@mmerterden/multi-agent-pipeline 8.6.2 → 10.2.0

package/README.md

@@ -5,40 +5,27 @@
 [![Node.js](https://img.shields.io/badge/Node.js-18%20%7C%2020%20%7C%2022-green)](https://nodejs.org)
 [![Zero Dependencies](https://img.shields.io/badge/dependencies-0-brightgreen)](https://github.com/mmerterden/multi-agent-pipeline/blob/main/package.json)
 
-8-phase AI development pipeline for **Claude Code** and **Copilot CLI**. Multi-repo orchestration, platform identity routing, push-must-succeed policy, CLI-aware parallel review with Opus triage (Claude Code: 2-model Opus+Sonnet · Copilot CLI: 3-model GPT-5.4+Opus+Sonnet), commit/PR creation — and, as of 5.0.0, a generic Figma-to-Component pipeline that works on iOS (SwiftUI) and Android (Jetpack Compose) with the same workflow.
+8-phase AI development pipeline for **Claude Code** and **Copilot CLI**. Multi-repo orchestration, platform identity routing, push-must-succeed policy, CLI-aware parallel review with Opus triage (Claude Code: 2-model Opus+Sonnet · Copilot CLI: 3-model GPT-5.4+Opus+Sonnet), commit/PR creation - and, as of 5.0.0, a generic Figma-to-Component pipeline that works on iOS (SwiftUI) and Android (Jetpack Compose) with the same workflow.
 
 ### Current at-a-glance (live from filesystem)
 
 | Surface | Count |
 |---|---|
-| Slash commands (colon-form `/multi-agent:*`) | 29 |
-| Copilot skills (dash-form `multi-agent-*`) | 29 |
-| Third-party tool adapters (Tier 2 + Tier 3) | 6 |
+| Slash commands (colon-form `/multi-agent:*`) | 34 |
+| Copilot skills (dash-form `multi-agent-*`) | 34 |
+| Platforms (native: Claude Code, Copilot CLI · adapter: Cursor, Antigravity, VS Code Copilot Chat, Codex CLI) | 6 |
 | Store-compliance skills (`apple-archive-compliance`, `google-play-compliance`) | 2 |
 | Figma skills (iOS + Android + Common) | 37 |
-| External skill catalog (`shared/external/`) | 127 |
-| Total `SKILL.md` files across all groups | 196 |
-| Smoke suites | 88 |
-| Golden-task fixtures (`pipeline/eval/golden-tasks/`) | 2 |
+| External skill catalog (`shared/external/`) | 143 |
+| Total `SKILL.md` files across all groups | 217 |
+| Smoke suites | 108 |
+| Golden-task fixtures (`pipeline/eval/golden-tasks/`) | 8 |
 | Eval-triage fixtures | 11 |
-| JSON schemas | 13 |
+| JSON schemas | 16 |
 | Agent personas | 8 |
 | Pipeline phases | 8 |
 
-## What's new
-
-Latest release: **v8.5.6** (review-actions contract: inline comments + approve/needs-work + Bitbucket Server, 2026-05-08) — `/multi-agent:review`'in PR-mode kontratı yeniden yazıldı. v8.5.5'in tek-büyük-advisory-yorumu pattern'ı KALDIRILDI; yerine **per-finding inline comment + explicit approve/needs-work state** kontratı geldi. Karar kuralı: 0 accepted blocking AND 0 accepted important → APPROVE (yorum yok). ≥1 → NEEDS_WORK + her accepted blocking/important için inline yorum (anchored to `file:line`). Suggestion'lar PR'a hiç gitmez (chat-only). Bitbucket Server URL'leri artık first-class — full URL parser + REST API ile diff/comment/approve. PR yorum body'leri her zaman `outputLanguage`'e renderlanır (v8.5.5'te EN-only bug'ı vardı). Yeni: `lib/post-pr-review.sh` (provider-aware orchestrator), `refs/channels/pr-review-actions.md` (yeni kanonik kontrat), `smoke-pr-review-actions.sh` (decision rule + lang + provider switch lint). Silinen: `pr-review-comment.md`, `render-pr-review-body.sh`, `smoke-pr-review-comment-template.sh` — fork'lar `post-pr-review.sh "$TASK_ID"` çağrısına geçmeli. Previous: v8.5.5 (review accepts PR input + posts verdict back, 2026-05-08) — `/multi-agent:review` now takes 5 input shapes (empty / branch / `#N` / `repo#N` / full PR URL) and in PR-mode fetches the diff via `gh pr diff` and prompts to post the parallel reviewer verdict as one canonical comment per run. Renderer reads `agent-state.review.*` and emits the body for `gh pr comment --body-file`; new `refs/channels/pr-review-comment.md` template enforces verdict block + per-severity findings + triage notes + build/test + footer marker, with hard prohibitions on `Closes/Fixes/Resolves` keywords, em-dashes in prose, and model vendor names. New smoke gate `smoke-pr-review-comment-template.sh` lints anchors + wiring + input parser. Branch-mode invocations stay chat-only (no auto-post). Previous: v8.5.4 (drop 4 unused adapters, 2026-05-08) — Windsurf, Cline, Zed AI, and Continue.dev knowledge-layer adapters removed because the pipeline owner did not use them; their smoke surface added cost without benefit. Tier 1 (Claude Code + Copilot CLI orchestration) and Tier 2 (Cursor + GitHub Copilot Chat knowledge layer) are unchanged. The adapter base framework (`pipeline/adapters/_base.mjs`) is preserved — re-adding any dropped tool is a one-file PR. Previous: v8.5.3 (Defect 1 picker language axis fully closed, 2026-05-08) — phase docs that drive runtime picker rendering had legacy "ask in English (`promptLanguage`)" wording that overrode the v8.5.1 `rules.md` matrix; user with `outputLanguage="tr"` saw the Phase 6 WIP-checkout picker render in English. Fix narrows `phase-6-commit.md` + `_dev-context.md` + `_repo-picker.md` to the per-field matrix (question + description follow `outputLanguage`; label + header stay English) and adds `smoke-language-axis.sh` to prevent regression. Previous: v8.5.2 (v9 stability defects 5 / 8 / 10 closed, 2026-05-08) — Phase 1.5 Existing-Component Discovery gate prevents silent overwrite of components that already have a Code Connect mapping or an existing source file (5 statuses: `GREENFIELD_OK` / `ALREADY_MAPPED` / `EXISTING_SOURCE_NO_CC` / `AMBIGUOUS_SOURCE` / `GAP_ANALYSIS`); Phase 2 + Phase 6 ENTRY GATEs now consult `discovery.status`. Token telemetry block enforced in phases 1 / 2 / 3 / 4 — every LLM call must invoke `phase-tracker.sh tokens <N> <in> <out>` so live cost shows on the active phase tile. New smoke gates: `smoke-tracker-tokens-invocation`, `smoke-worktree-path-convention` (forbidden `$HOME/.worktrees` patterns), `smoke-existing-discovery-gate`, `smoke-issue-comment-template`, `smoke-no-token-prompt`. Previous: v8.5.1 (stability fixes for 9 GH1241 defects + genericity review, 2026-05-08) — language matrix narrowed (`AskUserQuestion.label` + `header` stay English, `question` + `description` follow `outputLanguage`), canonical `refs/channels/issue-comment.md` template + `update-issue-progress.sh` script (Phase 7 Step 1.5 wires comment + flag sync), `keychain.md` Rule 1 forbids mid-run token prompts (routes to Setup Wizard instead), `phase-tracker.sh` pointer-fallback now warns on concurrent init, `dev.md` Phase 3 dispatch on `taskType==="component"` keeps the figma 17-substep orchestrator running even in `--dev` mode. v8.5.0 added the GitHub Projects v2 board adapter as the 5th channel + figma source incremental sync. v8.4.1 added the provider-aware account picker (Bitbucket / GitHub / GitLab), network reachability gate before the branch picker, Phase 6 PR creation contract with default reviewers, and the explicit `promptLanguage=en` (spec docs) / `outputLanguage=user-selectable` (chat + external bodies) split. v8.4.0 retired the standalone ArchiveGuard Swift binary in favour of the `ios_app_store_audit` MCP tool in `@mmerterden/dev-toolkit-mcp` ≥ v2.4 — same 17 rules, same JSON shape, all four consumer surfaces work without changes. **Cross-platform status:** macOS Claude Code path is production-ready; Linux libsecret + Windows PowerShell paths are coded but unverified — see CHANGELOG for honest field-testing notes.
-
-Four orthogonal additions, all advisory-by-default, all Cross-CLI parity preserved:
-
-- **Per-task Cost Breakdown** in `agent-log.md` — every Phase 7 run now appends a `## Cost Breakdown` block with per-phase tokens (in/out) + estimated USD, sourced from `phase-tracker.sh tokens` accumulators and `cost-table.json` prices. Rendered by `pipeline/scripts/render-agent-log-cost.sh`. Independent of the channels-side `reportContent.costSummary` (PR/Jira gating). Token forwarder `LOG_METRIC_FORWARD_TO_TRACKER=1` keeps `metrics.jsonl` and the tracker in sync from one call site.
-- **Phase 4 Step 1.75 — Diff Risk Scoring** (advisory): `pipeline/scripts/diff-risk-score.mjs` runs before reviewer dispatch and injects a top-N risk-ranked priority list into each reviewer's prompt. Heuristic, deterministic, sub-second, no LLM. Signals: security paths (×3), schema migrations (×4), public API surfaces (×2), no-test-change (×2.5), complexity delta (×1.5), UI-critical paths (×1.5), loc changed (×1). Default ON; flip `prefs.global.diffRiskAdvisory = false` to opt out.
-- **Phase 5 Step 0 — Test Gap Report** (advisory): `pipeline/scripts/test-gap-scan.mjs` walks the diff for newly added public symbols and reports those with no paired test. Stack-specific rules ship for iOS, Android, Python, and Node.js. iOS Views and Android `@Composable` symbols default to `important`; other public API additions to `suggestion`. Optional gating via `prefs.testGap.blockingThreshold`.
-- **Phase 4 Triage Memory** (advisory): per-repo append-only JSONL corpus at `~/.claude/memory/multi-agent/<repo-slug>/triage-corpus.jsonl` records every accepted/deferred/rejected finding. Phase 7 ingests on completion (idempotent); Phase 1 enriches the analysis with similar past tasks; Phase 4 triage attaches prior-art hits to each raw finding. Token-overlap recall, zero deps. `/multi-agent:search "<text>" --semantic` flag routes the query to the corpus instead of agent-log grep. Default ON; flip `prefs.global.priorArtEnrichment.enabled = false` to opt out.
-
-Cross-CLI parity: every change ships byte-identical on Claude Code (colon-form `/multi-agent:*`) and Copilot CLI (dash-form `multi-agent-*`). New smokes (5): `smoke-agent-log-cost`, `smoke-diff-risk`, `smoke-test-gap`, `smoke-triage-memory` plus extensions to `smoke-cost-summary`. New schemas: `diff-risk.schema.json`, `test-gap.schema.json`, `triage-corpus.schema.json` (3 new).
-
-Full version history lives in [CHANGELOG.md](./CHANGELOG.md). Every release entry is recorded there to avoid drift between the two files.
+> Platform tiers, stated honestly: **Claude Code** and **Copilot CLI** run the full pipeline natively - the gate scripts + live tracker are installed to `~/.claude` / `~/.copilot`, and on Claude Code a `PreToolUse` hook hard-blocks on the secret scan. **Cursor, Antigravity, and VS Code Copilot Chat** (v9.4.0+) receive the orchestration workflow + subagents/agents + the dev-toolkit MCP server, AND the gate scripts are installed to a shared `~/.multi-agent/` runtime that the emitted agents invoke by absolute path - so the deterministic gates (evidence, secret, intent, consensus, cost) DO run there. The remaining gap vs Claude Code is enforcement strength: those three platforms have no `PreToolUse` hook, so the gates are workflow-enforced (the agent runs them as steps) rather than OS-blocked. See `refs/picker-contract.md`.
 
 > Security issue? See [SECURITY.md](./SECURITY.md). Please do not open public issues for vulnerabilities.
 
@@ -48,24 +35,24 @@ Full version history lives in [CHANGELOG.md](./CHANGELOG.md). Every release entr
 - Claude Code (https://claude.ai/code) **or** GitHub Copilot CLI
 - macOS, Linux, or Windows (Git Bash / WSL). Native credential storage everywhere:
   - **macOS** → Keychain (`security`)
-  - **Linux** → libsecret (`secret-tool` — `apt install libsecret-tools` / `dnf install libsecret`)
-  - **Windows** → Credential Manager (PowerShell `CredentialManager` module — `Install-Module CredentialManager`)
+  - **Linux** → libsecret (`secret-tool` - `apt install libsecret-tools` / `dnf install libsecret`)
+  - **Windows** → Credential Manager (PowerShell `CredentialManager` module - `Install-Module CredentialManager`)
 - Runtime CLIs the pipeline shells out to:
   - `gh` (GitHub CLI) for issue / PR flows
   - `jq` for JSON parsing
   - `python3` (stdlib only, used by the deterministic keychain helper)
   - `bash` 4+
 
-The package is **public on npmjs.org** — no auth, no PAT, no `~/.npmrc` setup needed:
+The package is **public on npmjs.org** - no auth, no PAT, no `~/.npmrc` setup needed:
 
 ```bash
 npm view @mmerterden/multi-agent-pipeline version
-# → prints "8.6.1" (or newer)
+# → prints "10.0.0" (or newer)
 ```
 
 If `npm view` shows a stale version, run `npm cache clean --force` and retry.
 
-> **New here?** Worked end-to-end transcripts live in [`examples/`](./examples/) — bug fix from Jira, feature in autopilot, `--dev` fast path, and recovery from a broken run. Read one before you run the pipeline on your own code.
+> **New here?** Worked end-to-end transcripts live in [`examples/`](./examples/) - bug fix from Jira, feature in autopilot, `--dev` fast path, and recovery from a broken run. Read one before you run the pipeline on your own code.
 >
 > **Something broke?** [`docs/recovery-guide.md`](./docs/recovery-guide.md) is the single-page index of every failure mode (triage fallback, worktree collision, state corruption, identity rewind, etc.) and its fix.
 >
@@ -73,9 +60,9 @@ If `npm view` shows a stale version, run `npm cache clean --force` and retry.
 
 ## Quick Start
 
-### Option A — Install from source (recommended for development)
+### Option A - Install from source (recommended for development)
 
-Clone the repo and run the installer directly — full read access to source files.
+Clone the repo and run the installer directly - full read access to source files.
 
 ```bash
 git clone git@github.com:mmerterden/multi-agent-pipeline.git
@@ -88,10 +75,13 @@ node install.js --all                   # Both Claude + Copilot
 # Third-party AI tool adapters (knowledge layer only)
 node install.js --cursor                # Cursor (.cursor/rules/*.mdc + .cursorrules)
 node install.js --copilot-chat          # GitHub Copilot Chat (.github/copilot-instructions.md)
-node install.js --all-tools             # Everything: 2 orchestration (Claude + Copilot CLI) + 2 adapter targets
+node install.js --antigravity           # Antigravity (.agent/ + AGENTS.md)
+node install.js --codex                 # OpenAI Codex CLI (global: ~/.codex/prompts + config.toml)
+node install.js --all-tools             # Everything: 2 native (Claude + Copilot CLI) + 4 adapter targets
 node install.js --cursor --target=/path/to/repo   # Adapter target override (default: cwd)
 
 node install.js --link                  # Symlink mode (dev, saves ~10K tokens)
+node install.js --all --dry-run         # Preview every operation, write nothing
 
 # Token-preserving uninstall (Keychain access tokens NEVER touched)
 node install.js                         # ...later...
@@ -103,7 +93,7 @@ node pipeline/scripts/uninstall.mjs --cursor      # selective uninstall
 npm link
 ```
 
-**IMPORTANT — run setup before your first task:**
+**IMPORTANT - run setup before your first task:**
 
 ```
 /multi-agent:setup
@@ -113,23 +103,26 @@ This discovers your Keychain tokens (Jira, Bitbucket, GitHub, etc.), sets up you
 
 Update later with `git pull && npm install` inside the clone. Pin to a specific version by checking out the corresponding tag (`git tag -l` to list).
 
-### Option B — npx (public registry, no auth)
+### Option B - npx (public registry, no auth)
 
 ```bash
-npx @mmerterden/multi-agent-pipeline install            # Claude Code (default)
-npx @mmerterden/multi-agent-pipeline install --copilot  # Copilot CLI
-npx @mmerterden/multi-agent-pipeline install --all      # Both Claude + Copilot
-npx @mmerterden/multi-agent-pipeline install --cursor       # Cursor adapter
-npx @mmerterden/multi-agent-pipeline install --copilot-chat # GitHub Copilot Chat adapter
-npx @mmerterden/multi-agent-pipeline install --all-tools    # Every supported tool
+npx @mmerterden/multi-agent-pipeline install            # Claude Code only (default)
+npx @mmerterden/multi-agent-pipeline install --copilot  # Copilot CLI only
+npx @mmerterden/multi-agent-pipeline install --all      # Both native CLIs (Claude + Copilot)
+npx @mmerterden/multi-agent-pipeline install --cursor       # Cursor adapter (per-project, cwd)
+npx @mmerterden/multi-agent-pipeline install --copilot-chat # GitHub Copilot Chat adapter (per-project)
+npx @mmerterden/multi-agent-pipeline install --antigravity  # Antigravity adapter (per-project)
+npx @mmerterden/multi-agent-pipeline install --codex        # OpenAI Codex CLI (global ~/.codex)
+npx @mmerterden/multi-agent-pipeline install --all-tools    # Everything: 2 native + 4 adapter targets
 npx @mmerterden/multi-agent-pipeline install --link     # Symlink mode
+npx @mmerterden/multi-agent-pipeline install --all --dry-run  # Preview, write nothing
 
 # Token-preserving uninstall
 npx @mmerterden/multi-agent-pipeline uninstall          # interactive, all targets
 npx @mmerterden/multi-agent-pipeline uninstall --dry-run # preview only
 ```
 
-### Option C — Global install (public registry, no auth)
+### Option C - Global install (public registry, no auth)
 
 ```bash
 npm install -g @mmerterden/multi-agent-pipeline
@@ -156,9 +149,20 @@ When opted in, the ping includes:
 - Your GitHub username (via `gh api user` if authenticated) and Git email
 - Hostname, OS, arch, Node version
 
-Nothing else is collected. Ping failures are silent — telemetry never blocks or
+Nothing else is collected. Ping failures are silent - telemetry never blocks or
 slows down the install.
 
