@mmerterden/multi-agent-pipeline 12.6.0 → 12.7.0

package/docs/adr/0007-multi-tool-adapter-framework.md

@@ -1,15 +1,15 @@
 # 7. Multi-tool adapter framework + token-preserving uninstall
 
-**Status:** Superseded · 2026-07-02 (v10.7.0 removed all non-native adapters — the pipeline targets Claude Code + Copilot CLI only). Original acceptance: 2026-04-27 (v7.7.0 / v7.9.0). Kept as the historical record of why the adapter framework existed; install flags documented below no longer exist.
+**Status:** Superseded · 2026-07-02 (v10.7.0 removed all non-native adapters - the pipeline targets Claude Code + Copilot CLI only). Original acceptance: 2026-04-27 (v7.7.0 / v7.9.0). Kept as the historical record of why the adapter framework existed; install flags documented below no longer exist.
 
 ## Context
 
-Through v7.6, the pipeline shipped to two CLIs only: Claude Code and Copilot CLI. Both expose **subagent dispatch** — the ability for the orchestrator to fan out work to parallel sub-agents with their own model, prompt, and context. This is a hard prerequisite for the 8-phase pipeline (Phase 1 parallel exploration, Phase 4 multi-reviewer review, Phase 7 multi-channel reporting).
+Through v7.6, the pipeline shipped to two CLIs only: Claude Code and Copilot CLI. Both expose **subagent dispatch** - the ability for the orchestrator to fan out work to parallel sub-agents with their own model, prompt, and context. This is a hard prerequisite for the 8-phase pipeline (Phase 1 parallel exploration, Phase 4 multi-reviewer review, Phase 7 multi-channel reporting).
 
 Users started asking: "can it work with Cursor / Windsurf / Cline / Copilot Chat / Continue / Zed?" The honest answer is mixed:
 
 - **Subagent dispatch:** none of those tools expose it. So the orchestration layer cannot run there; only single-shot rules / instructions are loaded into a chat context.
-- **Knowledge layer:** the pipeline's value is split roughly 30/70 between orchestration and content. The 193 SKILL.md catalog + 12 rules describe how to write good Swift / Compose / TypeScript / etc. — that part is genuinely portable and would benefit users on tools where the orchestration can't run.
+- **Knowledge layer:** the pipeline's value is split roughly 30/70 between orchestration and content. The 193 SKILL.md catalog + 12 rules describe how to write good Swift / Compose / TypeScript / etc. - that part is genuinely portable and would benefit users on tools where the orchestration can't run.
 
 Three forces shaped this decision:
 
@@ -21,7 +21,7 @@ Three forces shaped this decision:
 
 We introduce a tiered support model and a uninstaller that's contractually forbidden from touching credential storage.
 
-### Tier 1 — Full pipeline (orchestration + knowledge)
+### Tier 1 - Full pipeline (orchestration + knowledge)
 
 Tools with subagent dispatch get the full 8-phase pipeline.
 
@@ -30,23 +30,23 @@ Tools with subagent dispatch get the full 8-phase pipeline.
 
 Both install slash commands / skills, agent personas, scripts, rules, and the full skills tree to `$HOME/.claude/` or `$HOME/.copilot/`.
 
-### Tier 2 — Knowledge layer only (v7.7.0)
+### Tier 2 - Knowledge layer only (v7.7.0)
 
 Tools without subagent dispatch but with a documented rules / instructions format. Pipeline orchestration commands are filtered out (they have no callable surface here); rules + skills catalog port natively to each tool's format.
 
-- **Cursor** (`--cursor`) — `.cursor/rules/multi-agent-*.mdc` + `.cursorrules` legacy fallback
-- **Windsurf** (`--windsurf`) — `.windsurfrules` (single file, marker-wrapped)
-- **Cline** (`--cline`) — `.clinerules/multi-agent-*.md` per-skill files
+- **Cursor** (`--cursor`) - `.cursor/rules/multi-agent-*.mdc` + `.cursorrules` legacy fallback
+- **Windsurf** (`--windsurf`) - `.windsurfrules` (single file, marker-wrapped)
+- **Cline** (`--cline`) - `.clinerules/multi-agent-*.md` per-skill files
 
-### Tier 3 — Knowledge layer (v7.9.0)
+### Tier 3 - Knowledge layer (v7.9.0)
 
 Three more tools with the same contract.
 
