@mmerterden/multi-agent-pipeline 10.6.0 → 10.7.0

package/CHANGELOG.md

@@ -14,6 +14,29 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ---
 
+## [10.7.0] - 2026-07-02
+
+The pipeline targets **Claude Code + Copilot CLI only**. The Cursor / Antigravity / VS Code Copilot Chat / OpenAI Codex CLI adapters are removed.
+
+### Removed
+
+- **All non-native adapters deleted.** `pipeline/adapters/` (Cursor, Antigravity,
+  Copilot Chat, Codex + orchestration variants), `pipeline/scripts/sync-adapters.mjs`,
+  `install/_adapters.mjs`, and the `smoke-adapters.sh` / `smoke-sync-adapters.sh` /
+  `smoke-shared-runtime.sh` smokes are gone.
+- Installer flags `--cursor` / `--copilot-chat` / `--antigravity` / `--codex` /
+  `--all-tools` removed; `install` now dispatches only Claude Code + Copilot CLI.
+- `multi-agent:sync` drops the Codex (Step 2a) and per-project adapter (Step 2b)
+  steps; the `--no-adapters` flag is retired. README, `phase-4-review`, and
+  `setup` adapter documentation removed.
+
+### Changed
+
+- **`multi-agent:update` prunes the retired global Codex adapter prompt**
+  (`~/.codex/prompts/multi-agent.md`). Per-project adapter files (`.cursor/`,
+  `.agent/`, `.github/copilot-instructions.md`) are left untouched — they live in
+  user repos; the `uninstall` command can still remove them selectively.
+
 ## [10.6.0] - 2026-07-02
 
 Fable 5 restored as the top model tier; `stack-swap` fully removed; setup gains a default stack step.

package/README.md

@@ -13,7 +13,7 @@
 |---|---|
 | Slash commands (colon-form `/multi-agent:*`) | 35 |
 | Copilot skills (dash-form `multi-agent-*`) | 35 |
-| Platforms (native: Claude Code, Copilot CLI · adapter: Cursor, Antigravity, VS Code Copilot Chat, Codex CLI) | 6 |
+| Platforms (Claude Code, Copilot CLI) | 2 |
 | Store-compliance skills (`apple-archive-compliance`, `google-play-compliance`) | 2 |
 | Figma skills (iOS + Android + Common) | 41 |
 | External skill catalog (`shared/external/`) | 143 |
@@ -25,7 +25,7 @@
 | Agent personas | 8 |
 | Pipeline phases | 8 |
 
-> 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`.
+> **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.
 
 > Security issue? See [SECURITY.md](./SECURITY.md). Please do not open public issues for vulnerabilities.
 
@@ -72,14 +72,6 @@ node install.js                         # Claude Code (default)
 node install.js --copilot               # Copilot CLI
 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 --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
 
@@ -87,7 +79,6 @@ node install.js --all --dry-run         # Preview every operation, write nothing
 node install.js                         # ...later...
 node pipeline/scripts/uninstall.mjs --dry-run     # preview what would be removed
 node pipeline/scripts/uninstall.mjs --yes         # remove from every installed target
-node pipeline/scripts/uninstall.mjs --cursor      # selective uninstall
 
 # Optional: expose the CLI globally as 'multi-agent-pipeline'
 npm link
@@ -109,11 +100,6 @@ Update later with `git pull && npm install` inside the clone. Pin to a specific
 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
 
@@ -194,42 +180,27 @@ Earlier README revisions referenced GitHub Packages with a Classic PAT and `~/.n
 
 ## Tool support
 
-> **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)
+The pipeline runs natively on **Claude Code** and **Copilot CLI** — the two CLIs it targets. Both install from the same `pipeline/skills/` source and get identical skill coverage.
 
 | Tool | Install Flag | How It Works |
 | --- | --- | --- |
 | **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]) |
-
-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.
-
-All install from the same `pipeline/skills/` source. Tree organization:
-
-- `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)
-
-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 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.
+Skill tree:
 
