@mmerterden/multi-agent-pipeline 20.36.0 → 20.37.1

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

@@ -7,14 +7,11 @@ metadata:
   language: en
 ---
 
+# multi-agent-design-check - Mock-mode vs Figma design audit
 
-# multi-agent-design-check  -  Mock-mode vs Figma design audit
+Runs the app in **mock mode** on a simulator / emulator and compares each screen and mock variant against Figma at the **pixel + geometry + typography + color** level. **Local-only**: no CI, no commits, no PR; the report goes to `~/DesignChecks/`, the worktree only isolates the Debug build.
 
-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` `header` chips, branch names, paths, code identifiers stay English; option `label`s follow `outputLanguage` like the rest of the picker copy.
+> **Language**: this spec stays English. `outputLanguage` covers conversational lines and the report (`design_report` `report.lang`); `ask_choice` `header` chips, paths, identifiers and logs stay English. Contract: `$HOME/.claude/multi-agent-refs/rules.md` "Language Application".
 
 ## Gotchas
 
@@ -22,135 +19,43 @@ Local, on-device design-conformance auditor. Runs the app in a **mock mode** on
 - The coverage gate fails the run when a target was neither audited nor skipped with a reason. "Not reached" is not "passed".
 - A Figma variant with no matching mock state is a finding about the mock, not a pass for the screen.
 