+## What's new
+
+- **v10.1.0** (2026-06-20) - Fable 5 retired (no longer available): the five heavy agent personas plus Phase 1 / Phase 2 / Phase 4 reviewer-1 + triage and `--dev` fast mode now route to Opus (top available tier); fallback ladder is `opus -> sonnet`. Per-task cost guard (`costBudget`) now defaults on in warn mode. Token economy: Phase 4 shared cache prefix + single-repo diff cap, Phase 1 light Explore tier for small bugfixes, triage prior-art injection capped.
+- **v10.0.0** (2026-06-12) - quality major driven by a 10-category self-audit + competitive sweep: validator gates wired into phases 1/2/4 (fails closed), Phase 3 code-simplifier diff-shrink pass, Phase 4 lesson memory loop, Phase 2 cross-artifact consistency gate, skill frontmatter linter (repaired 31 SKILL.md), installer `--dry-run` + unknown-flag rejection, timeout-guarded smoke runner, adapter family deduplicated (~490 lines), CI hardening (blocking lint, npm audit, shellcheck), tag-driven npm release automation, CHANGELOG split (310KB -> 40KB).
+- **v9.10.2** (2026-06-11) - live per-phase token narration on completion; tracker mandates per-phase cost lines in the final report.
+- **v9.10.1** (2026-06-11) - Claude Fable 5 fallback contract: date gate, dispatch retry, and budget guard when the Fable tier is unavailable.
+- **v9.10.0** (2026-06-11) - Claude Fable 5 adoption on the Claude Code side: the five heavy agent personas plus Phase 1 / Phase 2 / Phase 4 reviewer-1 + triage and `--dev` fast mode route to `claude-fable-5`; cost ledger gains `fable` pricing and fixes the stale `opus` entry.
+
+Full version history lives in [CHANGELOG.md](./CHANGELOG.md) - every release entry is recorded there to avoid drift between the two files.
+
+
 ## Troubleshooting
 
 ### `sh: multi-agent-pipeline: command not found`
@@ -166,7 +170,7 @@ slows down the install.
 `npx` couldn't fetch the package. Most common causes:
 
 - Network blocked or proxy in front of npmjs.org.
-- Stale npx cache — `npx clear-npx-cache` then retry.
+- Stale npx cache - `npx clear-npx-cache` then retry.
 - Wrong package name (it is `@mmerterden/multi-agent-pipeline`, with the scope).
 
 ### `npm error code E404` on `registry.npmjs.org`
@@ -175,7 +179,7 @@ The package wasn't reachable. Quick checks:
 
 ```bash
 curl -fsSL "https://registry.npmjs.org/@mmerterden/multi-agent-pipeline" | jq -r '."dist-tags".latest'
-# Should print 8.6.1 (or newer)
+# Should print 10.0.0 (or newer)
 ```
 
 - If this prints a version → your local npm cache is stale; run `npm cache clean --force` and retry.
@@ -183,42 +187,39 @@ curl -fsSL "https://registry.npmjs.org/@mmerterden/multi-agent-pipeline" | jq -r
 
 ### Older PAT / GitHub Packages docs
 
-Earlier README revisions referenced GitHub Packages with a Classic PAT and `~/.npmrc` setup. The package moved to **public npmjs.org** in v8.6.1; no token, no `~/.npmrc` line is needed. If you set one up previously, you can leave it — it just won't be consulted.
+Earlier README revisions referenced GitHub Packages with a Classic PAT and `~/.npmrc` setup. The package moved to **public npmjs.org** in v8.6.1; no token, no `~/.npmrc` line is needed. If you set one up previously, you can leave it - it just won't be consulted.
 
 ## Tool support
 
-> **TL;DR** — Full pipeline orchestration runs on Claude Code + Copilot CLI. Knowledge layer (rules + skills) ports to Cursor and GitHub Copilot Chat via dedicated adapters. Other tools require manual port. (Pre-v8.5.4 the adapter set also covered Windsurf, Cline, Zed, and Continue.dev — those were dropped in v8.5.4 because the pipeline owner did not use them; reintroducing any of them is a one-file add against `pipeline/adapters/_base.mjs`.)
+> **TL;DR** - Full pipeline orchestration runs on **Claude Code, Copilot CLI, Cursor, Antigravity, VS Code Copilot Chat, and OpenAI Codex CLI**. Claude Code and Copilot CLI run it natively; Cursor (`.cursor/agents` + `/multi-agent` command), Antigravity (`.agent/workflows` + rules), and VS Code Copilot Chat (`.github/agents` + `/multi-agent` prompt) run it via per-platform orchestration adapters, with the dev-toolkit MCP server registered automatically. Codex CLI runs it via a global adapter (`~/.codex/prompts/multi-agent.md` + `~/.codex/config.toml` MCP); since Codex has no subagent fan-out, its parallel review degrades to a sequential adversarial two-pass. Interactive pickers and hard gates degrade per `refs/picker-contract.md` (native dialog where available, else the `ask_user_choice` MCP tool or `pipeline/lib/ask-choice.sh`). Note: Gemini CLI is being folded into Antigravity (consumer support ends 2026-06-18), so Antigravity is the forward target.
 
-### Tier 1 — Full pipeline (orchestration + knowledge)
+### Tier 1 - Full pipeline (orchestration + knowledge)
 
 | Tool | Install Flag | How It Works |
 | --- | --- | --- |
-| **Claude Code** | `--claude` (default) | Slash commands + shared + figma skills + agents + rules + scripts |
-| **Copilot CLI** | `--copilot` | Instructions + shared + figma skills + scripts |
+| **Claude Code** | `--claude` (default) | Native: slash commands + shared + figma skills + agents + rules + scripts |
+| **Copilot CLI** | `--copilot` | Native: instructions + shared + figma skills + scripts |
+| **Cursor** | `--cursor` | Adapter: `.cursor/agents/ma-*.md` subagents + `.cursor/commands/multi-agent.md` + rules + `.cursor/mcp.json` |
+| **Antigravity** | `--antigravity` | Adapter: `.agent/workflows/multi-agent.md` + `.agent/rules/` + `AGENTS.md` + `.agent/mcp_config.json` |
+| **VS Code Copilot Chat** | `--copilot-chat` | Adapter: `.github/agents/ma-*.agent.md` + `.github/prompts/multi-agent.prompt.md` + `.vscode/mcp.json` |
+| **OpenAI Codex CLI** | `--codex` | Global adapter: `~/.codex/prompts/multi-agent.md` + `~/.codex/AGENTS.md` + `~/.codex/config.toml` ([mcp_servers.dev-toolkit]) |
 
-Both CLIs install from the same `pipeline/skills/` source. Tree organization:
+Claude Code and Copilot CLI run the pipeline natively. Cursor, Antigravity, and VS Code Copilot Chat run it through per-platform orchestration adapters that transform the pipeline personas (`pipeline/agents/*.md`) into that platform's subagent/agent format and emit a `/multi-agent` command/workflow, registering the dev-toolkit MCP server automatically. Codex CLI is a global-config tool (its prompts + MCP live under `~/.codex`, with no per-project prompt directory), so its adapter installs globally and runs the `/multi-agent` slash command sequentially - Codex has no subagent fan-out, so the parallel review degrades to a sequential adversarial two-pass. Where a platform lacks a native picker, confirmations degrade per `refs/picker-contract.md` (the `ask_user_choice` MCP tool or `pipeline/lib/ask-choice.sh`); hard blocking gates degrade to advisory rules plus a CI smoke step.
 
-- `pipeline/skills/shared/core/` — **orchestration skills** (`multi-agent-*` dash-form mirrors of colon-form slash commands + compliance skills + orchestrator)
-- `pipeline/skills/shared/external/` — **127 third-party / curated iOS, Android, and generic guidance skills** (SwiftUI, Jetpack Compose, testing, performance, security, etc.)
-- `pipeline/skills/figma-ios/` + `pipeline/skills/figma-android/` — **5 + 5 platform-specific Phase 3 sub-skills** (SwiftUI and Jetpack Compose code generation)
-- `pipeline/skills/figma-common/` — **27 platform-agnostic Figma helpers** (iterate, commit, wiki setup, MCP auth, performance harness)
+All install from the same `pipeline/skills/` source. Tree organization:
 
-You get identical skill coverage regardless of which CLI you use. Both CLIs also receive the same `pipeline/scripts/` tree so multi-CLI-only installs stay self-contained.
+- `pipeline/skills/shared/core/` - **orchestration skills** (`multi-agent-*` dash-form mirrors of colon-form slash commands + compliance skills + orchestrator)
+- `pipeline/skills/shared/external/` - **127 third-party / curated iOS, Android, and generic guidance skills** (SwiftUI, Jetpack Compose, testing, performance, security, etc.)
+- `pipeline/skills/figma-ios/` + `pipeline/skills/figma-android/` - **5 + 5 platform-specific Phase 3 sub-skills** (SwiftUI and Jetpack Compose code generation)
+- `pipeline/skills/figma-common/` - **27 platform-agnostic Figma helpers** (iterate, commit, wiki setup, MCP auth, performance harness)
 
-### Tier 2 — Knowledge layer only
-
-These tools don't have subagent dispatch, so the 8-phase orchestration can't run there. The rules tree + skills catalog ports natively via per-tool adapters.
-
-| Tool | Install Flag | Output | What works | What doesn't |
-| --- | --- | --- | --- | --- |
-| **Cursor** | `--cursor` | `.cursor/rules/multi-agent-*.mdc` (modern, 2025+) + `.cursorrules` legacy fallback | 193 SKILL contents, 12 rules, glob-aware activation | Slash commands, parallel review, autopilot, Phase 4 triage |
-| **GitHub Copilot Chat** | `--copilot-chat` | `.github/copilot-instructions.md` (marker-wrapped) + `.github/instructions/multi-agent-*.instructions.md` | Per-skill instructions with `applyTo:` glob frontmatter; loaded automatically into every Copilot Chat conversation in the repo | Slash commands, parallel review, autopilot, Phase 4 triage |
+You get identical skill coverage regardless of which CLI you use. Both CLIs also receive the same `pipeline/scripts/` tree so multi-CLI-only installs stay self-contained.
 
-All adapters default to `process.cwd()`; override with `--target=<path>`. Multiple tools at once: `--all-tools` (covers both Tier 2 surfaces). Filter by stack: `--platform=ios|android|all`.
+All orchestration adapters default to `process.cwd()`; override with `--target=<path>`. Install every supported tool at once with `--all-tools`. Filter the skill set by stack with `--platform=ios|android|all`. Each adapter also writes the knowledge layer (rules + per-skill instructions) so single-tool installs are self-contained.
 
-### Tier 3 — Manual port
+### Tier 2 - Manual port
 
-**Windsurf**, **Cline**, **Zed AI**, **Continue.dev**, **JetBrains AI**, **Codeium**, **Tabnine**, **Amazon Q Developer** — closed/proprietary config, deprecated adapter, or different paradigm. Skill content can be copy-pasted into native rule formats; no automated installer ships today. PRs welcome.
+**JetBrains AI**, **Codeium**, **Tabnine**, **Amazon Q Developer** - closed/proprietary config or a different paradigm with no agent/command file format we can target. Skill content can be copy-pasted into native rule formats; no automated installer ships today. PRs welcome.
 
 ### Uninstall (token-preserving, all tiers)
 
@@ -233,16 +234,16 @@ Personal access tokens stored in macOS Keychain / Windows Credential Manager / L
 ## Pipeline Phases
 
 ```
-Phase 0: Init      — Project selection, branch setup, identity, worktree
-Phase 1: Analysis  — Stack detection, codebase exploration
-Phase 2: Planning  — Task decomposition, architecture review, user approval
-Phase 3: Dev       — TDD cycle: test → code → build
-Phase 4: Review    — Deterministic gates + parallel review + Opus triage
+Phase 0: Init - Project selection, branch setup, identity, worktree
+Phase 1: Analysis - Stack detection, codebase exploration
+Phase 2: Planning - Task decomposition, architecture review, user approval
+Phase 3: Dev - TDD cycle: test → code → build
+Phase 4: Review - Deterministic gates + parallel review + Opus triage
                      • Claude Code → Opus + Sonnet (2 paralel)
                      • Copilot CLI → GPT-5.4 + Opus + Sonnet (3 paralel)
-Phase 5: Test      — Optional manual testing + MCP device audits (on-demand)
-Phase 6: Commit    — Pre-commit local checkout prompt, git commit, push, PR creation
-Phase 7: Report   — External: Jira comment · Wiki + Figma screenshots · Confluence
+Phase 5: Test - Optional manual testing + MCP device audits (on-demand)
+Phase 6: Commit - Pre-commit local checkout prompt, git commit, push, PR creation
+Phase 7: Report - External: Jira comment · Wiki + Figma screenshots · Confluence
                      Internal: Log · Knowledge + memory capture
 ```
 