-### Tier 2 - Manual port
+- `pipeline/skills/shared/core/` - **orchestration skills** (`multi-agent-*` dash-form mirrors of the colon-form slash commands + compliance skills + orchestrator)
+- `pipeline/skills/shared/external/` - **curated iOS / Android / generic guidance skills** (SwiftUI, Jetpack Compose, testing, performance, security, etc.) — also distributed as versioned marketplace plugins in `mmerterden/multi-agent-plugins`
+- `pipeline/skills/figma-ios/` + `pipeline/skills/figma-android/` - **platform-specific Phase 3 sub-skills** (SwiftUI and Jetpack Compose code generation)
+- `pipeline/skills/figma-common/` - **platform-agnostic Figma helpers** (iterate, commit, wiki setup, MCP auth, performance harness)
 
-**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.
+Filter the skill set by stack with `--platform=ios|android|all`. Both CLIs also receive the same `pipeline/scripts/` tree so single-CLI installs stay self-contained.
 
-### Uninstall (token-preserving, all tiers)
+### Uninstall (token-preserving)
 
 ```bash
 npx @mmerterden/multi-agent-pipeline uninstall            # interactive, all installed targets
 npx @mmerterden/multi-agent-pipeline uninstall --dry-run  # preview, zero side effects
-npx @mmerterden/multi-agent-pipeline uninstall --cursor   # selective: only this tool
 ```
 
 Personal access tokens stored in macOS Keychain / Windows Credential Manager / Linux libsecret are **never touched** by the uninstaller. Smoke tests enforce this with a static check that fails the build if the script ever references a credential-store deletion API.

package/install/index.mjs

@@ -1,12 +1,9 @@
 /**
  * multi-agent-pipeline installer entry point.
  *
- * Parses flags, dispatches to per-target installers (Claude / Copilot /
- * adapter modules), prints summary, and fires opt-in telemetry.
- *
- * Behaviour MUST stay byte-equivalent to the pre-v8.0.0 monolithic install.js.
- * The smoke `smoke-install-layout.sh` test compares the produced filesystem
- * tree against a fixture before/after refactor.
+ * Parses flags, dispatches to the per-target installers (Claude Code / Copilot
+ * CLI), prints a summary, and fires opt-in telemetry. The pipeline runs natively
+ * on these two CLIs only.
  *
  * @module install/index
  */
@@ -16,7 +13,6 @@ import { fileURLToPath } from "url";
 
 import { installClaude } from "./claude.mjs";
 import { installCopilot } from "./copilot.mjs";
-import { anyAdapterRequested, installAdapters } from "./_adapters.mjs";
 import { setDryRun } from "./_common.mjs";
 import { sendInstallTelemetry } from "./_telemetry.mjs";
 
@@ -26,14 +22,7 @@ const PIPELINE_ROOT = dirname(__dirname);
 const PIPELINE_SRC = `${PIPELINE_ROOT}/pipeline`;
 
 /** Tool flags surfaced in CLI help. */
-const TOOL_FLAGS = [
-  "--claude",
-  "--copilot",
-  "--cursor",
-  "--copilot-chat",
-  "--antigravity",
-  "--codex",
-];
+const TOOL_FLAGS = ["--claude", "--copilot"];
 
 /**
  * @param {string[]} argv
@@ -55,7 +44,6 @@ export async function runInstall(argv) {
   const KNOWN_FLAGS = [
     ...TOOL_FLAGS,
     "--all",
-    "--all-tools",
     "--link",
     "--index-only",
     "--dry-run",
@@ -79,32 +67,12 @@ export async function runInstall(argv) {
   setDryRun(dryRun);
 
   const isExplicitlyTargeted =
-    flags.some((f) => TOOL_FLAGS.includes(f)) ||
-    flags.includes("--all") ||
-    flags.includes("--all-tools");
+    flags.some((f) => TOOL_FLAGS.includes(f)) || flags.includes("--all");
 
   const forClaude =
-    flags.includes("--claude") ||
-    flags.includes("--all") ||
-    flags.includes("--all-tools") ||
-    !isExplicitlyTargeted;
-
-  const forCopilot =
-    flags.includes("--copilot") ||
-    flags.includes("--all") ||
-    flags.includes("--all-tools");
-
-  const adapterFlags = {
-    cursor: flags.includes("--cursor") || flags.includes("--all-tools"),
-    copilotChat: flags.includes("--copilot-chat") || flags.includes("--all-tools"),
-    antigravity: flags.includes("--antigravity") || flags.includes("--all-tools"),
-    codex: flags.includes("--codex") || flags.includes("--all-tools"),
-  };
+    flags.includes("--claude") || flags.includes("--all") || !isExplicitlyTargeted;
 