-## 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 | `order-status` | Every target whose `screen` matches (case/separator-insensitive) |
-| `screen@variant` | `order-status@expired` | One target |
-| target id | `scenario-case:orderstatusoutcome-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**: `multi-agent-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 module must be auditable: a **mock mode** (preferred - it can toggle variants) or a **snapshot capture** of the screen's view model. Neither → halt.
-
-**What each capture is compared against** - the per-component catalog, the measure-never-the-token rule, and the two-consecutive-clean convergence rule that decides when a component is done - is `$HOME/.claude/multi-agent-refs/features/design-conformance.md`. Read it before the first compare. A check that was not run is a fail-to-verify, and every skipped `[DYNAMIC]` / `[CAPTURE+]` item is listed in the report rather than omitted.
-
-## 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)** - a session bound to a process started before the last update keeps serving the OLD tool list while still reporting "connected". Assert both halves before the Debug build: (a) **session** - `design_scenario_inventory` is callable and `design_visual_compare` accepts `live_region`; (b) **disk** - probe what a fresh connection would serve. Disk OK but session stale → **HALT**; the user must reconnect the MCP server. 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. Full procedure: `$HOME/.claude/multi-agent-refs/design-check/mcp-currency-gate.md`. Read it for Phase 0 step 0.
-1. **Repo picker** - `$HOME/.claude/multi-agent-refs/_repo-picker.md`. Account picker skipped (Figma token user-supplied) unless Confluence export needs a token.
-2. **Module picker** - `$HOME/.claude/multi-agent-refs/_dev-context.md`. Multi-module = audit each independently.
-3. **Platform detect** - `.xcodeproj`/`Package.swift`→iOS, `build.gradle*`→Android. Persist `state.platform`.
-4. **MOCK FEASIBILITY GATE** - `mcp__multi-agent-toolkit__design_mock_detect` on the module path:
-   - `false` → try the **snapshot lane** before halting: a screen renderable from its own view model is auditable without a runtime mock switch. Ask via `ask_choice`, persist `state.designCheck.captureLane = "snapshot"`, and state the trade (no in-app variant flips). Declined or not renderable → **HALT** with `reason`. Never fabricate a comparison.
-   - `"debug-only"` → warn via ask_choice (variants can't be toggled at launch; only default Debug state comparable), Continue / Cancel.
-   - `true` → persist `state.designCheck.mock` (mechanism, activation, variantsHint, evidence).
-5. **SCENARIO INVENTORY (this is the audit's target set)** - `mcp__multi-agent-toolkit__design_scenario_inventory` with the config's inventory overrides. This list, not the agent's reading of the code and not what the UI happens to expose to tapping, is what the run is measured against. Persist verbatim to `state.designCheck.inventory`.
-   - `targetCount: 0` → warn that only the default launch state is auditable (a `debug-only` project legitimately lands here).
-   - `truncated: true` → the target set is INCOMPLETE. Say so now and pass `coverage.truncatedInventory: true` in Phase 4 so the gate fails instead of reporting a clean percentage of a partial denominator; narrow to a screen and work through the module in `--resume` steps.
-   - `ignored[]` non-empty → list what the config dropped, so a stale `ignoreTargets` cannot quietly shrink the audit.
-6. **Scope resolve** - intersect `$ARGUMENTS` with `inventory.targets`; persist `state.designCheck.scope = { argument, targetIds[] }`. Print the set grouped by screen as `<n> targets · <relaunchCount> relaunches` (cost from `plan`, not the target count). **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`** - scope = the latest `run-state.json` 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}/` (+ `assets/`) now, persist `state.designCheck.reportDir`; it exists before driving starts.
-9. **Worktree** - `{projectRoot}/.worktrees/{taskId}`, `taskId` = `DC-<shortId>`, never under $HOME; prune stale locks + add `.worktrees/` to `.git/info/exclude` first.
-
-Then persist `agent-state.json`. Full procedure: `$HOME/.claude/multi-agent-refs/design-check/init-inventory.md`. Read it for Phase 0 steps 1-9.
-
-## Phase 1 - Build & Launch (mock)
-
-Debug build in the worktree, boot + install once, fix status bar / appearance / locale, launch via `design_mock_launch` with the Phase 0 activation (`debug-only`: plain launch). Phase 3 relaunches, never rebuilds. Full procedure: `$HOME/.claude/multi-agent-refs/design-check/build-launch.md`. Read it for Phase 1.
-
-## Phase 2 - Figma fetch & variant mapping (module-scoped)
-
-Figma **discovery** happens only here: the frame tree is fetched once and no later phase browses Figma for candidates. Phase 3 may fetch a specific node the user hands over in the 3.3 batch-ask - a targeted fetch of an already-identified frame, and the only Figma call allowed after this phase.
-
-Fetch the frame tree, map each scoped target to a frame, fetch screenshot + design context per variant, persist `state.designCheck.variants[]`. **Ambiguous/unmatched → deferred to the Phase 3.3 batch-ask; never guess.** Full procedure: `$HOME/.claude/multi-agent-refs/design-check/figma-mapping.md`. Read it for Phase 2.
-
-## 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 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 relaunch target opens a screen, then every in-app target for that screen is flipped while the app is already there - **no relaunch between in-app targets**. Driving the plan is what makes full coverage affordable. Activate each target by its `driver.type`, and capture tap-reachable sub-states (sheets, modals, inline errors) under `<id>#<sub-label>`. Each capture (screenshot + `design_ui_geometry`) goes to `state.designCheck.captured[]`. **Persist `state` and `run-state.json` after every capture** so a dying run resumes from where it stopped. Full procedure (driver table, capture mechanics): `$HOME/.claude/multi-agent-refs/design-check/drive-capture.md`. Read it for Phase 3.1.
+## Scope, requirements, tracker
 
-Unreachable target → record `{ id, reason }` in `state.designCheck.skipped[]` with a concrete reason. "Requires a scenario / prefix / launch-arg" is **not** a reason - that describes the work, and the work is this phase's job.
+Before Phase 0, read `$HOME/.claude/multi-agent-refs/design-check/scope-and-ledger.md`: the scope grammar (empty, screen, `screen@variant`, target id, Figma URL, `--resume`), the requirements, the tracker detail and the ledger rules. Whole-module is the default and is meant to finish; scope is for resuming or re-checking, never for trimming. No mock mode and no snapshot capture: halt.
 
-### 3.2 Match each capture → Figma frame (auto)
+Tracker: `bash $HOME/.copilot/scripts/phase-tracker.sh init` + `add` for `0:Init & Gate`, `1:Build & Launch`, `2:Figma`, `3:Drive & Compare`, `4:Report`; there is no TaskList widget, so call `phase-tracker.sh render` after every state change and never TaskCreate.
 