-- **GitHub Copilot Chat** (`--copilot-chat`) — `.github/copilot-instructions.md` marker-wrapped + `.github/instructions/multi-agent-*.instructions.md` per-skill
-- **Continue.dev** (`--continue`) — `.continue/rules/multi-agent-*.md` per-skill
-- **Zed AI** (`--zed`) — `.rules` single file, marker-wrapped
+- **GitHub Copilot Chat** (`--copilot-chat`) - `.github/copilot-instructions.md` marker-wrapped + `.github/instructions/multi-agent-*.instructions.md` per-skill
+- **Continue.dev** (`--continue`) - `.continue/rules/multi-agent-*.md` per-skill
+- **Zed AI** (`--zed`) - `.rules` single file, marker-wrapped
 
-### Tier 4 — Manual port
+### Tier 4 - Manual port
 
 Closed/proprietary tools (JetBrains AI, Codeium, Tabnine, Amazon Q Developer) get no automated installer. Skill content can be copy-pasted; PRs welcome.
 
@@ -54,11 +54,11 @@ Closed/proprietary tools (JetBrains AI, Codeium, Tabnine, Amazon Q Developer) ge
 
 All non-Tier-1 adapters share `pipeline/adapters/_base.mjs`:
 
-- **`parseFrontmatter`** / **`walkSkills`** — read SKILL.md, return name + frontmatter + body
-- **`inferGlobs`** — map skill name → glob pattern (`**/*.swift`, `**/*.{kt,kts}`, etc.) for tools that scope rules by file pattern
-- **`replaceManagedBlock`** / **`removeManagedBlock`** — read/write/strip the `<!-- multi-agent-pipeline:begin / end -->` marker pair inside a user-owned file. Lets us share rules files (`.windsurfrules`, `.rules`, `copilot-instructions.md`) with content the user already authored.
-- **`withoutOrchestrationSkills`** — filter `multi-agent-*` core skills (the orchestration namespace) from the export. They have no callable surface in Tier 2 / Tier 3 tools.
-- **`concatSkills`** — single-document concatenation for adapters that emit one rules file (Windsurf, Zed) instead of per-skill files.
+- **`parseFrontmatter`** / **`walkSkills`** - read SKILL.md, return name + frontmatter + body
+- **`inferGlobs`** - map skill name → glob pattern (`**/*.swift`, `**/*.{kt,kts}`, etc.) for tools that scope rules by file pattern
+- **`replaceManagedBlock`** / **`removeManagedBlock`** - read/write/strip the `<!-- multi-agent-pipeline:begin / end -->` marker pair inside a user-owned file. Lets us share rules files (`.windsurfrules`, `.rules`, `copilot-instructions.md`) with content the user already authored.
+- **`withoutOrchestrationSkills`** - filter `multi-agent-*` core skills (the orchestration namespace) from the export. They have no callable surface in Tier 2 / Tier 3 tools.
+- **`concatSkills`** - single-document concatenation for adapters that emit one rules file (Windsurf, Zed) instead of per-skill files.
 
 Each adapter exports a `{ name, install, uninstall }` contract. New adapters are mostly format-mapping over this base; adding a fourth would be ~150 LOC.
 
@@ -76,7 +76,7 @@ The contract is enforced statically by `smoke-delete-flow.sh` step 7:
 
 ```bash
 grep -qE "credential-store|delete-generic-password|cmdkey /delete|secret-tool clear" uninstall.mjs
-# fail varsa exit 1 — pattern eklenirse build kırılır
+# fail varsa exit 1 - pattern eklenirse build kırılır
 ```
 
 A future refactor that adds any credential-store deletion API to the uninstaller fails the build before it ships. Same posture for adapter modules: `smoke-adapters-tier3.sh` step 6 scans every Tier 3 adapter file.

package/docs/adr/0008-installer-modularization-and-secret-leak-defense.md

@@ -10,9 +10,9 @@ Two pressures collided during the v7.x line:
 
 1. **Installer monolith.** `install.js` reached 1246 LOC by v7.9.1. It mixed flag parsing, three platform installers (Claude / Copilot / six third-party adapters), telemetry, a dev-only file exclusion list, and a 200-line static generator for `copilot-instructions.md`. Reasoning about install behaviour required holding the whole file in your head; reviewers asked for documentation we could not produce because every change touched untyped, intertwined sections.
 
-2. **Secret leaks at deploy time.** During the v7.9.1 production deploy of `mmerterden.dev`, a `vercel deploy --token=vcp_…` invocation failed. The Vercel CLI printed the failed argv verbatim in its retry hint. That leaked the deploy token into the conversation transcript and forced a token rotation. A second incident in the same release window — `git -c user.email=…` overriding the repo-local config — pushed seven commits with the wrong author identity, which Vercel's contributor gate then blocked. Both classes of failure share a root cause: privileged values flowed through argv when the codebase had no audited boundary between provider tools and the orchestration layer.
+2. **Secret leaks at deploy time.** During the v7.9.1 production deploy of `mmerterden.dev`, a `vercel deploy --token=vcp_...` invocation failed. The Vercel CLI printed the failed argv verbatim in its retry hint. That leaked the deploy token into the conversation transcript and forced a token rotation. A second incident in the same release window - `git -c user.email=...` overriding the repo-local config - pushed seven commits with the wrong author identity, which Vercel's contributor gate then blocked. Both classes of failure share a root cause: privileged values flowed through argv when the codebase had no audited boundary between provider tools and the orchestration layer.
 
-We needed an architectural answer that prevented both classes of failure from recurring without expanding scope into "rewrite everything as TypeScript" — the project's zero-dependency philosophy (ADR-4) is a hard constraint.
+We needed an architectural answer that prevented both classes of failure from recurring without expanding scope into "rewrite everything as TypeScript" - the project's zero-dependency philosophy (ADR-4) is a hard constraint.
 
 ## Decision
 
@@ -22,18 +22,18 @@ The monolith splits into focused modules under `install/`:
 
 ```
 install/
-  index.mjs                  — entry point, flag parsing, dispatcher
-  claude.mjs                 — Claude Code installer
-  copilot.mjs                — Copilot CLI installer
-  _adapters.mjs              — third-party adapter dispatch
-  _common.mjs                — shared FS helpers (copyDir, ensureDir, …)
-  _platform-filter.mjs       — --platform=ios|android filter
-  _telemetry.mjs             — opt-in install telemetry
-  _copilot-instructions.mjs  — generator for ~/.copilot/copilot-instructions.md
-  _dev-only-files.mjs        — single source of truth for excluded files
+  index.mjs                  - entry point, flag parsing, dispatcher
+  claude.mjs                 - Claude Code installer
+  copilot.mjs                - Copilot CLI installer
+  _adapters.mjs              - third-party adapter dispatch
+  _common.mjs                - shared FS helpers (copyDir, ensureDir, ...)
+  _platform-filter.mjs       - --platform=ios|android filter
+  _telemetry.mjs             - opt-in install telemetry
+  _copilot-instructions.mjs  - generator for ~/.copilot/copilot-instructions.md
+  _dev-only-files.mjs        - single source of truth for excluded files
 ```
 
-`install.js` keeps its bin entry contract (24 lines, just `import { runInstall } from './install/index.mjs'; await runInstall(process.argv)`). Existing invocations — `npx … install --all`, the `package.json` `./install` export, every smoke test that runs `node install.js` — continue working without API changes. The package.json `files` array adds `install/**/*` so npm publish ships the new modules.
+`install.js` keeps its bin entry contract (24 lines, just `import { runInstall } from './install/index.mjs'; await runInstall(process.argv)`). Existing invocations - `npx ... install --all`, the `package.json` `./install` export, every smoke test that runs `node install.js` - continue working without API changes. The package.json `files` array adds `install/**/*` so npm publish ships the new modules.
 
 ### 2. Install layout is now a regression gate
 
@@ -50,8 +50,8 @@ Future refactors must keep this smoke green. Drift is detected before it ships,
 
 `pipeline/lib/vercel-deploy.sh` is the safe wrapper around the Vercel CLI. Three properties hold for every invocation:
 
-1. Tokens flow through `VERCEL_TOKEN` env var. The wrapper refuses to deploy if `--token=` appears anywhere in argv — that pattern was the v7.9.1 leak.
-2. Every stdout/stderr line is piped through a `redact_filter` sed pass that scrubs `--token=…`, `vcp_…`, `Bearer …`, `"token":"…"`, and `"VERCEL_TOKEN":"…"` shapes.
+1. Tokens flow through `VERCEL_TOKEN` env var. The wrapper refuses to deploy if `--token=` appears anywhere in argv - that pattern was the v7.9.1 leak.
+2. Every stdout/stderr line is piped through a `redact_filter` sed pass that scrubs `--token=...`, `vcp_...`, `Bearer ...`, `"token":"..."`, and `"VERCEL_TOKEN":"..."` shapes.
 3. Failed deploys exit with a clear marker line; the wrapper does not echo the original argv that the CLI printed in its retry hint.
 