-  const adapterTarget = (() => {
-    const raw = flags.find((f) => f.startsWith("--target="));
-    return raw ? raw.slice("--target=".length) : process.cwd();
-  })();
+  const forCopilot = flags.includes("--copilot") || flags.includes("--all");
 
   const useSymlinks = flags.includes("--link");
   const indexOnly = flags.includes("--index-only");
@@ -127,26 +95,6 @@ export async function runInstall(argv) {
   if (forClaude) installClaude(installerCtx);
   if (forCopilot) installCopilot(installerCtx);
 
-  if (anyAdapterRequested(adapterFlags)) {
-    if (dryRun) {
-      // Adapter installs merge marker-wrapped blocks into user-owned files;
-      // the preview lists the touched paths instead of threading dry-run
-      // through every adapter write site.
-      const planned = Object.entries(adapterFlags)
-        .filter(([, on]) => on)
-        .map(([name]) => name);
-      console.log(`  [dry-run] would install adapter(s) ${planned.join(", ")} into ${adapterTarget}`);
-    } else {
-      await installAdapters({
-        pipelineRoot: PIPELINE_ROOT,
-        pipelineSrc: PIPELINE_SRC,
-        target: adapterTarget,
-        platformFilter: platformFlag,
-        flags: adapterFlags,
-      });
-    }
-  }
-
   if (dryRun) {
     console.log("");
     console.log("  Dry-run complete — nothing was written. Re-run without --dry-run to install.");
@@ -154,12 +102,7 @@ export async function runInstall(argv) {
     return;
   }
 
-  printSummary({
-    forClaude,
-    forCopilot,
-    adapterFlags,
-    adapterTarget,
-  });
+  printSummary({ forClaude, forCopilot });
 
   // Fire-and-forget; install is already done.
   sendInstallTelemetry({ packageRoot: PIPELINE_ROOT, flags });
@@ -182,7 +125,7 @@ function parsePlatformFlag(flags) {
 }
 
 function printSummary(opts) {
-  const { forClaude, forCopilot, adapterFlags, adapterTarget } = opts;
+  const { forClaude, forCopilot } = opts;
 
   console.log("  Installation complete!");
   console.log("");
@@ -200,41 +143,6 @@ function printSummary(opts) {
     console.log("    Just describe your task — Copilot will follow the pipeline");
     console.log("");
   }
-  if (adapterFlags.cursor) {
-    console.log("  Cursor (full orchestration):");
-    console.log(`    Rules:    ${adapterTarget}/.cursor/rules/multi-agent-*.mdc`);
-    console.log(`    Subagents: ${adapterTarget}/.cursor/agents/ma-*.md (parallel review / explorer / triage)`);
-    console.log(`    Command:  ${adapterTarget}/.cursor/commands/multi-agent.md  (run /multi-agent)`);
-    console.log(`    MCP:      ${adapterTarget}/.cursor/mcp.json (dev-toolkit)`);
-    console.log("    Pickers degrade per refs/picker-contract.md; hard gates -> advisory rules + CI.");
-    console.log("");
-  }
-  if (adapterFlags.copilotChat) {
-    console.log("  GitHub Copilot Chat (VS Code, full orchestration):");
-    console.log(`    Instructions: ${adapterTarget}/.github/copilot-instructions.md + .github/instructions/multi-agent-*`);
-    console.log(`    Agents:   ${adapterTarget}/.github/agents/ma-*.agent.md (parallel review / explorer / triage)`);
-    console.log(`    Command:  ${adapterTarget}/.github/prompts/multi-agent.prompt.md  (run /multi-agent)`);
-    console.log(`    MCP:      ${adapterTarget}/.vscode/mcp.json (dev-toolkit)`);
-    console.log("    Confirmations use VS Code native approval dialogs (refs/picker-contract.md).");
-    console.log("");
-  }
-  if (adapterFlags.antigravity) {
-    console.log("  Antigravity (full orchestration):");
-    console.log(`    Rules:    ${adapterTarget}/.agent/rules/multi-agent-*.md`);
-    console.log(`    Workflow: ${adapterTarget}/.agent/workflows/multi-agent.md  (run /multi-agent)`);
-    console.log(`    Context:  ${adapterTarget}/AGENTS.md (skill index, marker-wrapped)`);
-    console.log(`    MCP:      ${adapterTarget}/.agent/mcp_config.json (dev-toolkit)`);
-    console.log("    Note: .agent/ paths community-documented; confirm against current Antigravity docs.");
-    console.log("");
-  }
-  if (adapterFlags.codex) {
-    console.log("  OpenAI Codex CLI (global, sequential orchestration):");
-    console.log("    Command:  ~/.codex/prompts/multi-agent.md  (run /multi-agent)");
-    console.log("    Context:  ~/.codex/AGENTS.md (skill index, marker-wrapped)");
-    console.log("    MCP:      ~/.codex/config.toml ([mcp_servers.dev-toolkit])");
-    console.log("    Note: prompts + MCP are global; Codex has no subagent fan-out (review runs sequential).");
-    console.log("");
-  }
 
