSize` / `liveSize` come straight from the `design_visual_compare` result.
+3. Export:
+   ```
+   mcp__dev-toolkit__design_report({ report, out_dir: state.designCheck.reportDir,
+     formats: ["html","pdf"] (+ "confluence" if enabled) })
+   ```
+   HTML self-contained with the gate banner on top; PDF via Playwright (reports `pdfError` if unavailable); Confluence only if enabled (reuse `multi-agent-channels` adapter), else graceful skip.
+4. **COVERAGE GATE (blocking, not advisory)** - read `coverage` from the tool result and persist to `state.designCheck.coverage`:
+   - `gate: "pass"` → print per-variant PASS/FAIL + findings + report paths.
+   - `gate: "fail"` → the run is **INCOMPLETE**. Print `coverageError`, the `unaccountedIds`, and the command that closes the gap (`--resume`). Do not present an incomplete audit as finished, and never pad the covered list to make the gate pass.
+
+   The gate is a last line of defence, not the plan. If it fires, Phase 3 left work undone - drive the missing targets, then report.
+5. Remove the worktree unless asked to keep it. The report dir is never removed.
+
+## Notes
+
+- Feasibility is real - report honestly and stop when a module has no mock support; never fabricate a partial comparison.
+- **The inventory is the contract**: Phase 0 step 5 decides what "done" means. An audit that visits the linear happy path and lists the rest as "not visited" is the failure mode this pipeline exists to prevent; the gate makes it visible instead of polite.
+- **Chunk with scope, not with silence**: a 50-target module is a legitimate multi-run job. Scope it, close each run's gate, let `--resume` carry the remainder.
+- "Pixel perfect" is perceptual + geometric (scale normalized, chrome cropped); deltas reported in px/pt/hex with a tolerance.
+- The `design_*` engine is generic; project specifics (mock keys, extra launch args / targets, node overrides, status-bar crop, coverage floor, Confluence toggle) come from `design-check-config.json` / prefs, never hardcoded.

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

@@ -128,6 +128,17 @@ Manual Test (Phase 5 standalone  -  Xcode hint flow):
   /multi-agent:manual-test [#N]      Checkout task branch, print Xcode/SourceTree hints.
                                      (Renamed from :test in v5.7.4.)
 
+Design Check (mock-mode vs Figma, local-only  -  dev-toolkit-mcp design_* tools):
+
+  /multi-agent:design-check          Whole-module design audit: enumerate every state driver into a target set,
+  /multi-agent:design-check <scope>  drive each one in mock mode via idb, compare vs Figma (padding/width/spacing/
+  /multi-agent:design-check --resume font/color/component/localization), export HTML+PDF to ~/DesignChecks.
+                                     Scope: empty=module / screen / screen@variant / target-id / Figma URL(s).
+                                     COVERAGE GATE: a target is audited or skipped WITH a reason, else the run
+                                     is reported INCOMPLETE. --resume covers the remainder of the last run.
+                                     Unresolved frame → shows you the screenshot and asks for the node-id.
+  Drives dev-toolkit design_* : design_mock_detect / _scenario_inventory / _mock_launch / _ui_geometry / _visual_compare / _report.
+
 ------------------------------------------------------------
 
 Setup:
@@ -266,6 +277,17 @@ Manuel Test (Phase 5 standalone  -  Xcode hint akışı):
   /multi-agent:manual-test [#N]      Task branch'ine checkout, Xcode/SourceTree hint basar.
                                      (v5.7.4'te :test'ten :manual-test'e rename.)
 
+Design Check (mock-mod vs Figma, yalnızca lokal  -  dev-toolkit-mcp design_* tool'ları):
+
+  /multi-agent:design-check          Tüm modül tasarım denetimi: her state sürücüsünü hedef kümesine çıkar,
+  /multi-agent:design-check <scope>  her birini mock modda idb ile sür, Figma ile karşılaştır (padding/genişlik/
+  /multi-agent:design-check --resume spacing/font/renk/component/localization), HTML+PDF rapor ~/DesignChecks.
+                                     Kapsam: boş=modül / ekran / ekran@varyant / target-id / Figma URL(leri).
+                                     KAPSAM GEÇİDİ: hedef ya denetlenir ya da GEREKÇEYLE atlanır; aksi hâlde
+                                     koşu EKSİK raporlanır. --resume son koşunun kalanını kapatır.
+                                     Figma karşılığı bulunamazsa SANA screenshot'ı gösterip node-id sorar.
+  Sürdüğü dev-toolkit design_* : design_mock_detect / _scenario_inventory / _mock_launch / _ui_geometry / _visual_compare / _report.
+
 ------------------------------------------------------------
 
 Setup: