@mmerterden/multi-agent-pipeline 10.7.3 → 10.7.4

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

@@ -1,6 +1,6 @@
 ### Phase 4: Review (deterministic gates + parallel + triage)
 
-> **TLDR**  -  Three-stage review. Stage 1: deterministic gates (build + lint + test + secret scan) that MUST pass. Stage 2: AI models in parallel  -  reviewer set is **CLI-aware**: Claude Code dispatches 2 reviewers (Opus + Sonnet); Copilot CLI dispatches 3 reviewers (GPT-5.4 + Opus + Sonnet). Stage 3: Opus triage  -  evaluates raw findings, filters false-positives/out-of-scope, keeps only actionable items. Only triage-accepted blocking items loop back to Phase 3.
+> **TLDR**  -  Three-stage review. Stage 1: deterministic gates (build + lint + test + secret scan) that MUST pass. Stage 2: AI models in parallel  -  reviewer set is **CLI-aware**: Claude Code dispatches 2 reviewers (Fable + Sonnet); Copilot CLI dispatches 3 reviewers (GPT-5.4 + Opus + Sonnet — Fable 5 is not offered on Copilot CLI). Stage 3: Fable triage (Opus on Copilot CLI)  -  evaluates raw findings, filters false-positives/out-of-scope, keeps only actionable items. Only triage-accepted blocking items loop back to Phase 3.
 
 <!-- progress-contract: applied -->
 Progress emission per `refs/progress-contract.md`  -  lines for each gate, each reviewer dispatch + finish, triage start, triage verdict, fix dispatch.
@@ -181,17 +181,17 @@ Launch Agent instances **in parallel** using the shared `code-reviewer` subagent
 
 | Reviewer   | subagent_type     | Model               | Focus                             | Skills Referenced                             | Where it runs        |
 | ---------- | ----------------- | ------------------- | --------------------------------- | --------------------------------------------- | -------------------- |
-| Reviewer 1 | `code-reviewer`   | `claude-opus-4.6`   | Deep security + architecture      | `api-security-best-practices`, `architecture` | Both CLIs            |
+| Reviewer 1 | `code-reviewer`   | `claude-fable-5` (Claude Code) / `claude-opus-4-8` (Copilot CLI) | Deep security + architecture      | `api-security-best-practices`, `architecture` | Both CLIs            |
 | Reviewer 2 | `code-reviewer`   | `gpt-5.4`           | Edge cases, different perspective | cross-model diversity                         | **Copilot CLI only** |
-| Reviewer 3 | `code-reviewer`   | `claude-sonnet-4.6` | Quality + correctness + naming    | `clean-code`, stack-specific skill            | Both CLIs            |
+| Reviewer 3 | `code-reviewer`   | `claude-sonnet-4-6` | Quality + correctness + naming    | `clean-code`, stack-specific skill            | Both CLIs            |
 
 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: 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.
+**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.
 
-| Stack | Reviewer 1 (Opus) | Reviewer 2 (GPT-5.4  -  Copilot CLI only) | Reviewer 3 (Sonnet) |
+| Stack | Reviewer 1 (Fable / Opus on Copilot) | Reviewer 2 (GPT-5.4  -  Copilot CLI only) | Reviewer 3 (Sonnet) |
 |-------|-------------------|-----------------------------------------|---------------------|
 | iOS/Swift | `ios-security`, `swiftui-performance`, `hig-patterns` | `swift-concurrency`, `ios-accessibility` | `swiftui-pro`, `swift-testing` |
 | Android/Kotlin | `android-security`, `android-performance` | `compose-testing`, `android-architecture` | `compose-components`, `kotlin-coroutines-expert` |
@@ -204,11 +204,11 @@ Skills are injected into reviewer prompt context  -  the reviewer uses them as r
 
 **iOS/Swift  -  interaction & convention skills (conditional).** When the diff touches SwiftUI UI files (`*View.swift`, `*Screen.swift`, `*Configuration.swift`, `*+Modifiers.swift`), additionally inject the relevant `figma-common` convention skills as reference for the iOS reviewers: `figma-navigation`, `figma-overlays`, `figma-bottom-sheets` (interaction: emit-intent vs self-route/self-present; native-SwiftUI-first vs the project's `ui.*` custom system), and the enriched `figma-to-swiftui` accessibility rules (minimalism). These back the Step 1.5 iOS convention checks. Generic across SwiftUI projects  -  not tied to any one app. Omit when the diff has no SwiftUI UI changes (keeps the reviewer prompt lean).
 
