@mmerterden/multi-agent-pipeline 15.11.0 → 15.12.2

package/CHANGELOG.md

@@ -16,6 +16,33 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [15.12.2] - 2026-08-22
+
+### Fixed
+- **`grep -P` is banned in shell, and the ban is enforced.** Unlike the other divergences the portability gate tracks, this one has no guarded form: BSD grep has no `-P` at all, so it exits 2 with "invalid option", and the `2>/dev/null` that nearly every check carries turns that error into an empty result, which reads as "found nothing". A check written that way passes on every input including the one it was meant to catch. Two gates in this repo did exactly that, were handed a file with the defect deliberately planted in it, and reported a clean tree. The scan covers every shell file under `scripts/` and `lib/`, not only the shipped ones, because the two that broke were smoke gates that never ship - and a gate that cannot fail is worse than no gate, since it is trusted. The check opens by proving its own detector fires on a planted invocation.
+- **Always-loaded context is back under budget with its designed headroom.** The fixed per-run load had reached 60000 of a 60000 ceiling, so the next edit to either tracked file would have broken the gate. The cause was the pattern the gate exists to catch: `core/multi-agent/SKILL.md` carried a full transcription of the Phase 0 contract, restating all eight steps that `refs/phases/phase-0-init.md` already defines, while its own text said the transcription "does not replace the contract, read the ref". Its citations into that ref had also drifted - `L221` now points at the token pre-check, not the branch picker it claimed. Every rule was verified present in the ref before cutting (per-repo branch picker, shared branch name with per-repo collision, per-repo identity, serial per-repo worktrees). What stays in the always-loaded file is the part that enforces rather than describes: the blocking exit gate and the credential-inventory rule. 2422 bytes reclaimed, load now 57576 of 60000. The ceiling was not raised.
+
+## [15.12.1] - 2026-08-22
+
+### Fixed
+- **The pre-push gate no longer runs inside the push.** Git opens the connection to the remote before the hook fires, so the six-minute chain 15.12.0 wired in idled that connection until the server dropped it: the first two attempts to push the rename died on a broken pipe with every gate green. The hook is now verify-only and instant - it checks a stamp keyed to the exact tree (HEAD plus a hash of the working tree) and refuses the push when there is none. `npm run gate` produces the stamp. Refusing is the point: no stamp means nothing has verified this tree, and the reason this file exists is that nothing else will.
+
+
+
+## [15.12.0] - 2026-08-22
+
+### Changed
+- **The companion MCP server is now `@mmerterden/multi-agent-toolkit-mcp` (v3.0.0), registered as `multi-agent-toolkit`.** The old name read as internal scaffolding; the server is standalone (three runtime dependencies, 83 tools, no coupling to any orchestrator) and the name now says which family it belongs to. The MCP tool namespace moves with it: every `mcp__dev-toolkit__*` reference across 24 files is now `mcp__multi-agent-toolkit__*`, because a host derives the tool prefix from the server name and the old prefix would have addressed a server that no longer answers.
+- **Existing registrations are migrated, not duplicated.** A host keys its registration by name, so a rename does not upgrade an entry in place: without a migration an install ends up with both `dev-toolkit` (pointing at the now-frozen 2.26.0) and `multi-agent-toolkit`, two servers advertising the same 83 tools with the host choosing between them. The installer removes the legacy entry before adding the new one, and `uninstall` clears both names - "removes the pipeline's footprint" has to mean the footprint it ever had.
+- Declared minimums move to `v3.0.0+`; 2.x only ever existed under the old package name.
+
+### Migration
+- `@mmerterden/dev-toolkit-mcp` stays published at 2.26.0 and is deprecated with a pointer. Nothing is unpublished, so a pinned consumer keeps resolving. The toolkit also keeps `dev-toolkit-mcp` as a second `bin` alias.
+- A hand-registered client that the pipeline installer does not manage needs `<cli> mcp remove dev-toolkit` once.
+
+### Fixed
+- **`pre-push-check.sh` ran three of the eleven gate steps.** It was missing both linters, three of the four evals, `validate-prefs` and `scorecard`, and drove the smoke suites through the bare `for f in smoke-*.sh` loop that `run-smokes.mjs` was written to replace - the loop that cannot tell a passing suite from one that exited 0 having asserted nothing. It now runs `npm test`, defined once in `package.json` so the hook cannot drift behind the chain, plus eslint and the personal-data scan. Because a full run takes about six minutes and git has already opened the connection to the remote by the time the hook fires, the verdict is cached against the exact tree that produced it (HEAD plus a hash of the working tree): re-pushing an unchanged tree is instant, one edited byte re-runs everything. Without that, the first push after the fix died on a broken pipe with every gate green. Verified by planting a defect that only the previously-missing steps catch: the old subset reported 434 unit tests passing and a clean tree; the new gate blocked the push. The hook's header also claimed the repo has no CI, which stopped being true some time ago.
+
 ## [15.11.0] - 2026-08-21
 
 ### Changed
@@ -1800,7 +1827,7 @@ Requires `@mmerterden/dev-toolkit-mcp` >= v2.9.0 for the App Store audit path.
 
 ### Fixed
 
-- **Every `mcp__dev_toolkit__*` reference is now `mcp__dev-toolkit__*`** (55
+- **Every `mcp__dev_toolkit__*` reference is now `mcp__multi-agent-toolkit__*`** (55
   lines across 10 files). A host composes MCP tool names as
   `mcp__<registered-server-name>__<tool>` and the server registers as
   `dev-toolkit`, so the snake_case form named tools that do not exist. The worst

package/README.md

@@ -12,7 +12,7 @@ An 8-phase AI development pipeline for **Claude Code**, **Copilot CLI** and **Co
 
 Runs natively on Claude Code, Copilot CLI and Codex CLI. macOS / Linux / Windows. Zero runtime dependencies.
 
-📐 **[Architecture diagrams](./docs/architecture.md)** - the 8-phase flow, operating modes, review/triage, Figma subphases, component layout. **[Ecosystem diagram](./docs/ecosystem.md)** - how this repo, the `multi-agent-plugins` marketplace and `dev-toolkit-mcp` compose.
+📐 **[Architecture diagrams](./docs/architecture.md)** - the 8-phase flow, operating modes, review/triage, Figma subphases, component layout. **[Ecosystem diagram](./docs/ecosystem.md)** - how this repo, the `multi-agent-plugins` marketplace and `multi-agent-toolkit-mcp` compose.
 
 ## Quick Start
 
@@ -63,7 +63,7 @@ One command runs 8 phases, with a gate between the risky ones:
 
 Under the hood: each task runs in its own **git worktree** (or the current branch with `:local`), commits use the **git identity routed from the repo's origin URL**, and **multi-repo** tasks get per-repo worktrees plus an integration build. Tokens stay in the OS keychain; nothing is committed or logged. `/multi-agent:review` can also review an existing GitHub/Bitbucket PR - per-finding inline comments anchored to `file:line` + an explicit Approve / Needs-Work state.
 