   console.log("  For UI testing, also install the mobile MCP server:");
   console.log("    Add to your MCP config: npx @mmerterden/dev-toolkit-mcp");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "10.6.0",
+  "version": "10.7.0",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI, Cursor, Antigravity, and VS Code Copilot Chat. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Opus triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",

package/pipeline/commands/multi-agent/refs/phases/phase-4-review.md

@@ -187,17 +187,7 @@ Launch Agent instances **in parallel** using the shared `code-reviewer` subagent
 
 Each reviewer inherits the `code-reviewer` agent's focus areas (Security, Architecture, Quality, Performance) and output contract. The orchestrator overrides only the model and the stack-specific skill per-reviewer  -  no prompt duplication.
 
-**Model override wiring:** `code-reviewer.md` declares `preferredModel: opus`, so Reviewer 1 uses the persona default. Reviewer 2 (Copilot-only, `gpt-5.4`) and Reviewer 3 (`claude-sonnet-4.6`) set `PHASE_MODEL_OVERRIDE=<model>` before dispatch  -  the orchestrator exports `CLAUDE_CODE_SUBAGENT_MODEL` on Claude Code, or passes `--model` on Copilot CLI. Full precedence rule: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`. Opus dispatches are additionally subject to the fallback contract (`refs/features/model-fallback.md`): dispatch-error retry on `fallbackModel` (sonnet) and budget-ceiling downgrade.
-
-**Adapter platforms (Cursor / Antigravity / VS Code Copilot Chat) - reviewer set.** The native trio above is a Claude-Code / Copilot-CLI capability. On the adapter platforms the pipeline configures a 2-model cross-vendor review using the models each platform actually exposes (lineup in `pipeline/adapters/_base.mjs#REVIEWER_MODELS`; update as the platforms ship new versions):
-
-| Platform | Reviewer agents emitted | Models |
-|---|---|---|
-| Cursor | `ma-code-reviewer` + `ma-code-reviewer-x` (per-agent `model:` pinning is supported) | primary `inherit` (your selected model, usually Claude) + `gpt-5.5` |
-| VS Code Copilot Chat | `ma-code-reviewer` + `ma-code-reviewer-x` (frontmatter `model:` takes the picker label) | `Claude Opus 4.8` + `GPT-5.5` |
-| Antigravity | two parallel review agents (model chosen in the UI, not a file) | recommended `Gemini 3 Pro` + `Claude Opus 4.6`, set via the side-panel dropdown |
-
-So cross-vendor review IS restored on the adapter platforms (two different models on the code review), with the stack architect + `ma-security-auditor` as before. Two honest caveats remain vs the native hosts: (1) the exact model availability depends on the user's subscription (a pinned model the user lacks must be swapped in `REVIEWER_MODELS` / the dropdown), and (2) there is no `PreToolUse` hook, so gates are workflow-enforced not OS-blocked. Antigravity's models are dropdown-selected, so its pair is documented in the workflow rather than file-pinned.
+**Model override wiring:** `code-reviewer.md` declares `preferredModel: fable`, so Reviewer 1 uses the persona default (Fable 5). Reviewer 2 (Copilot-only, `gpt-5.4`) and Reviewer 3 (`claude-sonnet-4.6`) set `PHASE_MODEL_OVERRIDE=<model>` before dispatch  -  the orchestrator exports `CLAUDE_CODE_SUBAGENT_MODEL` on Claude Code, or passes `--model` on Copilot CLI. Full precedence rule: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`. Fable dispatches are subject to the fallback contract (`refs/features/model-fallback.md`): dispatch-error retry walks `fable -> opus -> sonnet` and budget-ceiling downgrade.
 
 **Stack-specific skills loaded per reviewer** (from Phase 1 `detectedStack`). On Claude Code, Reviewer 2 (GPT-5.4) is not dispatched  -  its skill column is ignored. On Copilot CLI all three columns are used.
 

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

@@ -799,7 +799,6 @@ Offer to make the secret scan a HARD pre-commit gate (a non-zero exit blocks the
 - Ask (picker): "Install the pre-commit secret-scan hook into `~/.claude/settings.json`?" Default Yes.
 - On Yes, deep-merge the template's `hooks.PreToolUse` into the user's `settings.json` (preserve any existing hooks; do not duplicate a matcher that already calls `pre-commit-check.sh`).
 - Honest note to show: this is the only deterministic gate that is OS-enforceable as a hook (it needs no run-specific arguments). The evidence / consensus / intent / learnings gates are invoked by the pipeline phases with per-run arguments, so they are enforced by the phase contract + the installed gate scripts, not by a hook.
-- On the adapter platforms (Cursor / Antigravity / VS Code Copilot Chat) there is no PreToolUse equivalent; the gate scripts live in `~/.multi-agent/` and are run as workflow steps. See `refs/picker-contract.md`.
 ### Step 9  -  Default stack plugin enablement
 
 Stack skills ship as versioned plugins in the `{owner}/multi-agent-plugins` marketplace. On first setup, wire the stack so the pipeline works out of the box.

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

@@ -1,6 +1,6 @@
 ---
-description: "One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, Cursor/Antigravity/Copilot Chat orchestration adapters, pipeline repo, website, and remote-control."
-argument-hint: "[release] [--no-adapters] [--platform=<macos|linux|windows>]"
+description: "One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, website, and remote-control."
+argument-hint: "[release] [--platform=<macos|linux|windows>]"
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, WebFetch
 ---
 
@@ -14,9 +14,8 @@ When invoked, it synchronizes all 7 targets in order. It detects what changed, u
 
 | Arg | Meaning |
 |---|---|
-| (none) | Full ecosystem sync: global targets (Claude, Copilot, Codex CLI, pipeline repo, website, remote-control) AND per-project adapter files (Cursor / Antigravity / Copilot Chat) in `prefs.global.projectsTouched[]`. Step 2b runs by default. Files are refreshed and a LOCAL commit is made per project; push stays the user's call (never automatic). |
+| (none) | Full ecosystem sync: Claude Code, Copilot CLI, pipeline repo, website, remote-control. |
 | `release` | Full sync + version bump + tag + npm publish + website deploy |
-| `--no-adapters` | Skip Step 2b (per-project adapter refresh). Use when you want only the global targets and must not touch any project repo (e.g. mid-feature-branch in a project). |
 | `--platform=<macos\|linux\|windows>` | Override automatic platform detection. For CI / cross-platform smoke. |
 | `"change description"` | Apply the description to every target at once |
 