@@ -423,7 +424,7 @@ flowchart TD
 flowchart TD
     CC["<b>Claude Code</b><br/>(Source of Truth)<br/><br/>~/.claude/commands/<br/>~/.claude/agents/<br/>~/.claude/scripts/"]
 
-    CC -->|"instructions + 192 skills + scripts"| COP["<b>Copilot CLI</b><br/>~/.copilot/skills/<br/>~/.copilot/scripts/<br/>copilot-instructions.md"]
+    CC -->|"instructions + 206 skills + scripts"| COP["<b>Copilot CLI</b><br/>~/.copilot/skills/<br/>~/.copilot/scripts/<br/>copilot-instructions.md"]
     CC -->|"genericized pipeline/"| REPO["<b>Pipeline Repo</b><br/>@mmerterden/<br/>multi-agent-pipeline"]
     CC -.->|"optional"| WEB["<b>Website</b><br/>(your docs site)"]
     CC -.->|"optional"| RC["<b>Remote Control</b><br/>(your dashboard)"]
@@ -519,10 +520,10 @@ Stack is auto-detected. Build commands, test runners, lint tools, and review foc
 | ---- | ----------- | ----------- | ----------- |
 | Normal | `/multi-agent "task"` | `multi-agent "task"` | Full 8 phases with CLI-aware parallel review (Claude: 2-model · Copilot: 3-model) |
 | Fast | `/multi-agent:dev "task"` | `multi-agent-dev "task"` | Init → Dev(Opus) → Commit → Report |
-| Local | `/multi-agent "task" --local` | `multi-agent "task" --local` | No worktree — works on local branch |
+| Local | `/multi-agent "task" --local` | `multi-agent "task" --local` | No worktree - works on local branch |
 | Autopilot | `/multi-agent:autopilot "task"` | `multi-agent-autopilot "task"` | Skip confirmations, auto commit/PR |
 | Fastest | `/multi-agent:dev-autopilot "task"` | `multi-agent-dev-autopilot "task"` | Zero interaction |
-| Test | `/multi-agent:test` | `multi-agent-test` | UI Bug Hunter — visual + accessibility |
+| Test | `/multi-agent:test` | `multi-agent-test` | UI Bug Hunter - visual + accessibility |
 | Channels | `/multi-agent:channels <target>` | `multi-agent-channels <target>` | Post report to Jira / Confluence / Wiki / PR (multi-select, humanizer pass, reviewer-preserving) |
 | Stack | `/multi-agent:stack ios` | `multi-agent-stack ios` | Manually swap skill set per platform |
 | Language | `/multi-agent:language [prompt\|output] <en\|tr>` | `multi-agent-language [prompt\|output] <en\|tr>` | Toggle `promptLanguage` (interactive prompts) and/or `outputLanguage` (assistant explanations). External payloads stay English. |
@@ -544,20 +545,20 @@ Automated visual testing and compliance audits. Requires the mobile MCP server.
 
 ### How Audit Tools Work
 
-All audits run via **direct Bash commands** — no MCP server dependency. Pipeline uses `xcrun simctl`, `adb`, `codesign`, `aapt2` etc. natively.
+All audits run via **direct Bash commands** - no MCP server dependency. Pipeline uses `xcrun simctl`, `adb`, `codesign`, `aapt2` etc. natively.
 
 | Audit                 | What It Does                                           | Command                      | When                    |
 | --------------------- | ------------------------------------------------------ | ---------------------------- | ----------------------- |
-| iOS Accessibility     | Missing labels, small tap targets                      | `swift ui-tree-dumper.swift` | Phase 5 — user requests |
-| Android Accessibility | Missing contentDescription, small touch targets        | `adb shell uiautomator dump` | Phase 5 — user requests |
-| iOS Biometric         | Face ID / Touch ID success/failure                     | `xcrun simctl keychain`      | Phase 5 — auth flow     |
-| Android Launch Time   | Cold start time (ms)                                   | `adb shell am start -W`      | Phase 5 — performance   |
-| iOS Archive           | App Store compliance: signing, debug tools, privacy    | `codesign`, `plutil`, `nm`   | Phase 6 — release       |
-| Android APK           | Play Store compliance: target SDK, debuggable, signing | `aapt2`, `apksigner`         | Phase 6 — release       |
+| iOS Accessibility     | Missing labels, small tap targets                      | `swift ui-tree-dumper.swift` | Phase 5 - user requests |
+| Android Accessibility | Missing contentDescription, small touch targets        | `adb shell uiautomator dump` | Phase 5 - user requests |
+| iOS Biometric         | Face ID / Touch ID success/failure                     | `xcrun simctl keychain`      | Phase 5 - auth flow     |
+| Android Launch Time   | Cold start time (ms)                                   | `adb shell am start -W`      | Phase 5 - performance   |
+| iOS Archive           | App Store compliance: signing, debug tools, privacy    | `codesign`, `plutil`, `nm`   | Phase 6 - release       |
+| Android APK           | Play Store compliance: target SDK, debuggable, signing | `aapt2`, `apksigner`         | Phase 6 - release       |
 
-**Important**: Audits are **on-demand** — triggered by user, not automatic. Phase 4 does code-level accessibility review (free, no device needed). Phase 5/6 do device-level audits only when requested.
+**Important**: Audits are **on-demand** - triggered by user, not automatic. Phase 4 does code-level accessibility review (free, no device needed). Phase 5/6 do device-level audits only when requested.
 
-**No external dependencies** — only standard Xcode CLI tools (iOS) and Android SDK (Android). Platform guides include **compliance rules** that map 1:1 to audit checks — follow the guide, pass the audit.
+**No external dependencies** - only standard Xcode CLI tools (iOS) and Android SDK (Android). Platform guides include **compliance rules** that map 1:1 to audit checks - follow the guide, pass the audit.
 