-Accept only a **confident** match against the Phase 2 tree → `pairs[]`.
+Every Phase 0 / Phase 2 decision uses the `ask_choice` picker (`$HOME/.copilot/lib/ask-choice.sh`) with a `Step <i>/<n>` breadcrumb; confirm even a single option; never inherit state from a previous run.
 
-### 3.3 Batch-ask the user for EVERYTHING unmatched (ONE prompt, WITH the visual)
+## Phase 0 - Init, feasibility gate, inventory
 
-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**, name the screen, ask for the Figma node-id / URL in `outputLanguage`. Each answer becomes a confirmed pair; a declined screen is a skip with reason "no Figma frame supplied".
+Read `$HOME/.claude/multi-agent-refs/design-check/mcp-currency-gate.md` for step 0 and `$HOME/.claude/multi-agent-refs/design-check/init-inventory.md` for steps 1-9.
 
-### 3.4 Compare ALL pairs in one pass
+0. **MCP currency gate** before anything expensive: session stale or disk stale: **HALT** (reconnect, or update the checkout). Never substitute a local `node` call for a missing tool.
+1-3. Repo picker, module picker, platform detect.
+4. **Mock feasibility** (`design_mock_detect`): `false`: offer the **snapshot lane** (`captureLane = "snapshot"`, no in-app flips), declined or not renderable: **HALT** with `reason`, never fabricate a comparison. `"debug-only"`: warn, Continue / Cancel. `true`: persist `state.designCheck.mock`.
+5. **Scenario inventory** (`design_scenario_inventory`) is the target set; persist verbatim. `truncated: true`: say so and pass `coverage.truncatedInventory: true` in Phase 4. `targetCount: 0`: only the default launch state is auditable. List `ignored[]`.
+6-7. Scope resolve, `--resume`; confirm only above `coverage.confirmAbove` relaunches, as a cost estimate, never offering a smaller scope.
+8-9. Report dir now; worktree `{projectRoot}/.worktrees/DC-<shortId>`, never under $HOME.
 
-`design_visual_compare` per pair with `tolerance_px: 2, color_tolerance: 3, max_diff_pct: 1.0`. **Bottom sheets, modals, and any partial overlay need region alignment** (`live_region` from the sheet container in `design_ui_geometry`, never a guess, plus `expected_region` from the Figma placement). Attach Code Connect refs (best-effort); compose a paste-ready fix prompt. Full procedure (match, batch-ask mechanics, compare call, region alignment): `$HOME/.claude/multi-agent-refs/design-check/compare.md`. Read it for Phase 3.2-3.4.
+## Phase 1 - Build & launch
 
-**Edge insets are defects, not tolerances.** 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.
+Debug build in the worktree, launch via `design_mock_launch`; Phase 3 relaunches, never rebuilds. Read `$HOME/.claude/multi-agent-refs/design-check/build-launch.md` for Phase 1.
 
-### 3.5 Close the ledger
+## Phase 2 - Figma mapping
 
-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.
+The only Figma discovery; later only a node the user hands over in 3.3. **Ambiguous or unmatched: defer to 3.3, never guess.** Read `$HOME/.claude/multi-agent-refs/design-check/figma-mapping.md` for Phase 2.
 
-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 3 - Drive, capture, match, compare
 
-## Phase 4 - Report, coverage gate & export
+Iterate `scope.targetIds`; done when every id is resolved, not when taps run out. Before the first compare, read `$HOME/.claude/multi-agent-refs/features/design-conformance.md`.
 
-1. Output dir: `state.designCheck.reportDir` from Phase 0; never a second timestamped dir.
-2. Assemble the report object: `coverage` (scoped `targets`, `covered`, `skipped` with reasons, `truncatedInventory`, optional `floor`) and per-variant results with a `walk` block. Pass **ids**, not counts.
-3. Export with `design_report` (`html` + `pdf`, + `confluence` only when enabled via the `multi-agent-channels` adapter; else graceful skip). Full procedure (report object, export formats, cleanup): `$HOME/.claude/multi-agent-refs/design-check/export.md`. Read it for Phase 4.
-4. **COVERAGE GATE (blocking, not advisory)** - read `coverage` from the tool result and persist to `state.designCheck.coverage`:
-   - `gate: "pass"` → print per-variant PASS/FAIL + findings + report paths.
-   - `gate: "fail"` → the run is **INCOMPLETE**. Print `coverageError`, the `unaccountedIds`, and the command that closes the gap (`/multi-agent-design-check --resume`). Do not present an incomplete audit as finished, and never pad the covered list to make the gate pass.
+- **3.1** Drive `inventory.plan` batch by batch; persist `state` and `run-state.json` after every capture. Unreachable: skip with a concrete reason. Read `$HOME/.claude/multi-agent-refs/design-check/drive-capture.md`.
+- **3.2-3.4** Confident matches only; batch-ask everything unmatched ONCE, showing each live screenshot; compare all pairs (`tolerance_px: 2, color_tolerance: 3, max_diff_pct: 1.0`), sheets and modals with region alignment. **Edge insets are defects**: never raise `tolerance_px` to hide one. Read `$HOME/.claude/multi-agent-refs/design-check/compare.md`.
+- **3.5** Every id ends covered or skipped; `covered + skipped` must equal `targetIds` before Phase 4.
 
-   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.
+## Phase 4 - Report and coverage gate
 
-## Notes
+Use `state.designCheck.reportDir`. Pass ids, not counts; each variant carries `walk` with `didNotConverge` and `notVerified`. Export with `design_report` (Confluence only when enabled, via the `multi-agent-channels` adapter). Read `$HOME/.claude/multi-agent-refs/design-check/export.md` for Phase 4.
 
-- 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.
+**Coverage gate (blocking)**: `pass`: report results and paths. `fail`: the run is **INCOMPLETE**; print `coverageError`, `unaccountedIds` and `/multi-agent-design-check --resume`. Never pad the covered list. Remove the worktree unless asked to keep it; never the report dir.

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

@@ -13,352 +13,20 @@ Called with no args or `help`, show the usage guide in the user's preferred lang
 
 ## Language resolution
 
-Help is the assistant's own explanation to the user  -  render it in `prefs.global.outputLanguage`. Fall back to `prefs.global.promptLanguage` for prefs written before v8.2.0. Two valid values: `"en"` (default) and `"tr"`. If both are missing / malformed → treat as `"en"`.
+Help is the assistant's own explanation to the user - render it in `prefs.global.outputLanguage`, falling back to `prefs.global.promptLanguage` for older prefs. Two valid values: `"en"` (default) and `"tr"`; missing or malformed means `"en"`. Language rule: `$HOME/.claude/multi-agent-refs/rules.md`.
 
 ```bash
 PREFS="$HOME/.claude/multi-agent-preferences.json"
 LANG=$(jq -r '.global.outputLanguage // .global.promptLanguage // "en"' "$PREFS" 2>/dev/null || echo "en")
 ```
 
-Render **exactly one** of the two blocks below  -  the one matching `LANG`. Do not print both.
+Read **exactly one** catalog, the one matching `LANG`, and print its block. Never print both.
 