 `pipeline/scripts/smoke-vercel-deploy-redact.sh` (12 assertions) is the regression gate for the redact filter. Each known leak shape has a fixture that must NOT survive redaction.
@@ -83,18 +83,18 @@ Schema validation proves each schema is well-formed. It does not prove that prod
 
 **What gets harder:**
 
-- Adding a brand-new install target. The contributor must touch `install/index.mjs` (flag wiring), create `install/<target>.mjs` (installer), update `smoke-install-layout.sh` (assertion). That's three files instead of one — but the boundaries are sharp and a smoke fails loudly if anything is missed.
+- Adding a brand-new install target. The contributor must touch `install/index.mjs` (flag wiring), create `install/<target>.mjs` (installer), update `smoke-install-layout.sh` (assertion). That's three files instead of one - but the boundaries are sharp and a smoke fails loudly if anything is missed.
 - Maintaining the static `_copilot-instructions.mjs` generator. The body still has to match the source-of-truth content in `pipeline/commands/multi-agent/`. Plan: in v9 we replace the static template with a generator that reads the actual phase files. For v8 the smoke `smoke-multi-repo-integration.sh` already greps the generator output for canonical strings, so drift is detected.
 
 **What we explicitly chose not to do:**
 
 - Migrate to TypeScript. The zero-dependency rule (ADR-4) still holds; TS would force a build step.
-- Move the install layout assertions into a unit test. Bash + `find` is the right tool — the assertions check a real filesystem tree, not pure logic.
+- Move the install layout assertions into a unit test. Bash + `find` is the right tool - the assertions check a real filesystem tree, not pure logic.
 - Auto-rotate Vercel tokens on detected leak. Rotation is a user decision; the wrapper just makes leaks harder, never silently mints replacements.
 
 ## References
 
 - `install/` directory split (this ADR)
-- `pipeline/lib/vercel-deploy.sh` — secret-leak defense wrapper
-- `pipeline/scripts/smoke-install-layout.sh`, `smoke-vercel-deploy-redact.sh`, `smoke-mode-dispatch-drift.sh`, `smoke-cross-phase-cohesion.sh` — regression gates
-- `feedback_vercel_cli_token_leak.md`, `feedback_git_author_repo_local.md`, `feedback_explicit_consent_for_push.md` — incident retrospectives that drove this work
+- `pipeline/lib/vercel-deploy.sh` - secret-leak defense wrapper
+- `pipeline/scripts/smoke-install-layout.sh`, `smoke-vercel-deploy-redact.sh`, `smoke-mode-dispatch-drift.sh`, `smoke-cross-phase-cohesion.sh` - regression gates
+- `feedback_vercel_cli_token_leak.md`, `feedback_git_author_repo_local.md`, `feedback_explicit_consent_for_push.md` - incident retrospectives that drove this work

package/docs/adr/README.md

@@ -30,5 +30,5 @@ Format: lightly adapted from [Michael Nygard's ADR template](https://cognitect.c
 
 ## Changing a Past Decision
 
-Don't rewrite ADRs — write a new one that supersedes the old. Set the old
+Don't rewrite ADRs - write a new one that supersedes the old. Set the old
 ADR's status to `Superseded by 00NN` and link both ways.

package/docs/best-practices.md

@@ -40,11 +40,11 @@ Applied in Phase 1 (Analysis):
 
 Applied in Phase 3:
 
-1. RED — Write the failing test
+1. RED - Write the failing test
 2. Verify it fails for the RIGHT reason
-3. GREEN — Write minimal code to pass
+3. GREEN - Write minimal code to pass
 4. Verify ALL tests pass
-5. REFACTOR — Clean up without changing behavior
+5. REFACTOR - Clean up without changing behavior
 
 ## 5. Deterministic Quality Gates (from claude-pipeline)
 

package/docs/features.md

@@ -1,6 +1,6 @@
-# Features — Full Reference
+# Features - Full Reference
 
-Comprehensive list of every feature the pipeline ships. The top-level `README.md` only highlights the 5–7 most important; this file is the complete catalog.
+Comprehensive list of every feature the pipeline ships. The top-level `README.md` only highlights the 5-7 most important; this file is the complete catalog.
 
 ## Core Pipeline
 
@@ -19,7 +19,7 @@ Phase 7: Report   External: Jira comment · Wiki + Figma screenshots · Confluen
                    Internal: agent-log.md + Quality & Metrics + knowledge + memory
 ```
 
-Each phase reads its own spec file under `pipeline/multi-agent-refs/phases/phase-N-*.md` — lazy-loaded so the orchestrator only pays the token cost for the phase it's currently in.
+Each phase reads its own spec file under `pipeline/multi-agent-refs/phases/phase-N-*.md` - lazy-loaded so the orchestrator only pays the token cost for the phase it's currently in.
 
 ### Modifier Flags (orthogonal, combinable)
 
@@ -27,7 +27,7 @@ Each phase reads its own spec file under `pipeline/multi-agent-refs/phases/phase
 | ----------- | ----------------------------------------------------------------------------------- |
 | `autopilot` | Skip all confirmation prompts; still fails safe on review blockers + build retries. |
 | `--dev`     | Strip to Init → Dev(Opus self-contained) → Commit → Report. No Phase 1/2/4/5.       |
-| `--local`   | No worktree — works directly in `$PROJECT_ROOT` on a local branch.                  |
+| `--local`   | No worktree - works directly in `$PROJECT_ROOT` on a local branch.                  |
 
 Compose freely: `--dev --local autopilot` = shortest, least-friction path.
 
@@ -45,7 +45,7 @@ Build commands, test runners, lint tools, and review focus areas all adapt to th
 
 ### Stack Selection (marketplace plugins)
 
-Stack skill sets ship as versioned plugins in the `multi-agent-plugins` marketplace. Selecting a stack enables the matching plugin(s) in the current repo's `.claude/settings.json` `enabledPlugins` — no skill copying, no session restart tricks, no directory shuffling. The `ai-common-engineering-toolkit` (accessibility audit, humanizer, Firebase) is always enabled alongside the stack plugin.
+Stack skill sets ship as versioned plugins in the `multi-agent-plugins` marketplace. Selecting a stack enables the matching plugin(s) in the current repo's `.claude/settings.json` `enabledPlugins` - no skill copying, no session restart tricks, no directory shuffling. The `ai-common-engineering-toolkit` (accessibility audit, humanizer, Firebase) is always enabled alongside the stack plugin.
 
 ```bash
 /multi-agent:stack ios         # ai-ios-engineering-toolkit (SwiftUI, Xcode, HIG)
@@ -73,7 +73,7 @@ Result persisted to `agent-state.taskType`:
 
 ### SubPhase Convention
 
-When a specialized skill takes over a main pipeline phase, progress is reported as SubPhases (e.g. `SubPhase 3.0: Init`, `SubPhase 3.1: Gather`). The top-level pipeline stays fixed at 8 phases (0-7) — specialized work slots into its parent phase without inflating the count.
+When a specialized skill takes over a main pipeline phase, progress is reported as SubPhases (e.g. `SubPhase 3.0: Init`, `SubPhase 3.1: Gather`). The top-level pipeline stays fixed at 8 phases (0-7) - specialized work slots into its parent phase without inflating the count.
 
 ## PR & Review Flow
 
@@ -92,7 +92,7 @@ Phase 6 asks `DRAFT or READY?` before creating the PR and persists the choice in
 