 ## Stack Swap
 
@@ -589,7 +590,7 @@ multi-agent-setup                           # Copilot CLI
 # -> Git identity (name + email)
 # -> Keychain token scan + mapping
 
-# That's it! Pipeline works standalone — no additional dependencies needed.
+# That's it! Pipeline works standalone - no additional dependencies needed.
 ```
 
 ## Hooks & Context Management
@@ -621,13 +622,12 @@ Run the full gate manually anytime, or wire the hook to run it on every `git pus
 # One-off check
 bash pipeline/scripts/pre-push-check.sh
 
-# Install as a git hook — runs automatically on `git push`
+# Install as a git hook - runs automatically on `git push`
 ln -sf ../../pipeline/scripts/pre-push-check.sh .git/hooks/pre-push
 chmod +x .git/hooks/pre-push
 ```
 
-Runs unit tests, smoke suites, eval fixtures, schema validation, and lint —
-the same gate that used to run in CI. Bypass only in emergencies with
+Runs unit tests, smoke suites, eval fixtures, schema validation, and lint - the same gate that used to run in CI. Bypass only in emergencies with
 `git push --no-verify`.
 
 ### Scripts
@@ -668,21 +668,21 @@ Runs **~1,300 assertions** across four layers:
 | Eval fixtures     | 11 adversarial cases + 2 golden tasks | Semantic regression for triage classification + full pipeline replay |
 | Schema validation | 13 schemas                     | Structural integrity of JSON schemas                     |
 
-CI runs locally via the `pre-push` git hook (see **Scripts** above) — no GitHub Actions. Enable the hook once per clone with `ln -sf ../../pipeline/scripts/pre-push-check.sh .git/hooks/pre-push`.
+CI runs locally via the `pre-push` git hook (see **Scripts** above) - no GitHub Actions. Enable the hook once per clone with `ln -sf ../../pipeline/scripts/pre-push-check.sh .git/hooks/pre-push`.
 
 ## Key Features
 
-Ten highlights — see [`docs/features.md`](docs/features.md) for the full catalog.
+Ten highlights - see [`docs/features.md`](docs/features.md) for the full catalog.
 
-1. **8-phase orchestration** with lazy-loaded phase specs — only pay token cost for the current phase.
-2. **CLI-aware parallel review + Opus triage** — Opus (security/architecture) + Sonnet (quality/correctness) run in parallel on Claude Code (2-model); Copilot CLI adds GPT-5.4 (edge cases/different perspective) for a 3-model set. A single Opus triage pass filters false-positives, rejects out-of-scope findings, and forwards only actionable items to Phase 3. Reviewer noise never auto-triggers rework.
+1. **8-phase orchestration** with lazy-loaded phase specs - only pay token cost for the current phase.
+2. **CLI-aware parallel review + Opus triage** - Opus (security/architecture) + Sonnet (quality/correctness) run in parallel on Claude Code (2-model); Copilot CLI adds GPT-5.4 (edge cases/different perspective) for a 3-model set. A single Opus triage pass filters false-positives, rejects out-of-scope findings, and forwards only actionable items to Phase 3. Reviewer noise never auto-triggers rework.
 3. **Bitbucket / GitHub PR automation** with default reviewers auto-injected, draft/ready prompt, body preservation (no literal `\n`, no HTML entities).
 4. **`channels` command** posts task reports to Jira / Confluence / Wiki / PR with multi-select channel + content. Humanizer pass per-channel, reviewer-preserving Bitbucket PR PUT. Phase 7 delegates; also invocable post-hoc for fixes made outside the pipeline.
-5. **Deterministic safety gates + pre-commit local-checkout prompt + runtime triage validator**: pre-commit secret scan (PreToolUse hook), xcodebuild lock queue, 3-iteration hard-kill on retry loops, "checkout locally and test before commit?" Phase 6 prompt, and a zero-dep Node validator that gates Phase 4 triage output on real exit codes — no longer just markdown guidance. Includes telemetry (metrics.jsonl + aggregator — GPT-5.4 reviewer metric emitted only on Copilot CLI) and a sync-parity script that catches Claude↔Copilot↔repo drift before it ships.
+5. **Deterministic safety gates + pre-commit local-checkout prompt + runtime triage validator**: pre-commit secret scan (PreToolUse hook), xcodebuild lock queue, 3-iteration hard-kill on retry loops, "checkout locally and test before commit?" Phase 6 prompt, and a zero-dep Node validator that gates Phase 4 triage output on real exit codes - no longer just markdown guidance. Includes telemetry (metrics.jsonl + aggregator - GPT-5.4 reviewer metric emitted only on Copilot CLI) and a sync-parity script that catches Claude↔Copilot↔repo drift before it ships.
 6. **Cross-session learning**: per-project knowledge base (architecture, patterns, gotchas) + user-level memory (feedback, project constraints, references).
 7. **Schema-validated state + smoke-tested contracts**: `schemas/*.schema.json` for `agent-state.json` and preferences; `scripts/smoke-channels-flow.sh` guards body-preservation + Bitbucket PUT contract + multi-channel dispatch.
-8. **Task Type Detection** — every task classified as component/bugfix/feature/refactor/chore at Phase 0 Step 9, used by every downstream phase for deterministic routing.
-9. **SubPhase progress tracking** for specialized workflows — component generation (figma-to-swiftui) reports nested SubPhases under the parent main phase instead of inflating the top-level phase count.
+8. **Task Type Detection** - every task classified as component/bugfix/feature/refactor/chore at Phase 0 Step 9, used by every downstream phase for deterministic routing.
+9. **SubPhase progress tracking** for specialized workflows - component generation (figma-to-swiftui) reports nested SubPhases under the parent main phase instead of inflating the top-level phase count.
 10. **Interactive launchers**: `multi-agent-jira` lists your open Jira issues; `multi-agent-issue` lists unassigned GitHub issues. Pick one → choose branch → choose mode (full/--dev) → autopilot? → pipeline starts. GitHub issues are auto-assigned on selection.
 