@@ -27,8 +26,6 @@ When invoked, it synchronizes all 7 targets in order. It detects what changed, u
 | 0 | Figma source (deprecated) | `prefs.global.figmaSource.path` | skip (see memory `feedback_figma_source_deprecated`) |
 | 1 | Claude Code (source of truth) | `~/.claude/commands/multi-agent.md` + `~/.claude/commands/multi-agent/` + `~/.claude/agents/` + `~/.claude/scripts/` + `~/.claude/lib/` | source |
 | 2 | Copilot CLI | `~/.copilot/copilot-instructions.md` + `~/.copilot/skills/` | <- from Claude |
-| 2a | OpenAI Codex CLI (global, auto when `~/.codex` present) | `~/.codex/prompts/multi-agent.md` + `~/.codex/AGENTS.md` + `~/.codex/config.toml` | <- from Claude |
-| 2b | Cursor / Antigravity / Copilot Chat adapters (default; skip with `--no-adapters`) | `.cursor/rules/multi-agent.mdc`, `.github/copilot-instructions.md` in each project root | <- from Claude (template) |
 | 3 | multi-agent-pipeline repo | `~/multi-agent-pipeline/pipeline/` | <- from Claude (genericized) |
 | 4 | Website | `{owner}/{website-host}` | <- version + features |
 | 5 | Remote Control | `{owner}/remote-control` | <- pipeline references |
@@ -62,13 +59,6 @@ Step 0: FIGMA_SYNC  SKIP (deprecated  -  feedback_figma_source_deprecated)
 Step 1: PLATFORM    Detect macOS / Linux / Windows (Git Bash / WSL); export PLATFORM env
 Step 1.5: DETECT    Compare timestamps, find stale targets
 Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 34 sub-command skills)
-Step 2a: CODEX      Claude Code -> Codex CLI (global ~/.codex prompt + AGENTS.md + config.toml mcp)
-                     -  runs via `node pipeline/scripts/sync-adapters.mjs`, which fires the
-                        codex adapter ONCE (global) when `~/.codex` exists on this machine
-Step 2b: ADAPTERS   Cursor / Antigravity / Copilot Chat per-project rule files refresh
-                     -  RUNS BY DEFAULT: refreshes all projectsTouched[] targets + the pipeline repo
-                     -  `--no-adapters` skips this step entirely
-                     -  writes files + a LOCAL commit per project; push stays the user's call
 Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub, bash -n on all sh)
 Step 3c: PLUGINS    pipeline shared/external -> multi-agent-plugins marketplace (rebuild knowledge/,
                      bump changed plugins' patch version, commit + push the plugins repo)
@@ -134,65 +124,6 @@ If nothing is stale → report "All targets up to date" and stop.
 4. **Do not duplicate**  -  summary in Copilot, full spec in Claude. Keep this distinction.
 5. **Report**  -  show a short diff summary after sync
 