 ### `channels` Command
 
-Multi-channel reporter — Phase 7 delegates to it, and it's also invocable post-hoc for fixes closed outside the pipeline:
+Multi-channel reporter - Phase 7 delegates to it, and it's also invocable post-hoc for fixes closed outside the pipeline:
 
 ```bash
 /multi-agent:channels                              # current branch, current PR
@@ -102,7 +102,7 @@ Multi-channel reporter — Phase 7 delegates to it, and it's also invocable post
 /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 earlier `enrich` command — all its capabilities (diff auto-summarize, manual mode, reviewer-preserving) are preserved; Confluence + Wiki are new.
+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 earlier `enrich` command - all its capabilities (diff auto-summarize, manual mode, reviewer-preserving) are preserved; Confluence + Wiki are new.
 
 ### Body Preservation Contract (smoke-verified)
 
@@ -110,7 +110,7 @@ Every external-system body (PR description, Jira comment, GitHub issue) uses `jq
 
 ### Issue Safety
 
-Never auto-closes issues — uses `Ref: #N` / `Related: #N` / `See: PROJ-12345`, never `Closes` / `Fixes` / `Resolves`. Closure requires team review (configurable, typically 4 approvals).
+Never auto-closes issues - uses `Ref: #N` / `Related: #N` / `See: PROJ-12345`, never `Closes` / `Fixes` / `Resolves`. Closure requires team review (configurable, typically 4 approvals).
 
 ## Review Quality
 
@@ -119,13 +119,13 @@ Never auto-closes issues — uses `Ref: #N` / `Related: #N` / `See: PROJ-12345`,
 Cheap, objective checks run BEFORE any AI token is spent:
 
 1. Build (acquires xcodebuild lock, isolated DerivedData per worktree)
-2. Lint (SwiftLint / detekt / ruff / eslint — stack-dependent)
+2. Lint (SwiftLint / detekt / ruff / eslint - stack-dependent)
 3. Tests pass
 4. Secret scan
 
 If any gate fails, fix first. Don't waste AI tokens reviewing broken code.
 
-### CLI-Aware Parallel Review + Fable Triage (Phase 4 Steps 2–3)
+### CLI-Aware Parallel Review + Fable Triage (Phase 4 Steps 2-3)
 
 | Reviewer   | Model               | Focus                             | Where it runs        |
 | ---------- | ------------------- | --------------------------------- | -------------------- |
@@ -133,7 +133,7 @@ If any gate fails, fix first. Don't waste AI tokens reviewing broken code.
 | Reviewer 2 | `gpt-5.4`           | Edge cases, different perspective | **Copilot CLI only** |
 | Reviewer 3 | `claude-sonnet-4-6` | Quality + correctness + naming    | Both CLIs            |
 
-The reviewer set is **CLI-aware**: Claude Code dispatches 2 reviewers in parallel (Fable + Sonnet — GPT-5.4 is not available there); Copilot CLI dispatches all 3. Each returns structured JSON for deterministic aggregation. Cross-model diversity catches blind spots that any single model family would miss.
+The reviewer set is **CLI-aware**: Claude Code dispatches 2 reviewers in parallel (Fable + Sonnet - GPT-5.4 is not available there); Copilot CLI dispatches all 3. Each returns structured JSON for deterministic aggregation. Cross-model diversity catches blind spots that any single model family would miss.
 
 **Fable Triage** (Phase 4 Step 3, Opus on Copilot CLI): Evaluates merged raw findings against task scope. Classifies each as `accepted` (fix now), `deferred` (out of scope, log for later), or `rejected` (false positive / noise). Only triage-accepted blocking items loop back to Phase 3.
 
@@ -143,10 +143,10 @@ After triage returns, output is validated by `validate-triage.mjs`:
 
 | Exit  | Meaning                                                      |
 | ----- | ------------------------------------------------------------ |
-| **0** | Valid and clean — act on triage output                       |
-| **1** | Invalid structure — retry once, then fallback                |
-| **2** | Over-rejection guard tripped — pause for human               |
-| **3** | Contradiction auto-corrected — proceed with corrected output |
+| **0** | Valid and clean - act on triage output                       |
+| **1** | Invalid structure - retry once, then fallback                |
+| **2** | Over-rejection guard tripped - pause for human               |
+| **3** | Contradiction auto-corrected - proceed with corrected output |
 
 ### Bidirectional Approved↔Blocking Auto-Correction
 
@@ -176,7 +176,7 @@ If changes include UI files, reviewers check for:
 - Small tap targets (<44×44pt iOS / <48×48dp Android) (→ important)
 - Missing identifiers + Dynamic Type support (→ suggestion)
 
-Pure code analysis — no simulator needed. Device-level audits run in Phase 5 when requested.
+Pure code analysis - no simulator needed. Device-level audits run in Phase 5 when requested.
 
 ### Status Enforcement
 
@@ -186,7 +186,7 @@ Phase 3 treats the issue-tracker status update as a required step with a post-mu
 
 - **Pre-Commit Secret Detection** (12 patterns): `PreToolUse` hook scans staged files for API keys/tokens, AWS access keys, private keys, `.env` files, service account JSON. Commit **blocked** if found.
 - **Build Queue**: All `xcodebuild` calls acquire a lock. Each worktree uses own `-derivedDataPath`. Stale locks auto-clean after 15 min. Non-Xcode builds don't need the lock.