 ## What's Included
@@ -741,12 +741,11 @@ pipeline/
           log-format.md         Log file spec
   skills/
     shared/
-      core/                     22 orchestration skills (multi-agent-*) —
-                                pipeline-critical; changes here affect pipeline
+      core/                     22 orchestration skills (multi-agent-*) -                                 pipeline-critical; changes here affect pipeline
                                 behavior directly.
       external/                 127 iOS/Android/generic guidance skills imported
                                 from upstream (mirrors of third-party skill sets
-                                — SwiftUI, Compose, Kotlin, Swift, web, backend,
+ - SwiftUI, Compose, Kotlin, Swift, web, backend,
                                 CI/CD, HIG, etc.).
     figma-common/               Platform-agnostic Figma pipeline shared steps
     figma-ios/                  Figma → SwiftUI component generator (iOS)
@@ -822,8 +821,8 @@ The pipeline maintains consistency across multiple repositories and CLI targets:
 
 | Target             | What syncs                                           |
 | ------------------ | ---------------------------------------------------- |
-| **Claude Code**    | Source of truth — commands, agents, scripts          |
-| **Copilot CLI**    | Summary mirror + 192 unified skills + scripts |
+| **Claude Code**    | Source of truth - commands, agents, scripts          |
+| **Copilot CLI**    | Summary mirror + 206 unified skills + scripts |
 | **Pipeline Repo**  | Genericized open-source version (no personal data)   |
 | **Website**        | Version, phase/model counts, feature strings (EN+TR) |
 | **Remote Control** | Pipeline feature references                          |

package/docs/features.md

@@ -98,7 +98,7 @@ Multi-channel reporter — Phase 7 delegates to it, and it's also invocable post
 /multi-agent:channels https://jira.company/browse/PROJ-12345
 /multi-agent:channels #42 --channels pr            # PR only
 /multi-agent:channels --message "manual fix description"
-/multi-agent:channels DIJITAL-1234 --channels jira,confluence --content test
+/multi-agent:channels ABC-1234 --channels jira,confluence --content test
 ```
 
 Multi-select **channels** (Jira / Confluence / Wiki / PR description) × multi-select **content** (normal analysis / test scenarios / auto-diff summary / manual note). Each body runs through the humanizer skill per-channel. Bitbucket PR updates use the reviewer-preserving PUT pattern (title + description + reviewers + fromRef + toRef + version mandatory). Replaces the pre-v5.7 `enrich` command — all its capabilities (diff auto-summarize, manual mode, reviewer-preserving) are preserved; Confluence + Wiki are new.

package/index.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 
 /**
- * multi-agent-pipeline — 9-phase AI development pipeline
+ * multi-agent-pipeline — 8-phase AI development pipeline
  *
  * Supports: Claude Code, Copilot CLI
  * Install: npx @mmerterden/multi-agent-pipeline install
@@ -35,19 +35,16 @@ if (!command || command === "install") {
   await import(pathToFileURL(join(__dirname, "pipeline", "scripts", "uninstall.mjs")).href);
 } else if (command === "help") {
   console.log(`
-  multi-agent-pipeline — 9-phase AI development pipeline
+  multi-agent-pipeline — 8-phase AI development pipeline
 
   Install:
     npx @mmerterden/multi-agent-pipeline install              Install for Claude Code (default)
     npx @mmerterden/multi-agent-pipeline install --copilot    Install for Copilot CLI
     npx @mmerterden/multi-agent-pipeline install --all        Both Claude + Copilot
-    npx @mmerterden/multi-agent-pipeline install --cursor       Cursor adapter (.cursor/rules/*.mdc)
-    npx @mmerterden/multi-agent-pipeline install --windsurf     Windsurf adapter (.windsurfrules)
-    npx @mmerterden/multi-agent-pipeline install --cline        Cline adapter (.clinerules/)
+    npx @mmerterden/multi-agent-pipeline install --cursor       Cursor full orchestration (rules + subagents + /multi-agent + MCP)
     npx @mmerterden/multi-agent-pipeline install --copilot-chat GitHub Copilot Chat (.github/copilot-instructions.md)
-    npx @mmerterden/multi-agent-pipeline install --continue     Continue.dev (.continue/rules/)
-    npx @mmerterden/multi-agent-pipeline install --zed          Zed AI (.rules)
-    npx @mmerterden/multi-agent-pipeline install --all-tools    Every supported tool (Tier 1 + Tier 2 + Tier 3)
+    npx @mmerterden/multi-agent-pipeline install --antigravity  Antigravity full orchestration (.agent/ + AGENTS.md + MCP)
+    npx @mmerterden/multi-agent-pipeline install --all-tools    Every supported tool (Claude + Copilot + Cursor + Copilot Chat + Antigravity)
     npx @mmerterden/multi-agent-pipeline install --link       Use symlinks (saves tokens, dev mode)
 
   Uninstall (token-preserving — Keychain/Credential Manager untouched):
@@ -67,10 +64,11 @@ if (!command || command === "install") {
   After installation:
     Claude Code:  /multi-agent "MOBILE-123"
     Copilot CLI:  Describe your task naturally — pipeline instructions are loaded
-    Cursor / Windsurf / Cline: knowledge layer only (orchestration not portable)
+    Cursor / Antigravity / VS Code Copilot Chat: full orchestration (subagents + /multi-agent + MCP)
 
   More info: https://github.com/mmerterden/multi-agent-pipeline
   `);
 } else {
-  console.log(`Unknown command: ${command}. Run with 'help' for usage.`);
+  console.error(`Unknown command: ${command}. Run with 'help' for usage.`);
+  process.exit(1);
 }

package/install/_adapters.mjs

@@ -20,6 +20,8 @@ import { join } from "path";
  * @typedef {object} AdapterFlags
  * @property {boolean} cursor
  * @property {boolean} copilotChat
+ * @property {boolean} antigravity
+ * @property {boolean} codex
  */
 
 /**
@@ -27,7 +29,7 @@ import { join } from "path";
  * @returns {boolean}
  */
 export function anyAdapterRequested(flags) {
-  return flags.cursor || flags.copilotChat;
+  return flags.cursor || flags.copilotChat || flags.antigravity || flags.codex;
 }
 
 /**
@@ -55,6 +57,8 @@ export async function installAdapters(ctx) {
   const adapterTargets = [
     flags.cursor && "./pipeline/adapters/cursor.mjs",
     flags.copilotChat && "./pipeline/adapters/copilot-chat.mjs",
+    flags.antigravity && "./pipeline/adapters/antigravity.mjs",
+    flags.codex && "./pipeline/adapters/codex.mjs",
   ].filter(Boolean);
 
   for (const modPath of adapterTargets) {