-## Step 2b  -  Per-Project Adapter Sync (default; skip with `--no-adapters`)
-
-Cursor and GitHub Copilot Chat do not have global skill directories like Claude Code (`~/.claude/`) or Copilot CLI (`~/.copilot/`). They consume the pipeline through a separate rule file per project. So for them, sync runs **per-project**, over every repo in `prefs.global.projectsTouched[]`.
-
-This step RUNS BY DEFAULT. The only side effect on a project repo is a refresh of the marker-wrapped adapter files plus a LOCAL commit; **push is never automatic** (see below), so sync cannot publish anything to a project's remote on its own. If you still need to keep a project repo completely untouched this run (e.g. you are mid-feature-branch and do not want even a local commit), pass `--no-adapters` to skip the step.
-
-| Adapter | Per-project files | Created by setup |
-|---|---|---|
-| Cursor | `.cursor/rules/multi-agent-*.mdc` + `.cursor/agents/ma-*.md` + `.cursor/commands/multi-agent.md` + `.cursor/mcp.json` | `multi-agent:setup` `--cursor` flag |
-| Antigravity | `.agent/rules/multi-agent-*.md` + `.agent/workflows/multi-agent.md` + `AGENTS.md` + `.agent/mcp_config.json` | `multi-agent:setup` `--antigravity` flag |
-| Copilot Chat (VS Code) | `.github/copilot-instructions.md` + `.github/agents/ma-*.agent.md` + `.github/prompts/multi-agent.prompt.md` + `.vscode/mcp.json` | `multi-agent:setup` `--copilot-chat` flag |
-
-These three are FULL-orchestration adapters (subagents/workflow + a `/multi-agent` command + the dev-toolkit MCP server), not just knowledge layers. Claude Code and Copilot CLI run the pipeline natively and are synced via the global flow above, not here.
-
-**OpenAI Codex CLI is NOT in this per-project table.** Codex is a global-config tool: its custom prompts and MCP servers live under `~/.codex/` and there is no per-project prompt directory. So Codex is synced in the GLOBAL flow (Step 2a), not per-project - `sync-adapters.mjs` fires the codex adapter once when `~/.codex` exists, writing `~/.codex/prompts/multi-agent.md`, `~/.codex/AGENTS.md`, and the `[mcp_servers.dev-toolkit]` block in `~/.codex/config.toml`. Installed via `multi-agent:setup` `--codex` flag (or `node install.js --codex`). Codex has no subagent fan-out, so the Phase 4 parallel review degrades to a sequential adversarial two-pass.
-
-### Flow
-
-Adapter sync orchestration goes through `pipeline/scripts/sync-adapters.mjs`  -  this script discovers per-project marker files (`.cursor*`, `.github/copilot-instructions.md`, `.agent`/`AGENTS.md`) and dispatches the matching adapter module (`pipeline/adapters/{cursor,copilot-chat,antigravity}.mjs`, each of which also emits its orchestration layer).
-
-1. Read the `prefs.global.projectsTouched[]` list (LRU, max 20 entries). Each entry is in the form `{ path, adapters: [...] }`: a record of which adapters are installed in that project.
-
-2. One command, all projects:
-   ```bash
-   node pipeline/scripts/sync-adapters.mjs --all
-   ```
-
-   For each target the script:
-   - If a `.cursor/` or `.cursorrules` marker is present, runs the **cursor** adapter → `pipeline/adapters/cursor.mjs install()` emits 174+ `.cursor/rules/multi-agent-*.mdc` files + one legacy `.cursorrules` digest.
-   - If a `.copilot/` or `.github/copilot-instructions.md` marker is present, runs the **copilot-chat** adapter.
-   - The pipeline repo itself (when `pipeline/` + `.git/` are present) always gets the cursor sync  -  the maintainer's canonical cursor consumer.
-   - If no marker is present, skips (`[skip]`).
-
-3. Dry-run view:
-   ```bash
-   node pipeline/scripts/sync-adapters.mjs --doctor
-   ```
-
-4. Single-project refresh (this repo or another target):
-   ```bash
-   node pipeline/scripts/sync-adapters.mjs --target=/path/to/repo --platform=ios
-   ```
-
-5. Commits are made separately per project (no cross-project commit):
-   ```bash
-   cd "$PROJ"
-   if ! git diff --cached --quiet; then
-     git commit -m "chore(adapter): sync multi-agent rules"
-     # NOTE: push is not automatic  -  it's the user's call. Sync only makes a local commit.
-   fi
-   ```
-
-4. Push is **not automatic**. Adapter sync leaves the commit local by default; the push decision for each project branch is the user's (whether the project branch is shared requires external knowledge).
-
-### Skip conditions
-
-- If `--no-adapters` is given, Step 2b is skipped entirely (the report says "skipped (--no-adapters)").
-- `prefs.global.projectsTouched[]` empty -> "no project adapter installs recorded  -  run `multi-agent:setup` in a project first". Step 2b is a no-op (nothing to refresh), not an error.
-- Project directory deleted -> the entry is subject to LRU pruning (sync does not error there).
 
 ---
 
@@ -340,7 +271,7 @@ When invoked with the `release` argument:
 
 ## Sub-Command Sync (Claude Code <-> Copilot CLI Skills)
 
-This step runs only on the Claude <-> Copilot axis. Cursor / Copilot Chat do not have a global command directory; they consume the pipeline through the per-project rule files in Step 2b, so they have no sub-command-level sync target.
+This runs on the Claude <-> Copilot axis — the two CLIs the pipeline supports natively.
 
 | Claude Code | Copilot CLI |
 |-------------|-------------|

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

@@ -51,6 +51,15 @@ Update the pipeline in one command. Existing preferences are preserved; only ski
    fi
    ```
 
+4c. **Prune retired adapter files** (Cursor / Antigravity / Codex / Copilot Chat were removed in v10.7.0 — the pipeline now targets Claude Code + Copilot CLI only):
+   ```bash
+   # Global Codex adapter prompt is safe to remove (no longer produced).
+   rm -f "$HOME/.codex/prompts/multi-agent.md"
+   echo "  -> pruned retired global Codex adapter prompt (if present)"
+   # Per-project adapter files (.cursor/, .agent/, .github/copilot-instructions.md)
+   # live in your repos and are left untouched — remove them manually if you like.
+   ```
+
 5. **Migrate preferences** (if there is an old schema):
    ```bash
    if [ -f "$HOME/.claude/scripts/migrate-prefs.mjs" ]; then