-- **Context Management**: `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=65` — compaction at 65% usage (prevents degradation in 8-phase sessions).
+- **Context Management**: `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=65` - compaction at 65% usage (prevents degradation in 8-phase sessions).
 - **3-Iteration Hard Kill**: Any retry loop stops after 3 attempts, then pauses for user. No infinite loops.
 
 ## Testing & Quality
@@ -195,9 +195,9 @@ Phase 3 treats the issue-tracker status update as a required step with a post-mu
 
 All critical state files are schema-validated at read and write time:
 
-- `agent-state.schema.json` — validates `$HOME/.claude/logs/multi-agent/.../agent-state.json`
-- `prefs.schema.json` — validates `$HOME/.claude/multi-agent-preferences.json`
-- `triage-output.schema.json` — validates triage output (contradiction `if`/`then` constraint built in)
+- `agent-state.schema.json` - validates `$HOME/.claude/logs/multi-agent/.../agent-state.json`
+- `prefs.schema.json` - validates `$HOME/.claude/multi-agent-preferences.json`
+- `triage-output.schema.json` - validates triage output (contradiction `if`/`then` constraint built in)
 
 ### Smoke Test Suites
 
@@ -225,13 +225,13 @@ Per-phase token budgets prevent runaway sessions. If a phase exceeds its budget,
 
 ### Diff Risk Scoring
 
-`pipeline/scripts/diff-risk-score.mjs` runs at Phase 4 Step 1.75 — before reviewer dispatch. Heuristic, deterministic, sub-second, no LLM. Top-N risk-ranked files inject into each reviewer's prompt as a `${PRIORITY_FILES}` block; reviewers read those files first but still review the entire diff.
+`pipeline/scripts/diff-risk-score.mjs` runs at Phase 4 Step 1.75 - before reviewer dispatch. Heuristic, deterministic, sub-second, no LLM. Top-N risk-ranked files inject into each reviewer's prompt as a `${PRIORITY_FILES}` block; reviewers read those files first but still review the entire diff.
 
 Signals + weights: `security_path` ×3, `migration` ×4, `public_api` ×2, `no_test_change` ×2.5, `test_lines_removed` ×3 (test file shrinks - immutable-test backstop), `complexity_delta` ×1.5, `ui_critical` ×1.5, `loc_changed` ×1. Toggle via `prefs.global.diffRiskAdvisory` (default ON).
 
 ### Test Gap Detection
 
-`pipeline/scripts/test-gap-scan.mjs` runs at Phase 5 Step 0. Walks the diff for newly added public symbols and reports those with no paired test. Stack-specific rules ship for iOS, Android, Python, Node.js. iOS Views and Android `@Composable` symbols default to `important`; other public API additions to `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` — when set, the report becomes a Phase 4 rework finding once `important + blocking` count exceeds the threshold.
+`pipeline/scripts/test-gap-scan.mjs` runs at Phase 5 Step 0. Walks the diff for newly added public symbols and reports those with no paired test. Stack-specific rules ship for iOS, Android, Python, Node.js. iOS Views and Android `@Composable` symbols default to `important`; other public API additions to `suggestion`. Optional gating via `prefs.testGap.blockingThreshold` - when set, the report becomes a Phase 4 rework finding once `important + blocking` count exceeds the threshold.
 
 ### Triage Memory
 
@@ -247,7 +247,7 @@ Incremental learning. Phase 7 captures architecture, patterns, gotchas, and deci
 
 Pipeline learns behavioral signals (feedback corrections, project constraints, external references). Phase 7 saves, Phase 1 injects. Max 3 new memories per run. Merge-over-duplicate. Stale memories verified before use.
 
-**What does NOT go in memory**: architecture, code patterns, build gotchas, design decisions — those belong in the knowledge base.
+**What does NOT go in memory**: architecture, code patterns, build gotchas, design decisions - those belong in the knowledge base.
 
 ### Lesson Diagnosis (Reflexion)
 
@@ -290,7 +290,7 @@ Automated visual testing and compliance audits via direct Bash (no MCP server de
 | iOS Archive           | Phase 6, release    | `codesign`, `plutil`, `nm`   |
 | Android APK           | Phase 6, release    | `aapt2`, `apksigner`         |
 
-Audits are **on-demand** — triggered by user, never automatic.
+Audits are **on-demand** - triggered by user, never automatic.
 
 ### Jira + Confluence
 
@@ -304,9 +304,9 @@ Token registry maps logical names (`jira`, `bitbucket`, `github`, `confluence`)
 
 ## Schemas & Validation
 
-- `pipeline/schemas/agent-state.schema.json` — validates agent state lifecycle
-- `pipeline/schemas/prefs.schema.json` — validates preferences
-- `pipeline/schemas/triage-output.schema.json` — validates triage output (contradiction `if`/`then` constraint built in)
+- `pipeline/schemas/agent-state.schema.json` - validates agent state lifecycle
+- `pipeline/schemas/prefs.schema.json` - validates preferences
+- `pipeline/schemas/triage-output.schema.json` - validates triage output (contradiction `if`/`then` constraint built in)
 
 ## File Layout
 

package/docs/performance.md

@@ -7,16 +7,16 @@ you can read, embed in a report, or feed into a dashboard.
 ## Quick Start
 