-The discipline behind all of this - bounded loops, evidence gates, token-budgeted phase docs, immutable tests, fresh-context handoffs - is catalogued in [docs/engineering.md](./docs/engineering.md). The full feature list lives in [docs/features.md](./docs/features.md). How this repo, the `multi-agent-plugins` marketplace, and the `dev-toolkit-mcp` server compose at install time and at run time is diagrammed in [docs/ecosystem.md](./docs/ecosystem.md).
+The discipline behind all of this - bounded loops, evidence gates, token-budgeted phase docs, immutable tests, fresh-context handoffs - is catalogued in [docs/engineering.md](./docs/engineering.md). The full feature list lives in [docs/features.md](./docs/features.md). How this repo, the `multi-agent-plugins` marketplace, and the `multi-agent-toolkit-mcp` server compose at install time and at run time is diagrammed in [docs/ecosystem.md](./docs/ecosystem.md).
 
 ## Modes
 
@@ -142,7 +142,7 @@ Runs on **macOS**, **Linux**, and **Windows** (Git Bash / WSL). Shell and creden
 | Repo | What it is |
 |---|---|
 | [`mmerterden/multi-agent-plugins`](https://github.com/mmerterden/multi-agent-plugins) | Marketplace of per-stack skill toolkits (iOS / Android / Frontend / Backend + common). `/multi-agent:stack` enables the matching plugin. |
-| [`mmerterden/dev-toolkit-mcp`](https://github.com/mmerterden/dev-toolkit-mcp) | MCP server for UI testing / simulator capture / xcodebuild - powers the Phase 5 UI Bug Hunter. Published on the public npm registry as [`@mmerterden/dev-toolkit-mcp`](https://www.npmjs.com/package/@mmerterden/dev-toolkit-mcp); the installer registers it with each CLI for you, so `npx` resolves it with no extra configuration. |
+| [`mmerterden/multi-agent-toolkit-mcp`](https://github.com/mmerterden/multi-agent-toolkit-mcp) | MCP server for UI testing / simulator capture / xcodebuild - powers the Phase 5 UI Bug Hunter. Published on the public npm registry as [`@mmerterden/multi-agent-toolkit-mcp`](https://www.npmjs.com/package/@mmerterden/multi-agent-toolkit-mcp); the installer registers it with each CLI for you, so `npx` resolves it with no extra configuration. |
 
 ## License
 

package/README.tr.md

@@ -12,7 +12,7 @@
 
 Claude Code, Copilot CLI ve Codex CLI üzerinde native çalışır. macOS / Linux / Windows. Sıfır runtime dependency.
 
-📐 **[Mimari diyagramları](./docs/architecture.md)** - 8 faz akışı, çalışma modları, review/triage, Figma subphase'leri, component yapısı. **[Ekosistem diyagramı](./docs/ecosystem.md)** - bu repo, `multi-agent-plugins` marketplace'i ve `dev-toolkit-mcp`'nin nasıl bir araya geldiği.
+📐 **[Mimari diyagramları](./docs/architecture.md)** - 8 faz akışı, çalışma modları, review/triage, Figma subphase'leri, component yapısı. **[Ekosistem diyagramı](./docs/ecosystem.md)** - bu repo, `multi-agent-plugins` marketplace'i ve `multi-agent-toolkit-mcp`'nin nasıl bir araya geldiği.
 
 ## Hızlı Başlangıç
 
@@ -63,7 +63,7 @@ Tek komut 8 fazı çalıştırır, riskli olanlar arasında bir kapı ile:
 
 Perde arkasında: her görev kendi **git worktree**'sinde çalışır (ya da `:local` ile mevcut branch'te), commit'ler **repo'nun origin URL'inden yönlendirilen git kimliğini** kullanır, ve **çoklu-repo** görevleri repo başına worktree artı bir integration build alır. Tokenlar OS keychain'de kalır; hiçbir şey commit edilmez ya da loglanmaz. `/multi-agent:review` mevcut bir GitHub/Bitbucket PR'ını da review edebilir - `file:line`'a bağlı bulgu-başına inline yorumlar + açık bir Approve / Needs-Work durumu.
 
-Bunun arkasındaki disiplin - sınırlı loop'lar, kanıt kapıları, token-bütçeli faz dokümanları, değişmez testler, taze-context handoff'lar - [docs/engineering.md](./docs/engineering.md)'de kataloglanmıştır. Tam özellik listesi [docs/features.md](./docs/features.md)'te. Bu repo, `multi-agent-plugins` marketplace'i ve `dev-toolkit-mcp` sunucusunun install zamanında ve run zamanında nasıl bir araya geldiği [docs/ecosystem.md](./docs/ecosystem.md)'de diyagramlanmıştır.
+Bunun arkasındaki disiplin - sınırlı loop'lar, kanıt kapıları, token-bütçeli faz dokümanları, değişmez testler, taze-context handoff'lar - [docs/engineering.md](./docs/engineering.md)'de kataloglanmıştır. Tam özellik listesi [docs/features.md](./docs/features.md)'te. Bu repo, `multi-agent-plugins` marketplace'i ve `multi-agent-toolkit-mcp` sunucusunun install zamanında ve run zamanında nasıl bir araya geldiği [docs/ecosystem.md](./docs/ecosystem.md)'de diyagramlanmıştır.
 
 ## Modlar
 
@@ -143,7 +143,7 @@ triage notu bunu belirtir.
 | Repo | Ne olduğu |
 |---|---|
 | [`mmerterden/multi-agent-plugins`](https://github.com/mmerterden/multi-agent-plugins) | Stack-başına skill toolkit'lerinin marketplace'i (iOS / Android / Frontend / Backend + common). `/multi-agent:stack` ilgili plugin'i etkinleştirir. |
-| [`mmerterden/dev-toolkit-mcp`](https://github.com/mmerterden/dev-toolkit-mcp) | UI testing / simulator capture / xcodebuild için MCP sunucusu - Phase 5 UI Bug Hunter'ı güçlendirir. Public npm registry'de [`@mmerterden/dev-toolkit-mcp`](https://www.npmjs.com/package/@mmerterden/dev-toolkit-mcp) olarak yayınlanır; installer her CLI'a onu senin için register eder, böylece `npx` ekstra konfigürasyon olmadan onu çözer. |
+| [`mmerterden/multi-agent-toolkit-mcp`](https://github.com/mmerterden/multi-agent-toolkit-mcp) | UI testing / simulator capture / xcodebuild için MCP sunucusu - Phase 5 UI Bug Hunter'ı güçlendirir. Public npm registry'de [`@mmerterden/multi-agent-toolkit-mcp`](https://www.npmjs.com/package/@mmerterden/multi-agent-toolkit-mcp) olarak yayınlanır; installer her CLI'a onu senin için register eder, böylece `npx` ekstra konfigürasyon olmadan onu çözer. |
 
 ## Lisans
 

package/install/_mcp-register.mjs

@@ -28,8 +28,20 @@ import { homedir } from "os";
 
 import { isDryRun } from "./_common.mjs";
 
-export const MCP_SERVER_NAME = "dev-toolkit";
-export const MCP_SERVER_PACKAGE = "@mmerterden/dev-toolkit-mcp";
+export const MCP_SERVER_NAME = "multi-agent-toolkit";
+export const MCP_SERVER_PACKAGE = "@mmerterden/multi-agent-toolkit-mcp";
+
+/**
+ * The name this server was registered under before v15.12.0.
+ *
+ * A host keys its registration by name, so renaming does NOT upgrade an entry in
+ * place: without this, an existing install ends up with both `dev-toolkit`
+ * (pointing at the old package, still resolvable, now frozen at 2.26.0) and
+ * `multi-agent-toolkit`. Two servers advertising the same 83 tools is worse than
+ * either alone - the host has to pick, and which one it picks is not something
+ * the pipeline controls. Registration removes the legacy entry first.
+ */
+export const LEGACY_MCP_SERVER_NAME = "dev-toolkit";
 
 /**
  * Per-host CLI invocation details.
@@ -44,7 +56,7 @@ export const MCP_SERVER_PACKAGE = "@mmerterden/dev-toolkit-mcp";
  * `scopeArgs`: options inserted before the server name. Only Claude Code needs
  * them, and it needs them badly: `claude mcp add` defaults to `--scope local`,
  * which binds the server to whichever directory the installer happened to run
- * in. Every other project would then see no dev-toolkit server at all. Codex
+ * in. Every other project would then see no multi-agent-toolkit server at all. Codex
  * writes `~/.codex/config.toml` and Copilot writes `~/.copilot/mcp-config.json`,
  * both already user-global, so both take no scope flag - passing one errors.
  */
@@ -129,6 +141,19 @@ export function registerMcpServer(host, label) {
     return { registered: false, reason: "opted out" };
   }
 
+  // Drop the pre-rename entry before adding the new one. Best-effort by design:
+  // "not registered" is the common case (a fresh install) and is not an error,
+  // and a host that cannot remove it is not a reason to skip the add.
+  try {
+    execFileSync(cli, ["mcp", "remove", ...scopeArgs, LEGACY_MCP_SERVER_NAME], {
+      stdio: "pipe",
+      timeout: 20_000,
+    });
+    console.log(`    -> ${label}: removed the legacy ${LEGACY_MCP_SERVER_NAME} registration`);
+  } catch {
+    /* not present, or the host declines - either way the add below is what matters */
+  }
+
   try {
     // Bounded: an installer must never hang on a child process. This is a local config
     // write and returns in milliseconds.

package/install/claude.mjs

@@ -103,7 +103,7 @@ export function installClaude(ctx) {
   configureSettings(home);
 
   // Claude Code was the last target still shipping skills without the tools those
-  // skills call. The dev-toolkit server backs design-check, every ios_* / android_*
+  // skills call. The multi-agent-toolkit server backs design-check, every ios_* / android_*
   // simulator call and the archive audits, and its absence is invisible until a run
   // reaches for one of them. `--scope user` is not optional here: `claude mcp add`
   // defaults to project scope, which would register the server only for whichever

package/install/codex.mjs

@@ -3,7 +3,7 @@
  *
  * Lays down `~/.codex/{skills/multi-agent,multi-agent-refs,agents,prompts,
  * scripts,lib,schemas}/` plus the managed block in `~/.codex/AGENTS.md`, and
- * registers the dev-toolkit MCP server through the `codex` CLI.
+ * registers the multi-agent-toolkit MCP server through the `codex` CLI.
  *
  * Shape note: this target follows the **Claude Code** thin-dispatcher layout,
  * not the Copilot CLI fan-out. Codex assembles every discovered skill's
@@ -542,7 +542,7 @@ function ensureSharedPreferences(home, pipelineSrc) {
 }
 
 /**
- * Register the dev-toolkit MCP server via the `codex` CLI.
+ * Register the multi-agent-toolkit MCP server via the `codex` CLI.
  *
  * Deliberately NOT a hand-written `[mcp_servers.*]` block in `config.toml`:
  * Codex owns that file (it writes `[marketplaces.*]` and `[plugins."x@y"]`

package/install/index.mjs

@@ -166,7 +166,7 @@ function printSummary(opts) {
     console.log("    /multi-agent setup          Configure tokens + git identity");
     console.log("    /multi-agent help           Full usage guide");
     console.log('    /multi-agent "MOBILE-123"   Start a task');
-    console.log("    /multi-agent test           UI Bug Hunter (requires dev-toolkit MCP)");
+    console.log("    /multi-agent test           UI Bug Hunter (requires multi-agent-toolkit MCP)");
     console.log("");
   }
   if (forCopilot) {
@@ -187,17 +187,17 @@ function printSummary(opts) {
   // All three register automatically now. Claude Code was the last to gain it, and
   // this summary kept telling users to do it by hand long enough that the
   // hand-registered entry became the only reason it worked on any given machine.
-  console.log("  For UI testing, the dev-toolkit MCP server is registered automatically:");
+  console.log("  For UI testing, the multi-agent-toolkit MCP server is registered automatically:");
   if (forClaude) {
     console.log(
-      "    Claude Code: claude mcp add --scope user dev-toolkit  (user scope, all projects)",
+      "    Claude Code: claude mcp add --scope user multi-agent-toolkit  (user scope, all projects)",
     );
   }
   if (forCopilot) {
-    console.log("    Copilot CLI: copilot mcp add dev-toolkit");
+    console.log("    Copilot CLI: copilot mcp add multi-agent-toolkit");
   }
   if (forCodex) {
-    console.log("    Codex CLI:   codex mcp add dev-toolkit");
+    console.log("    Codex CLI:   codex mcp add multi-agent-toolkit");
   }
   console.log(
     "    Skipped only when the host CLI is not on PATH - the command to run is printed above.",

package/install/templates/copilot-instructions.md

@@ -253,13 +253,13 @@ multi-agent-stack [ios|android|mobile|backend|frontend|fullstack|all]
 
 ## UI Bug Hunter
 
-For visual testing, use the dev-toolkit MCP server tools:
+For visual testing, use the multi-agent-toolkit MCP server tools:
 - ios_screenshot / android_screenshot - capture screen
 - ios_tap / android_tap - interact with UI
 - ios_set_appearance - toggle dark mode
 - ios_get_ui_tree / android_get_ui_tree - accessibility tree
 
-Requires: @mmerterden/dev-toolkit-mcp MCP server running
+Requires: @mmerterden/multi-agent-toolkit-mcp MCP server running
 
 ## Post-Development Integration Build (Multi-Repo) - required
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "15.11.0",
+  "version": "15.12.2",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",
@@ -24,7 +24,8 @@
     "lint:fix": "eslint . --fix",
     "format": "prettier --write \"**/*.{js,mjs,json,yml}\" --ignore-path .gitignore",
     "format:check": "prettier --check \"**/*.{js,mjs,json,yml}\" --ignore-path .gitignore",
-    "scorecard": "node pipeline/scripts/scorecard.mjs"
+    "scorecard": "node pipeline/scripts/scorecard.mjs",
+    "gate": "bash pipeline/scripts/pre-push-check.sh --run"
   },
   "keywords": [
     "multi-agent",

package/pipeline/commands/archive-guard.md

@@ -3,13 +3,13 @@ description: Scan an .xcarchive for Apple App Store Review compliance (18-rule d
 allowed-tools: Bash, Read, Glob
 ---
 
-Run the `ios_app_store_audit` MCP tool (shipped in `@mmerterden/dev-toolkit-mcp` ≥ v2.9.0)
+Run the `ios_app_store_audit` MCP tool (shipped in `@mmerterden/multi-agent-toolkit-mcp` ≥ v3.0.0)
 on an iOS archive. Backed by the same 18-rule catalog as `/multi-agent:test "store-ready"`
  -  this command is the lighter, post-hoc form (no platform-detect, no UI sweep).
 
 > **v8.4.0 migration note:** The standalone `~/ArchiveGuard/.build/release/archive-guard`
 > binary has been retired. The 18 rules live in
-> `dev-toolkit-mcp/tools/ios-app-store-audit/rules/` as a pure-Node port. Output JSON
+> `multi-agent-toolkit-mcp/tools/ios-app-store-audit/rules/` as a pure-Node port. Output JSON
 > shape is unchanged.
 
 ## Steps
@@ -21,7 +21,7 @@ on an iOS archive. Backed by the same 18-rule catalog as `/multi-agent:test "sto
 2. Ask user which archive to scan (or use the argument if provided: $ARGUMENTS).
 3. Run the scan  -  preferred mode is the native MCP tool call:
    ```
-   mcp__dev-toolkit__ios_app_store_audit({
+   mcp__multi-agent-toolkit__ios_app_store_audit({
      archive_path: "<archive_path>",
      rules: "all"          // "all" | "core" | "deep" | csv of ruleIDs
    })
@@ -29,15 +29,15 @@ on an iOS archive. Backed by the same 18-rule catalog as `/multi-agent:test "sto
 4. Fallback (plain shell / CI, no MCP host):
    ```
    node -e "
-   import('@mmerterden/dev-toolkit-mcp/tools/ios-app-store-audit/index.js').then(async m => {
+   import('@mmerterden/multi-agent-toolkit-mcp/tools/ios-app-store-audit/index.js').then(async m => {
      const r = await m.runAudit({ archivePath: '<archive_path>', rules: 'all' });
      console.log(JSON.stringify(r, null, 2));
    });
    "
    ```
-5. If `@mmerterden/dev-toolkit-mcp` is not installed, prompt the user:
+5. If `@mmerterden/multi-agent-toolkit-mcp` is not installed, prompt the user:
    ```
-   npm i -g @mmerterden/dev-toolkit-mcp
+   npm i -g @mmerterden/multi-agent-toolkit-mcp
    # or add it to your MCP config and reload the editor
    ```
 6. Summarize results  -  group by severity (`error` blockers, `warning` risks,

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

@@ -2,7 +2,7 @@
 description: "Mock-mode vs Figma design audit (iOS / Android, local-only). Pick repo + module, gate on mock support, enumerate every state driver into a countable target set, build Debug in a worktree, launch in mock mode, fetch Figma variants, compare each pixel + px-spacing + typography + color, and export a side-by-side annotated report (HTML + PDF + Confluence) to ~/DesignChecks. A coverage gate fails the run when a target is neither audited nor skipped with a reason."
 description-tr: "Mock-mod vs Figma tasarım denetimi (iOS / Android, yalnızca lokal). Repo + modül seç, mock desteğini geçitle, her state sürücüsünü sayılabilir bir hedef kümesine çıkar, worktree'de Debug derle, mock modda aç, Figma varyantlarını çek, her varyantı piksel + px-boşluk + tipografi + renk düzeyinde karşılaştır, yan yana annotasyonlu raporu (HTML + PDF + Confluence) ~/DesignChecks altına aktar. Bir hedef ne denetlenmiş ne de gerekçeyle atlanmışsa kapsam geçidi koşuyu başarısız sayar."
 argument-hint: '[scope]  -  empty = whole module; screen name; screen@variant; Figma URL(s); --resume'
-allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, AskUserQuestion, Skill, mcp__claude_ai_Figma__get_metadata, mcp__claude_ai_Figma__get_design_context, mcp__claude_ai_Figma__get_screenshot, mcp__dev-toolkit__design_mock_detect, mcp__dev-toolkit__design_scenario_inventory, mcp__dev-toolkit__design_mock_launch, mcp__dev-toolkit__design_ui_geometry, mcp__dev-toolkit__design_visual_compare, mcp__dev-toolkit__design_report, mcp__dev-toolkit__ios_list_devices, mcp__dev-toolkit__ios_boot_device, mcp__dev-toolkit__ios_launch_app, mcp__dev-toolkit__ios_terminate_app, mcp__dev-toolkit__ios_screenshot, mcp__dev-toolkit__ios_tap, mcp__dev-toolkit__ios_swipe, mcp__dev-toolkit__ios_type_text, mcp__dev-toolkit__ios_open_url, mcp__dev-toolkit__ios_get_ui_tree, mcp__dev-toolkit__ios_status_bar, mcp__dev-toolkit__ios_set_appearance, mcp__dev-toolkit__ios_set_locale, mcp__dev-toolkit__ios_xcodebuild, mcp__dev-toolkit__ios_xcresult, mcp__dev-toolkit__android_list_devices, mcp__dev-toolkit__android_screenshot, mcp__dev-toolkit__android_tap, mcp__dev-toolkit__android_swipe, mcp__dev-toolkit__android_type_text, mcp__dev-toolkit__android_open_url, mcp__dev-toolkit__android_launch_app, mcp__dev-toolkit__android_stop_app
+allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, AskUserQuestion, Skill, mcp__claude_ai_Figma__get_metadata, mcp__claude_ai_Figma__get_design_context, mcp__claude_ai_Figma__get_screenshot, mcp__multi-agent-toolkit__design_mock_detect, mcp__multi-agent-toolkit__design_scenario_inventory, mcp__multi-agent-toolkit__design_mock_launch, mcp__multi-agent-toolkit__design_ui_geometry, mcp__multi-agent-toolkit__design_visual_compare, mcp__multi-agent-toolkit__design_report, mcp__multi-agent-toolkit__ios_list_devices, mcp__multi-agent-toolkit__ios_boot_device, mcp__multi-agent-toolkit__ios_launch_app, mcp__multi-agent-toolkit__ios_terminate_app, mcp__multi-agent-toolkit__ios_screenshot, mcp__multi-agent-toolkit__ios_tap, mcp__multi-agent-toolkit__ios_swipe, mcp__multi-agent-toolkit__ios_type_text, mcp__multi-agent-toolkit__ios_open_url, mcp__multi-agent-toolkit__ios_get_ui_tree, mcp__multi-agent-toolkit__ios_status_bar, mcp__multi-agent-toolkit__ios_set_appearance, mcp__multi-agent-toolkit__ios_set_locale, mcp__multi-agent-toolkit__ios_xcodebuild, mcp__multi-agent-toolkit__ios_xcresult, mcp__multi-agent-toolkit__android_list_devices, mcp__multi-agent-toolkit__android_screenshot, mcp__multi-agent-toolkit__android_tap, mcp__multi-agent-toolkit__android_swipe, mcp__multi-agent-toolkit__android_type_text, mcp__multi-agent-toolkit__android_open_url, mcp__multi-agent-toolkit__android_launch_app, mcp__multi-agent-toolkit__android_stop_app
 ---
 
 # /multi-agent:design-check  -  Mock-mode vs Figma design audit
@@ -49,7 +49,7 @@ Phase 4: Report         → coverage gate + assemble + export HTML + PDF (+ Conf
 ## Requirements
 
 - **iOS**: Xcode + an available Simulator. **Android**: Android SDK + a running emulator / device.
-- **MCP**: the `dev-toolkit` MCP server (>= 2.8.0, for `design_scenario_inventory`, the `design_report` coverage gate, and `design_visual_compare` region alignment). The Figma MCP (`mcp__claude_ai_Figma__*`) must be authenticated - the user supplies the Figma URL.
+- **MCP**: the `multi-agent-toolkit` MCP server (>= 2.8.0, for `design_scenario_inventory`, the `design_report` coverage gate, and `design_visual_compare` region alignment). The Figma MCP (`mcp__claude_ai_Figma__*`) must be authenticated - the user supplies the Figma URL.
 - The selected module must support a **mock mode** (Phase 0 gate decides this). No mock support → the command halts.
 
 ## Phase Tracker Contract (mandatory)
@@ -77,11 +77,11 @@ Every Phase 0 / Phase 2 decision uses a native `AskUserQuestion` picker (numbere
 
    Assert both halves before continuing:
 
-   a. **Session** - `mcp__dev-toolkit__design_scenario_inventory` must be present in the tools available to you, and `mcp__dev-toolkit__design_visual_compare` must accept `live_region`. Absent → the session is bound to a stale process.
+   a. **Session** - `mcp__multi-agent-toolkit__design_scenario_inventory` must be present in the tools available to you, and `mcp__multi-agent-toolkit__design_visual_compare` must accept `live_region`. Absent → the session is bound to a stale process.
 
    b. **Disk** - probe the configured server directly, which reports what a fresh connection WOULD serve:
    ```bash
-   cd "$(python3 -c "import json,os;print(json.load(open(os.path.expanduser('~/.claude.json')))['mcpServers']['dev-toolkit']['args'][0].rsplit('/',1)[0])")" && \
+   cd "$(python3 -c "import json,os;print(json.load(open(os.path.expanduser('~/.claude.json')))['mcpServers']['multi-agent-toolkit']['args'][0].rsplit('/',1)[0])")" && \
    printf '%s\n%s\n' \
      '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"probe","version":"1"}}}' \
      '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
@@ -97,7 +97,7 @@ for l in sys.stdin:
    ```
 
    Branch on the two results:
-   - **disk OK, session missing the tool** → **HALT** and tell the user to reconnect: `/mcp` → `dev-toolkit` → Reconnect. Note the tool-count tell (a stale build advertises one fewer `design_*` tool). If a reconnect does not take, stale server processes may be lingering - `pgrep -f dev-toolkit-mcp/index.js` with `ps -o lstart=` shows their start times, and any that predate the code's mtime cannot serve the current tools.
+   - **disk OK, session missing the tool** → **HALT** and tell the user to reconnect: `/mcp` → `multi-agent-toolkit` → Reconnect. Note the tool-count tell (a stale build advertises one fewer `design_*` tool). If a reconnect does not take, stale server processes may be lingering - `pgrep -f multi-agent-toolkit-mcp/index.js` with `ps -o lstart=` shows their start times, and any that predate the code's mtime cannot serve the current tools.
    - **disk itself stale** (older version, or `inventory False`) → **HALT**: the checkout needs updating before a reconnect can help.
    - **both current** → continue.
 
@@ -108,7 +108,7 @@ for l in sys.stdin:
 3. **Platform detect** - `.xcodeproj` / `Package.swift` → iOS; `build.gradle*` → Android (same markers as `phase-0-init.md`). Persist `state.platform`.
 4. **MOCK FEASIBILITY GATE** - run against the selected module path:
    ```
-   mcp__dev-toolkit__design_mock_detect({ repo_path: "<module path>", platform: "<ios|android>",
+   mcp__multi-agent-toolkit__design_mock_detect({ repo_path: "<module path>", platform: "<ios|android>",
      extra_keys: <design-check-config mock.keys, if any> })
    ```
    Branch on `supported`:
@@ -117,7 +117,7 @@ for l in sys.stdin:
    - **`true`** → continue. Persist `state.designCheck.mock = <detect result>` (mechanism, activation, variantsHint, evidence).
 5. **SCENARIO INVENTORY (this is the audit's target set)**:
    ```
-   mcp__dev-toolkit__design_scenario_inventory({ repo_path: "<module path>", platform,
+   mcp__multi-agent-toolkit__design_scenario_inventory({ repo_path: "<module path>", platform,
      extra_launch_args: <config inventory.extraLaunchArgs>,
      extra_targets:     <config inventory.extraTargets>,
      ignore_targets:    <config inventory.ignoreTargets> })
@@ -140,13 +140,13 @@ Persist `agent-state.json` with `taskId`, `mode: "design-check"`, `platform`, `p
 ## Phase 1 - Build & Launch (mock)
 
 1. **Debug build** in the worktree (mock activation requires the Debug configuration):
-   - iOS: `mcp__dev-toolkit__ios_xcodebuild({ workspace|project, scheme, configuration: "Debug", action: "build", destination: "generic/platform=iOS Simulator" })`. Drill failures via `ios_xcresult`.
+   - iOS: `mcp__multi-agent-toolkit__ios_xcodebuild({ workspace|project, scheme, configuration: "Debug", action: "build", destination: "generic/platform=iOS Simulator" })`. Drill failures via `ios_xcresult`.
    - Android: `./gradlew :<module>:assembleDebug` (or `installDebug`) via Bash.
 2. **Boot device + install**: iOS `ios_list_devices` → `ios_boot_device` → install the built `.app` (`xcrun simctl install`). Android: ensure an emulator is running, `adb install -r <apk>`.
 3. **Deterministic state**: iOS `ios_status_bar({ preset: "clean" })` (09:41 / full battery); set a fixed appearance + locale so captures are stable across runs.
 4. **Launch in mock mode** using the activation from Phase 0:
    ```
-   mcp__dev-toolkit__design_mock_launch({ platform, bundle_id|package_name,
+   mcp__multi-agent-toolkit__design_mock_launch({ platform, bundle_id|package_name,
      launch_arg: state.designCheck.mock.activation.launchArg,      // iOS, e.g. "-debugMockMode YES"
      intent_extra: state.designCheck.mock.activation.intentExtra }) // Android
    ```
@@ -195,7 +195,7 @@ Per-target activation by `driver.type`:
 
 While a target's state is on screen, also capture the **sub-states reachable from it by tapping** - overlays, bottom sheets, modals, popups, inline errors, QR / share sheets. These cost no relaunch and belong to the target that exposed them; record them as additional captures under that target id (`<id>#<sub-label>`).
 
-For each capture: `ios_screenshot` (save PNG into the Phase 0 report dir) + `mcp__dev-toolkit__design_ui_geometry` (live boxes + screen size) → append to `state.designCheck.captured[]` with the target id and a human label. **Persist `state` and `run-state.json` after every capture**, so a run that dies mid-way resumes from where it stopped instead of starting over.
+For each capture: `ios_screenshot` (save PNG into the Phase 0 report dir) + `mcp__multi-agent-toolkit__design_ui_geometry` (live boxes + screen size) → append to `state.designCheck.captured[]` with the target id and a human label. **Persist `state` and `run-state.json` after every capture**, so a run that dies mid-way resumes from where it stopped instead of starting over.
 
 If a target cannot be reached, record it immediately as `{ id, reason }` in `state.designCheck.skipped[]` with a concrete reason ("scenario picker not present in this build", "needs a live PNR", "crashes on launch: <symbol>"). "Requires a scenario / prefix / launch-arg" is **not** a reason - that is a description of the work, and the work is this phase's job.
 
@@ -211,7 +211,7 @@ Collect ALL captures with no confident Figma match into a single list and ask th
 
 For each pair (matched + user-supplied), fetch `get_screenshot` + `get_design_context`, then:
    ```
-   mcp__dev-toolkit__design_visual_compare({
+   mcp__multi-agent-toolkit__design_visual_compare({
      figma_png, live_png, out_dir: "<report dir>/assets", label: "<variant>",
      figma_spec, live_geometry, figma_frame, live_screen,
      crop_top_live: <status-bar px>,       // strip device chrome the Figma frame lacks
@@ -222,7 +222,7 @@ For each pair (matched + user-supplied), fetch `get_screenshot` + `get_design_co
 **Bottom sheets, modals, and any partial overlay need region alignment.** Their Figma frame covers only the sheet, while the capture is the whole screen. Passing that pair as-is stretches a full screen onto a sheet-shaped frame, which misplaces every element inside the sheet and buries the real defect in noise. So for any capture whose frame is not full-screen:
 
    ```
-   mcp__dev-toolkit__design_visual_compare({ ...as above,
+   mcp__multi-agent-toolkit__design_visual_compare({ ...as above,
      live_region:     <the sheet container's {x,y,w,h} from design_ui_geometry>,
      expected_region: <where the design puts that sheet, same units> })
    ```
@@ -265,7 +265,7 @@ Before leaving this phase, compare `covered.length + skipped.length` against `sc
    Pass **ids**, not counts: the engine then names each unaccounted target in the report instead of printing an anonymous tally. `compareSize` and `liveSize` come straight from the `design_visual_compare` result.
 3. **Render + export**:
    ```
-   mcp__dev-toolkit__design_report({ report, out_dir: state.designCheck.reportDir,
+   mcp__multi-agent-toolkit__design_report({ report, out_dir: state.designCheck.reportDir,
      formats: ["html", "pdf"] + (confluence enabled ? ["confluence"] : []) })
    ```
    - HTML: self-contained (base64 images, CSS-positioned annotations over the live capture, stacked findings, fix prompt), with the coverage gate banner at the top.

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

@@ -124,7 +124,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:diff-explain   Map a Phase 4 triage finding back to specific diff lines
   /multi-agent:search         Cross-task log search with smart ranking; --semantic queries triage corpus
   /multi-agent:scan           Skill security scan against tiered pattern catalog
-  /multi-agent:refactor       Adapted best-practices + bug hunt + upstream-drift + dev-toolkit MCP research -> one plan, approval, dev + sync
+  /multi-agent:refactor       Best practices + bug hunt + upstream drift + toolkit MCP research -> one plan, approval, dev + sync
   /multi-agent:store-ready [repo] [--archive=|--ipa=|--aab=|--apk=] [--skip-sweep]  Pre-submission store readiness,
                               iOS + Android, local-only. Three symmetric gates per platform: static package audit,
                               the store's own validator, policy review vs repo source. Plus the running-app sweep.
@@ -139,7 +139,7 @@ Setup & Maintenance:
   /multi-agent:setup          First-run wizard  -  Keychain tokens + Git identity + language
   /multi-agent:language [en|tr]   Show or set outputLanguage (promptLanguage stays English)
   /multi-agent:stack [ids...]  Enable stack plugin(s); multi-select: ids together (ios backend) or no arg -> native picker (common always on)
-  /multi-agent:sync           Sync ecosystem (Claude Code + Copilot CLI + pipeline + website + dev-toolkit MCP)
+  /multi-agent:sync           Sync ecosystem (Claude Code + Copilot CLI + pipeline + website + toolkit MCP)
   /multi-agent:update         Pull latest pipeline + reinstall + run migrations
   /multi-agent:uninstall      Uninstall pipeline from every CLI (--all-data also clears settings + logs; Keychain tokens always intact, double confirm)
 
@@ -200,7 +200,7 @@ Manual Test (Phase 5 standalone  -  Xcode hint flow):
   /multi-agent:manual-test           Checkout task branch, print Xcode/SourceTree hints,
   /multi-agent:manual-test #N        wait for your "ok" / "fix: ..." verdict.
 
-Design Check (mock-mode vs Figma, local-only  -  powered by dev-toolkit-mcp design_* tools):
+Design Check (mock-mode vs Figma, local-only  -  powered by the toolkit MCP design_* tools):
 
   /multi-agent:design-check                Whole-module design audit: pick repo+module, gate on mock support,
                                            enumerate every state driver (launch args, scenario cases, scenario codes,
@@ -217,7 +217,7 @@ Design Check (mock-mode vs Figma, local-only  -  powered by dev-toolkit-mcp desi
   # "Requires a scenario / prefix / launch-arg" is not a reason; reaching those states is the run's job.
   # When a live screen has no confident Figma match, it SHOWS you the screenshot and asks for the node-id.
 
-  Drives the dev-toolkit-mcp design_* tool suite (+ ios_* / android_* device control).
+  Drives the toolkit design_* tools (+ ios_* / android_* device control).
 
 ------------------------------------------------------------
 
@@ -397,7 +397,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:diff-explain   Phase 4 triage bulgusunu diff satırlarına eşle
   /multi-agent:search         Task log'larında akıllı arama; --semantic triage corpus'unu sorgular
   /multi-agent:scan           Skill güvenlik taraması (tiered pattern catalog)
-  /multi-agent:refactor       Uyarlanmış best-practice + bug avı + upstream-drift + dev-toolkit MCP araştırması -> tek plan, onay, dev + sync
+  /multi-agent:refactor       Uyarlanmış best-practice + bug avı + upstream-drift + multi-agent-toolkit MCP araştırması -> tek plan, onay, dev + sync
   /multi-agent:store-ready [repo] [--archive=|--ipa=|--aab=|--apk=] [--skip-sweep]  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.
@@ -412,7 +412,7 @@ Setup & Maintenance:
   /multi-agent:setup              İlk kurulum sihirbazı  -  Keychain token + Git kimliği + dil
   /multi-agent:language [en|tr]   outputLanguage'ı göster veya ayarla (promptLanguage İngilizce kalır)
   /multi-agent:stack [ids...]     Stack plugin'lerini etkinleştir; çoklu seçim: id'ler yan yana (ios backend) ya da argümansız -> native picker (common hep açık)
-  /multi-agent:sync               Ekosistemi senkronize et (Claude Code + Copilot CLI + pipeline + website + dev-toolkit MCP)
+  /multi-agent:sync               Ekosistemi senkronize et (Claude Code + Copilot CLI + pipeline + website + multi-agent-toolkit MCP)
   /multi-agent:update             En son pipeline'ı çek + reinstall + migration çalıştır
   /multi-agent:uninstall          Pipeline'ı tüm CLI'lerden kaldır (--all-data ayar + logları da siler; Keychain token her zaman dokunulmaz, çift onay)
 
@@ -474,7 +474,7 @@ Manuel Test (Phase 5 standalone  -  Xcode hint akışı):
   /multi-agent:manual-test           Task branch'ine checkout, Xcode/SourceTree hint basar,
   /multi-agent:manual-test #N        "ok" / "fix: ..." yanıtını bekler.
 
-Design Check (mock-mod vs Figma, yalnızca lokal  -  dev-toolkit-mcp design_* tool'larıyla):
+Design Check (mock-mod vs Figma, yalnızca lokal  -  multi-agent-toolkit-mcp design_* tool'larıyla):
 
   /multi-agent:design-check                Tüm modül tasarım denetimi: repo+modül seç, mock desteğini geçitle,
                                            her state sürücüsünü (launch arg, senaryo case'leri, senaryo kodları,
@@ -491,7 +491,7 @@ Design Check (mock-mod vs Figma, yalnızca lokal  -  dev-toolkit-mcp design_* to
   # "Senaryo / prefix / launch-arg gerektirir" gerekçe değildir; o state'lere ulaşmak koşunun işidir.
   # Canlı ekranın Figma karşılığı kesin bulunamazsa SANA screenshot'ı gösterip node-id sorar.
 
-  dev-toolkit-mcp design_* tool takımını sürer (+ ios_* / android_* cihaz kontrolü).
+  multi-agent-toolkit-mcp design_* tool takımını sürer (+ ios_* / android_* cihaz kontrolü).
 
 ------------------------------------------------------------
 

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

@@ -1,6 +1,6 @@
 ---
-description: "Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research the companion dev-toolkit MCP server against current MCP practice, draft one plan, take approval, develop, then ask whether to sync. Use when asked to review a project for bugs, gaps or improvements, or to check whether derived skills have drifted from upstream."
-description-tr: "Projeyi analiz eder: uyarlanmış best-practice'leri çıkarır, gerçek bug + iyileştirme alanlarını avlar, türetilmiş skill'lerin upstream drift'ini kontrol eder, dev-toolkit MCP sunucusunu güncel MCP pratiklerine göre araştırır, tek plan taslağı çıkarır, onay alır, geliştirir, sonra sync isteyip istemediğini sorar."
+description: "Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research the companion multi-agent-toolkit MCP server against current MCP practice, draft one plan, take approval, develop, then ask whether to sync. Use when asked to review a project for bugs, gaps or improvements, or to check whether derived skills have drifted from upstream."
+description-tr: "Projeyi analiz eder: uyarlanmış best-practice'leri çıkarır, gerçek bug + iyileştirme alanlarını avlar, türetilmiş skill'lerin upstream drift'ini kontrol eder, multi-agent-toolkit MCP sunucusunu güncel MCP pratiklerine göre araştırır, tek plan taslağı çıkarır, onay alır, geliştirir, sonra sync isteyip istemediğini sorar."
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, AskUserQuestion, WebFetch, WebSearch
 ---
 
@@ -8,21 +8,21 @@ allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, AskUserQuestion, WebF
 
 **One command. Best-practices + Bug hunt + Upstream drift + Dev-toolkit -> Score -> Plan -> Approval -> Develop -> Sync.**
 
-Deep-analyses the current project, extracts the global best-practices worth adopting (adapted to our stack), hunts real bugs and improvement areas, checks whether any skills we derived from an upstream source have drifted, researches the companion dev-toolkit MCP server against current MCP practice, scores everything, drafts a single prioritized plan, asks the user for approval, applies the approved items, and asks about sync at the end.
+Deep-analyses the current project, extracts the global best-practices worth adopting (adapted to our stack), hunts real bugs and improvement areas, checks whether any skills we derived from an upstream source have drifted, researches the companion multi-agent-toolkit MCP server against current MCP practice, scores everything, drafts a single prioritized plan, asks the user for approval, applies the approved items, and asks about sync at the end.
 
-**Input**: $ARGUMENTS (optional  -  area to focus on: "security", "performance", "tests", "bugs", "best-practices", "drift", "dev-toolkit", etc.)
+**Input**: $ARGUMENTS (optional  -  area to focus on: "security", "performance", "tests", "bugs", "best-practices", "drift", "multi-agent-toolkit", etc.)
 
 ## Flow
 
 ```
 Step 0:  BEST-PRACTICES  Research the field, extract the best approaches, ADAPT them to our stack -> plan band A
 Step 0b: DRIFT           Check upstream-derived skills for updates we have not pulled -> plan band D
-Step 0c: DEV-TOOLKIT     Research current MCP practice + audit the companion dev-toolkit repo -> plan band E
+Step 0c: DEV-TOOLKIT     Research current MCP practice + audit the companion multi-agent-toolkit repo -> plan band E
 Step 0d: RUN-ERRORS      Read the local run-error ledger, rank recurring failures -> plan band F
 Step 1:  SCAN            Walk the project structure (files, LOC, dependencies, CI, tests)
 Step 2:  ANALYZE         10 categories + an explicit BUG HUNT (real defects, not just scores) -> plan bands B, C
 Step 3:  SCORE           Each category /10, overall /100
-Step 4:  PLAN            Merge bands A (best-practice) + B (bugs) + C (improvements) + D (drift) + E (dev-toolkit) + F (run-errors)
+Step 4:  PLAN            Merge bands A (best-practice) + B (bugs) + C (improvements) + D (drift) + E (multi-agent-toolkit) + F (run-errors)
 Step 5:  ASK             "Start the work?"  -  wait for user approval
 Step 6:  IMPLEMENT       Apply approved items one by one (lint, test, commit)
 Step 7:  VERIFY          Confirm every test + lint passes
@@ -34,7 +34,7 @@ Plan bands (all five feed the single Step 4 table):
 - **B - Bug**: real defects found in the code (correctness, security, data-loss, crashes).
 - **C - Improvement**: quality/perf/DX gaps surfaced by the 10-category analysis.
 - **D - Drift**: upstream updates to skills we derived from an external source.
-- **E - Dev-toolkit**: current-practice gaps in the companion dev-toolkit MCP server (the pipeline's device and browser hands), applied in that repo.
+- **E - Dev-toolkit**: current-practice gaps in the companion multi-agent-toolkit MCP server (the pipeline's device and browser hands), applied in that repo.
 - **F - Run-errors**: recurring real failures the pipeline actually hit across past runs, read from the local run-error ledger. These are lived evidence, not speculation - a failure that recurs across users or tasks is a prioritized improvement area.
 
 ## Step 0: BEST-PRACTICES  -  research the field, adapt to us
@@ -110,7 +110,7 @@ Procedure:
 
 ## Step 0c: DEV-TOOLKIT  -  current MCP practice for the companion toolkit
 
-The pipeline's hands on devices and browsers are MCP tools served by a companion repo (`dev-toolkit-mcp`): Phase 5 test, `manual-test`, `design-check` and `apple-archive-compliance` all call them, and several pipeline skills declare a minimum toolkit version (see `cross-cli-contract.md`). That repo therefore has to track the MCP field, not just its own README. This step researches what current practice is and audits the toolkit against it.
+The pipeline's hands on devices and browsers are MCP tools served by a companion repo (`multi-agent-toolkit-mcp`): Phase 5 test, `manual-test`, `design-check` and `apple-archive-compliance` all call them, and several pipeline skills declare a minimum toolkit version (see `cross-cli-contract.md`). That repo therefore has to track the MCP field, not just its own README. This step researches what current practice is and audits the toolkit against it.
 
 Full procedure  -  resolution (configuration first, never a hardcoded path; skip when nothing resolves or `enabled` is false), the 5 research axes, the audit command block, and the band-E output table + rules  -  lives in `$HOME/.claude/multi-agent-refs/refactor/dev-toolkit-research.md`. Read it before running this step.
 
@@ -219,7 +219,7 @@ Each category is scored out of 10. Output:
 
 ## Step 4: PLAN  -  one merged, prioritized table
 
-Merge all five bands into a single plan. Tag each row with its band (A best-practice / B bug / C improvement / D drift / E dev-toolkit) so the source is visible.
+Merge all five bands into a single plan. Tag each row with its band (A best-practice / B bug / C improvement / D drift / E multi-agent-toolkit) so the source is visible.
 
 ```
 | # | Priority | Band | Category | Item | Impact |
@@ -228,7 +228,7 @@ Merge all five bands into a single plan. Tag each row with its band (A best-prac
 | 2 | P0 | B | Tests | Fix nil-deref on empty response (src/y:42) | High |
 | 3 | P1 | A | CI/CD | Adopt matrix build (adapt: .github/workflows/ci.yml) | Medium |
 | 4 | P1 | D | Skills | Port upstream <plugin> 0.3.0 fixes into <localPath> | Medium |
-| 5 | P1 | E | Toolkit | Add read-only annotations to the dev-toolkit device tools | Medium |
+| 5 | P1 | E | Toolkit | Add read-only annotations to the multi-agent-toolkit device tools | Medium |
 | 6 | P2 | C | DevEx | Rename npm scripts for consistency | Low |
 ```
 
@@ -241,14 +241,14 @@ Priority levels:
 
 After showing the plan, ask:
 
-> "Found X items (P0: N, P1: M, P2: K) across bugs, best-practices, improvements, upstream drift, and dev-toolkit practice. Should I start the work?"
+> "Found X items (P0: N, P1: M, P2: K) across bugs, best-practices, improvements, upstream drift, and multi-agent-toolkit practice. Should I start the work?"
 
 Options:
 - "Yes, do all"
 - "Only P0"
 - "P0 + P1 only"
 - "Only bugs (band B)"
-- "Only the dev-toolkit (band E)"
+- "Only the multi-agent-toolkit (band E)"
 - (the user may pick specific items)
 
 **Never start the work without approval.**
@@ -305,7 +305,7 @@ If $ARGUMENTS is set, focus on that band/category only:
 | `bugs` | Bug hunt only (band B) |
 | `best-practices` | Field research + adapted plan only (band A) |
 | `drift` | Upstream derived-skill drift only (band D) |
-| `dev-toolkit` | Companion MCP toolkit research + audit only (band E) |
+| `multi-agent-toolkit` | Companion MCP toolkit research + audit only (band E) |
 | `security` | Security analysis only |
 | `tests` | Test coverage and quality only |
 | `performance` | Performance optimisation only |