----
-
-## Render when `LANG == "en"`  -  English guide
-
-```
-+----------------------------------------------------------+
-|             Multi-Agent Task Orchestrator                |
-+----------------------------------------------------------+
-
-5 different input types supported  -  all enter the same flow:
-
-  multi-agent "{JIRA_KEY}-XXXXX"                 -> Jira ID
-  multi-agent "https://{JIRA_HOST}/browse/..."   -> Jira URL
-  multi-agent "https://github.com/.../issues/N"  -> GitHub Issue URL
-  multi-agent "#316"                              -> GitHub Issue #
-  multi-agent "bug/feature description"           -> Free-text
-
-(Copilot CLI uses the dash form: multi-agent-channels, etc.
- Claude Code uses colon form: /multi-agent:channels, etc.)
-
-------------------------------------------------------------
-
-How It Works (Phase 0  -  Interactive Flow):
-
-  1. PARSE       Classify input, fetch info from Jira/GitHub
-  2. PROJECT     $HOME scanned, projects listed -> select by number
-  3. BRANCH      Remote branches fetched (develop* first) -> select
-  4. DESIGN?     Any Figma URL or screenshot? (optional)
-  5. BRANCH NAME bugfix/{jiraId} or feature/{jiraId} -> confirm
-  6. GIT ID      Select identity from preferences (multiple supported)
-  7. INSTRUCTION Auto-detect if .instructions/ exists (figma etc.)
-  8. WORKSPACE   Ask where the branch lives: worktree (default) or project root
-
-------------------------------------------------------------
-
-Pipeline (after Phase 0):
-
-  Phase 0: Init      -> The 8 steps above
-  Phase 1: Plan      -> Stack detection + codebase scan, then task breakdown,
-                        architecture review and the Plan Approval Gate (Opus)
-  Phase 2: Dev       -> TDD: test -> code -> build (Sonnet) + build queue, then the
-                        Verify exit gate: build, lint, tests, secrets
-                        (the build runs ONCE per run; its log carries into Review)
-  Phase 3: Review    -> Parallel AI review + Fable triage, then the optional user test
-                        (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 4: Commit    -> Commit -> push -> PR + issue body update (never auto-closes)
-  Phase 5: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
-                        + internal capture (agent-log · knowledge · memory)
-
-  Autopilot always pauses at the Phase 5 channels menu (30-min timeout → session ends).
-
-------------------------------------------------------------
-
-Modes:
-
-  One pipeline. Every mode runs its whole phase set:
-    Plan -> Dev(Sonnet) -> Review -> Commit -> Report
-  What a run costs follows the evidence the task carries.
-
-  autopilot            Skip all confirmations and resolve the workspace to a
-                       worktree (EXCEPT Phase 5 channels menu)
-
-Dedicated dash commands (Copilot):
-  multi-agent-autopilot
-
-------------------------------------------------------------
-
-Utility Commands (dash form on Copilot, colon form on Claude Code):
-
-  /multi-agent:status         List tasks across all projects
-  /multi-agent:log [#id]      Show task log
-  /multi-agent:resume [#id]   Resume a paused task
-  /multi-agent:kill [#id]     Delete worktree (logs preserved)
-  /multi-agent:prune-logs     Delete per-task logs (audit + metrics kept; dry-run first)
-  /multi-agent:garbage-collect  Sweep leftover /tmp scratch + worktree residue (dry-run first)
-  /multi-agent:purge          Worktree + logs  -  full reset (double confirm)
-  /multi-agent:channels       Post multi-channel report (Jira/Confluence/Wiki/PR)
-  /multi-agent:review         Review 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
-  /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps
-  /multi-agent:analysis ["name"]  Feature-spec analysis. Asks the standard first: global (23-section dev handoff) or corporate (IG→UC→FG requirements doc). Stack optional
-  /multi-agent:analysis-resolve [doc]  Resolve an analysis doc's open questions one at a time, with source-labeled candidates
-  /multi-agent:review-analysis [doc | page | KEY]  Review a written analysis: gates first, then parallel model review; findings cite the rule
-  /multi-agent:feedback "msg" Tell the maintainer something broke; only your text is sent, shown before it goes
-  /multi-agent:create-jira ["desc"] [figma-url] [swagger-url]  Create a Jira Task/Bug/Story matching team conventions (asks type + preview + approval)
-  /multi-agent:sync           Sync ecosystem (Claude + Copilot + website)
-  /multi-agent:setup          Keychain tokens + Git identity + language onboarding
-  /multi-agent:language [en|tr]  Show or set prompt language
-  /multi-agent:store-ready [repo] [--archive=|--ipa=|--aab=|--apk=]  Pre-submission store readiness,
-                              iOS + Android, local-only. Three symmetric gates per platform: static package
-                              audit, the store's own validator, policy review vs source. Plus the running-app
-                              sweep. A skipped gate is never counted as a pass. Never uploads.
-  /multi-agent:testflight-validation [repo] [--ipa=|--archive=]  iOS-pinned alias of :store-ready.
-  /multi-agent:ios-coding-standard [module]  Audit an iOS module against the 99-rule coding-standard
-                              registry -> remediation plan + onboarding summary -> hand off to dev.
-
-------------------------------------------------------------
-
-Interactive Launchers:
+| `LANG` | Catalog |
+|---|---|
+| `tr` | `$HOME/.claude/multi-agent-refs/help/tr.md` |
+| anything else | `$HOME/.claude/multi-agent-refs/help/en.md` |
 