 ```bash
-# Plain-text summary (the default — fits in a terminal)
+# Plain-text summary (the default - fits in a terminal)
 node pipeline/scripts/aggregate-metrics.mjs
 
 # Markdown table (for PR descriptions, wikis, dashboards)
 node pipeline/scripts/aggregate-metrics.mjs --markdown
 
-# JSON (for machine consumption — Phase 7 report uses this)
+# JSON (for machine consumption - Phase 7 report uses this)
 node pipeline/scripts/aggregate-metrics.mjs --json
 
-# Filtered — only recent runs
+# Filtered - only recent runs
 node pipeline/scripts/aggregate-metrics.mjs --since=2026-04-01
 
 # Per-task or per-phase drill-down
@@ -29,15 +29,15 @@ node pipeline/scripts/aggregate-metrics.mjs --phase=4
 Each event in `metrics.jsonl` is a single-line JSON object written by
 `log-metric.sh`. Events cover:
 
-- **Review cycles** — how many iterations of Phase 3 → Phase 4 → Phase 3 a task
+- **Review cycles** - how many iterations of Phase 3 → Phase 4 → Phase 3 a task
   needed before triage approved.
-- **Triage classification** — accepted / deferred / rejected counts per review.
-- **Triage edge cases** — over-rejection guard trips, contradictions, invalid-
+- **Triage classification** - accepted / deferred / rejected counts per review.
+- **Triage edge cases** - over-rejection guard trips, contradictions, invalid-
   JSON retries, timeouts.
-- **Phase 3 retries** — build / test / lint retry distribution per task.
-- **Cost per model** — calls, duration, tokens in/out, broken down by model
+- **Phase 3 retries** - build / test / lint retry distribution per task.
+- **Cost per model** - calls, duration, tokens in/out, broken down by model
   (Fable, Opus, Sonnet, GPT-5.4).
-- **Language preference** — distribution of EN vs TR prompts.
+- **Language preference** - distribution of EN vs TR prompts.
 
 ## Typical Output (Markdown)
 
@@ -58,9 +58,9 @@ _Source: ~/.claude/logs/multi-agent/metrics.jsonl · Events: 421 (0 parse errors
 
 | Category | Count | Rate |
 |----------|-------|------|
-| Raw findings | 167 | — |
+| Raw findings | 167 | - |
 | Accepted | 41 | 0.25 |
-| Deferred | 19 | — |
+| Deferred | 19 | - |
 | Rejected | 107 | 0.64 |
 
 ## Cost Per Model
@@ -74,11 +74,11 @@ _Source: ~/.claude/logs/multi-agent/metrics.jsonl · Events: 421 (0 parse errors
 
 ## Interpreting Review-Cycle Metrics
 
-- **`cycles per task avg` > 2.0** — triage is rejecting too many real findings
+- **`cycles per task avg` > 2.0** - triage is rejecting too many real findings
   or Phase 3 isn't converging. Inspect the edge-cases table.
-- **Most-common edge case = `over_rejection_guard_tripped`** — the triage
+- **Most-common edge case = `over_rejection_guard_tripped`** - the triage
   prompt lost scope context. Look at `phase-4-review.md:57-91`.
-- **`p95` much higher than `avg`** — a few tasks are looping 3+ times. Usually
+- **`p95` much higher than `avg`** - a few tasks are looping 3+ times. Usually
   means one of: bad acceptance criteria in Phase 2, tests that flake, or
   environment-dependent build failures.
 
@@ -101,7 +101,7 @@ Current totals (v3.5.0):
 | **Total** | **13600** | **16300** | **~14.3k** |
 
 Lazy loading keeps these off the model's context until each phase actually
-runs — the full 14 k total is never loaded at once.
+runs - the full 14 k total is never loaded at once.
 
 ## Embedding Metrics in Phase 7 Reports
 
@@ -112,5 +112,5 @@ template in `phase-7-report.md`.
 ## Disabling Metrics
 
 Remove or rename `~/.claude/logs/multi-agent/metrics.jsonl`. The pipeline
-will not error — `log-metric.sh` fails silently if the file isn't writable.
+will not error - `log-metric.sh` fails silently if the file isn't writable.
 Nothing is sent off-device.