package/pipeline/scripts/smoke-cross-cli-behavior.sh

@@ -226,13 +226,6 @@ if grep -q '"reviewerCount"' "$TRSCHEMA" && grep -qi "Claude Code = 2, Copilot C
 else
   fail "triage consensus.reviewerCount does not document the 2/3 split"
 fi
-# The 3 adapter platforms must document their concrete reviewer set (a 2-model
-# cross-vendor review configured to each platform's available models).
-if grep -qi "Adapter platforms" "$P4" && grep -qi "cross-vendor" "$P4" && grep -q "ma-code-reviewer-x" "$P4"; then
-  pass "phase-4-review documents the adapter-platform cross-vendor reviewer set"
-else
-  fail "phase-4-review does not document the adapter-platform reviewer set"
-fi
 
 echo ""
 echo "══ cross-cli-behavior smoke: $PASS passed, $FAIL failed ══"

package/pipeline/scripts/smoke-install-layout.sh

@@ -4,7 +4,7 @@
 # the same on-disk output as the pre-v8.0.0 monolithic installer.
 #
 # v8.0.0 split install.js (1246 LOC) into ./install/{index,claude,copilot,
-# _common,_platform-filter,_telemetry,_adapters,_dev-only-files,
+# _common,_platform-filter,_telemetry,_dev-only-files,
 # _copilot-instructions}.mjs. The legacy install.js stayed as a thin shim
 # that imports install/index.mjs and calls runInstall(process.argv).
 #
@@ -66,7 +66,6 @@ expected_modules=(
   "_common.mjs"
   "_platform-filter.mjs"
   "_telemetry.mjs"
-  "_adapters.mjs"
   "_copilot-instructions.mjs"
   "_dev-only-files.mjs"
 )

package/install/_adapters.mjs

@@ -1,73 +0,0 @@
-/**
- * Third-party adapter dispatch.
- *
- * Each adapter (Cursor / Copilot Chat) is dynamically imported only when its
- * flag is set, so the default Claude / Copilot install path stays free of
- * adapter module load cost.
- *
- * As of v8.5.4 the previously-shipped Windsurf / Cline / Zed / Continue
- * adapters were removed — pipeline owner did not use them, and keeping them
- * green added smoke-test surface for no real benefit. Their files were
- * deleted from `pipeline/adapters/`. Reintroducing any of them is a one-file
- * add against `_base.mjs`.
- *
- * @module install/_adapters
- */
-
-import { join } from "path";
-
-/**
- * @typedef {object} AdapterFlags
- * @property {boolean} cursor
- * @property {boolean} copilotChat
- * @property {boolean} antigravity
- * @property {boolean} codex
- */
-
-/**
- * @param {AdapterFlags} flags
- * @returns {boolean}
- */
-export function anyAdapterRequested(flags) {
-  return flags.cursor || flags.copilotChat || flags.antigravity || flags.codex;
-}
-
-/**
- * @param {{
- *   pipelineRoot: string,
- *   pipelineSrc: string,
- *   target: string,
- *   platformFilter: "ios"|"android"|"all",
- *   flags: AdapterFlags,
- * }} ctx
- */
-export async function installAdapters(ctx) {
-  const { pipelineRoot, target, platformFilter, flags } = ctx;
-  console.log("");
-  console.log("  Third-party tool adapters (knowledge layer only)");
-  console.log(`  Target: ${target}`);
-  console.log("");
-
-  const adapterCommonOpts = {
-    pipelineSrc: ctx.pipelineSrc,
-    target,
-    platformFilter,
-  };
-
-  const adapterTargets = [
-    flags.cursor && "./pipeline/adapters/cursor.mjs",
-    flags.copilotChat && "./pipeline/adapters/copilot-chat.mjs",
-    flags.antigravity && "./pipeline/adapters/antigravity.mjs",
-    flags.codex && "./pipeline/adapters/codex.mjs",
-  ].filter(Boolean);
-
-  for (const modPath of adapterTargets) {
-    try {
-      const adapter = (await import(join(pipelineRoot, modPath))).default;
-      console.log(`  [${adapter.name}] Installing...`);
-      adapter.install(adapterCommonOpts);
-    } catch (e) {
-      console.error(`    -> Adapter load failed (${modPath}): ${e.message}`);
-    }
-  }
-}