-  /multi-agent:jira           List MY open Jira issues → pick → branch → mode → go
-  /multi-agent:issue          List UNASSIGNED GitHub issues → pick → auto-assign → go
+## Copilot CLI rendering
 
-------------------------------------------------------------
-
-UI Testing (standalone):
-
-  /multi-agent:test                  Full simulator test (screenshot all screens)
-
-  Fixed-scenario commands  -  no quoting, and they autocomplete off `test-`:
-
-  /multi-agent:test-dark-mode        Dark mode bug test
-  /multi-agent:test-accessibility    Accessibility audit
-  /multi-agent:test-dynamic-type     Large text size test
-  /multi-agent:test-screenshots [tr] App Store screenshot set in a locale (default tr)
-
-  The scenario-tag form still works and is not deprecated  -  each command above is
-  an alias for it.
-
-  /multi-agent:test "dark mode" | "accessibility" | "dynamic type" | "screenshot <lang>"
-
-  `store-ready` is NOT a UI test: it validates a built package, on iOS and Android,
-  and lives at /multi-agent:store-ready. The old /multi-agent:test "store-ready"
-  tag still works and hands off there.
-
-Manual Test (Phase 3 user-test step, 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  -  multi-agent-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 multi-agent-toolkit design_* : design_mock_detect / _scenario_inventory / _mock_launch / _ui_geometry / _visual_compare / _report.
-
-------------------------------------------------------------
-
-Setup:
-
-  /multi-agent:setup
-
-  1. Dynamic Keychain Discovery
-  2. Token Mapping
-  3. Jira Project Key
-  4. Git Identity
-  5. Missing Tokens
-  6. Verify
-
-------------------------------------------------------------
-
-Key Features:
-
-  Multi-Platform  iOS, Android, Backend, Web  -  auto-detected
-  Build Queue     xcodebuild/Gradle serialized  -  parallel safe
-  Stack Aware     Auto-detects iOS/Android/Python/Node/Go/Docker
-  Det. Gates      Build + lint + test + secret scan BEFORE AI review
-  Dual Submodule  Multiple submodules simultaneously
-  Issue Safety    Never auto-closes issues
-  Bilingual       EN + TR  -  prompts, banners, and this help render in your language
-
-------------------------------------------------------------
-
-Logs: $HOME/.copilot/logs/multi-agent/{project}/{task-id}/  (Copilot)
-      $HOME/.claude/logs/multi-agent/{project}/{task-id}/  (Claude)
-```
-
----
-
-## Render when `LANG == "tr"`  -  Türkçe rehber
-
-```
-+----------------------------------------------------------+
-|             Multi-Agent Görev Orkestratörü               |
-+----------------------------------------------------------+
-
-5 farklı girdi tipi desteklenir  -  hepsi aynı akışa girer:
-
-  multi-agent "{JIRA_KEY}-XXXXX"                 -> Jira ID
-  multi-agent "https://{JIRA_HOST}/browse/..."   -> Jira URL
-  multi-agent "https://github.com/.../issues/N"  -> GitHub Issue URL
-  multi-agent "#316"                              -> GitHub Issue #
-  multi-agent "bug/özellik açıklaması"            -> Serbest metin
-
-(Copilot CLI dash form kullanır: multi-agent-channels vb.
- Claude Code colon form kullanır: /multi-agent:channels vb.)
-
-------------------------------------------------------------
-
-Nasıl Çalışır (Phase 0  -  İnteraktif Akış):
-
-  1. PARSE       Girdiyi sınıflandır, Jira/GitHub'dan bilgi çek
-  2. PROJECT     $HOME taranır, projeler listelenir -> numarayla seç
-  3. BRANCH      Remote branch'ler çekilir (develop* önde) -> seç
-  4. DESIGN?     Figma URL'si ya da screenshot var mı? (opsiyonel)
-  5. BRANCH NAME bugfix/{jiraId} veya feature/{jiraId} -> onayla
-  6. GIT ID      Kimlik seç (prefs'ten; birden fazla desteklenir)
-  7. INSTRUCTION .instructions/ varsa otomatik algıla
-  8. WORKSPACE   Branch nerede yaşayacak: worktree (default) ya da proje kökü
-
-------------------------------------------------------------
-
-Pipeline (Phase 0'dan sonra):
-
-  Phase 0: Init      -> Yukarıdaki 8 adım
-  Phase 1: Plan      -> Stack tespiti + codebase taraması, ardından task kırılımı,
-                        mimari inceleme ve Plan Onay Kapısı (Opus)
-  Phase 2: Dev       -> TDD: test -> kod -> build (Sonnet) + build queue, sonra
-                        Verify çıkış kapısı: build, lint, test, sır taraması
-                        (build koşu başına BİR kez çalışır, log'u Review'a devreder)
-  Phase 3: Review    -> Paralel AI review + Fable triage, sonra opsiyonel kullanıcı testi
-                        (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 4: Commit    -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
-  Phase 5: Report    -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
-                        + internal capture (agent-log · knowledge · memory)
-
-  Autopilot Phase 5 channels menüsünde HER ZAMAN durur (30 dk timeout → session biter).
-
-------------------------------------------------------------
-
-Modlar:
-
-  Derinlik Faz 0 Adım 7.5'te sorulur, bayrakla geçilmez:
-    Tam    Plan -> Dev(Sonnet) -> Review -> Commit -> Report
-    Kısa   Dev(Opus, kendi kendine yeten) -> Review -> Commit -> Report
-  taskType'a göre önerilir. Review iki durumda da atlanmaz.
-
-  autopilot            Derinlik sorusu dahil tüm onayları atlar, bu yüzden her
-                       zaman Tam koşar (İSTİSNA: Phase 5 channels menüsü)
-
-Dedicated dash komutlar (Copilot):
-  multi-agent-autopilot
-
-------------------------------------------------------------
-
-Utility Komutları:
-
-  /multi-agent:status         Tüm projelerdeki task'ları listele
-  /multi-agent:log [#id]      Task log'unu göster
-  /multi-agent:resume [#id]   Duraklamış task'ı devam ettir
-  /multi-agent:kill [#id]     Worktree'yi sil (log'lar korunur)
-  /multi-agent:prune-logs     Task bazlı log'ları sil (audit + metrics korunur; önce dry-run)
-  /multi-agent:garbage-collect  /tmp artıkları + worktree residue süpür (önce dry-run)
-  /multi-agent:purge          Worktree + log'lar  -  tam reset (çift onay)
-  /multi-agent:channels       Multi-channel rapor gönder (Jira/Confluence/Wiki/PR)
-  /multi-agent:review         PR veya branch diff'ini review et; URL yoksa -> açık GitHub/Bitbucket PR seç
-  /multi-agent:review-jira    Jira maddesinin pipeline hazırlığını değerlendir -> eksikleri yorumla
-  /multi-agent:review-issue   GitHub issue hazırlığını değerlendir -> eksikleri yorumla
-  /multi-agent:create-jira ["açıklama"] [figma-url] [swagger-url]  Takım standartlarına uygun Jira Task/Bug/Story oluştur (tip sorar + önizleme + onay)
-  /multi-agent:sync           Ekosistemi senkronize et
-  /multi-agent:setup          Keychain token + Git kimliği + dil onboarding
-  /multi-agent:language [en|tr]  Prompt dilini göster veya ayarla
-  /multi-agent:store-ready [repo] [--archive=|--ipa=|--aab=|--apk=]  Yükleme öncesi store hazırlığı,
-                              iOS + Android, yalnızca lokal. Platform başına 3 simetrik kapı: statik paket
-                              denetimi, store'un kendi doğrulayıcısı, kaynağa karşı politika incelemesi.
-                              Artı çalışan-app sweep'i. Atlanan kapı asla pass sayılmaz. Asla yüklemez.
-  /multi-agent:testflight-validation [repo] [--ipa=|--archive=]  :store-ready'nin iOS'a sabitlenmiş alias'ı.
-  /multi-agent:ios-coding-standard [modül]  Bir iOS modülünü 99 kurallık kodlama-standardı registry'sine
-                              göre denetler -> düzeltme planı + onboarding özeti -> dev'e devreder.
-
-------------------------------------------------------------
-
-İnteraktif Launcher'lar:
-
-  /multi-agent:jira           BENİM açık Jira issue'larımı listele → seç → başla
-  /multi-agent:issue          ATANMAMIŞ GitHub issue'ları → seç → auto-assign → başla
-
-------------------------------------------------------------
-
-UI Testing (standalone):
-
-  /multi-agent:test                  Tam simulator testi (tüm ekran screenshot'ları)
-
-  Sabit-senaryo komutları  -  tırnak gerekmez, `test-` ile autocomplete'e düşer:
-
-  /multi-agent:test-dark-mode        Dark mode bug testi
-  /multi-agent:test-accessibility    Erişilebilirlik denetimi
-  /multi-agent:test-dynamic-type     Büyük metin boyutu testi
-  /multi-agent:test-screenshots [tr] Belirtilen dilde App Store screenshot seti (default tr)
-
-  Senaryo etiketli form çalışmaya devam eder, kaldırılmadı  -  yukarıdaki komutların
-  her biri onun alias'ı.
-
-  /multi-agent:test "dark mode" | "accessibility" | "dynamic type" | "screenshot <dil>"
-
-  `store-ready` bir UI testi DEĞİL: üretilmiş paketi doğrular, iOS + Android, ve
-  /multi-agent:store-ready altında. Eski /multi-agent:test "store-ready" etiketi
-  çalışmaya devam eder ve oraya devreder.
-
-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  -  multi-agent-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 multi-agent-toolkit design_* : design_mock_detect / _scenario_inventory / _mock_launch / _ui_geometry / _visual_compare / _report.
-
-------------------------------------------------------------
-
-Setup:
-
-  /multi-agent:setup
-
-  1. Dynamic Keychain Discovery
-  2. Token Mapping
-  3. Jira Project Key
-  4. Git Kimliği
-  5. Eksik Token'lar
-  6. Doğrulama
-
-------------------------------------------------------------
-
-Temel Özellikler:
-
-  Multi-Platform  iOS, Android, Backend, Web  -  otomatik tespit
-  Build Queue     xcodebuild/Gradle seri  -  parallel güvenli
-  Stack Aware     iOS/Android/Python/Node/Go/Docker otomatik
-  Det. Gates      AI review'dan ÖNCE build + lint + test + secret scan
-  Dual Submodule  Birden çok submodule eş zamanlı
-  Issue Safety    Issue'lar asla auto-close edilmez
-  Bilingual       EN + TR  -  prompt'lar, banner'lar ve bu help dilinize göre
-
-------------------------------------------------------------
-
-Log'lar: $HOME/.copilot/logs/multi-agent/{project}/{task-id}/  (Copilot)
-         $HOME/.claude/logs/multi-agent/{project}/{task-id}/  (Claude)
-```
+The catalogs are shared with Claude Code and written in its colon form. On Copilot CLI, print every `/multi-agent:<name>` as `/multi-agent-<name>` (for example `/multi-agent:create-jira` becomes `/multi-agent-create-jira`), and print the log root as `$HOME/.copilot/logs/multi-agent/{project}/{task-id}/`. Change nothing else in the block.