-**Dispatch timeout (required, mirrors triage 3.3).** Reviewers run in parallel and triage waits on all of them, so one stalled reviewer hangs the phase. Bound each reviewer dispatch by `REVIEWER_TIMEOUT_SECONDS` (default 180). If a reviewer has not returned by the budget: log `review.reviewer_timeout reviewer=<name>`, treat that reviewer as absent, and proceed to triage with the reviewers that did return. The merged-findings count and `consensus.reviewerCount` reflect only the reviewers that returned. If **zero** reviewers return, retry the Opus reviewer once; on a second total failure HALT with `ERR: no reviewer returned within ${REVIEWER_TIMEOUT_SECONDS}s; resume with /multi-agent:resume #N.`. The Step 2.5 rebuttal round uses the same per-dispatch timeout. Never block indefinitely on a slow or dead reviewer dispatch.
+**Dispatch timeout (required, mirrors triage 3.3).** Reviewers run in parallel and triage waits on all of them, so one stalled reviewer hangs the phase. Bound each reviewer dispatch by `REVIEWER_TIMEOUT_SECONDS` (default 180). If a reviewer has not returned by the budget: log `review.reviewer_timeout reviewer=<name>`, treat that reviewer as absent, and proceed to triage with the reviewers that did return. The merged-findings count and `consensus.reviewerCount` reflect only the reviewers that returned. If **zero** reviewers return, retry Reviewer 1 once; on a second total failure HALT with `ERR: no reviewer returned within ${REVIEWER_TIMEOUT_SECONDS}s; resume with /multi-agent:resume #N.`. The Step 2.5 rebuttal round uses the same per-dispatch timeout. Never block indefinitely on a slow or dead reviewer dispatch.
 
 #### Output contract  -  reviewer step
 
-Step 2 produces N reviewer-output objects (one per dispatched reviewer), each conforming to `pipeline/schemas/reviewer-output.schema.json`. They are persisted to `state.reviewIterations[<iteration>].reviewers[]` and consumed by Step 3 (Opus triage)  -  never by Phase 6 directly. The triage step (below) is the producer of the only review artifact Phase 6 reads, conforming to `pipeline/schemas/triage-output.schema.json`.
+Step 2 produces N reviewer-output objects (one per dispatched reviewer), each conforming to `pipeline/schemas/reviewer-output.schema.json`. They are persisted to `state.reviewIterations[<iteration>].reviewers[]` and consumed by Step 3 (Fable triage)  -  never by Phase 6 directly. The triage step (below) is the producer of the only review artifact Phase 6 reads, conforming to `pipeline/schemas/triage-output.schema.json`.
 
 **Subagent return format**  -  each reviewer returns JSON conforming to `pipeline/schemas/reviewer-output.schema.json`:
 
@@ -248,9 +248,9 @@ Exit 0 = valid. Exit 2 = contradiction (approved=true with blocking findings)  -
 
 **Off by default reason:** mixed-verdict cases are ~8% of runs in practice; the extra ~$0.20-$0.50 per run isn't worth automating for users who'd rather let triage resolve it cleanly. Users with high-stakes tasks (security-critical, release branches) can flip the flag.
 
-#### Step 3  -  Opus Triage (filter before acting)
+#### Step 3  -  Fable Triage (filter before acting)
 
-**CRITICAL**: Reviewer findings are **raw signals**, not commands. Never auto-loop on every "blocking" tag  -  reviewers hallucinate, misread scope, or repeat each other. Run Opus triage to evaluate merged findings against task scope.
+**CRITICAL**: Reviewer findings are **raw signals**, not commands. Never auto-loop on every "blocking" tag  -  reviewers hallucinate, misread scope, or repeat each other. Run Fable triage (Opus on Copilot CLI) to evaluate merged findings against task scope.
 
 ##### 3.1 Short-circuit: no findings
 
@@ -258,7 +258,7 @@ If merged findings `length === 0`, **skip triage**: write empty result `{"accept
 
 ##### 3.2 Launch triage agent
 
-Launch **1 Agent** (subagent_type: `general-purpose`, model: `opus`) with:
+Launch **1 Agent** (subagent_type: `general-purpose`, model: `fable` on Claude Code / `opus` on Copilot CLI) with:
 
 - Raw findings from Reviewer 1 + Reviewer 2 (merged JSON)
 - Task scope (Phase 1 analysis summary + Phase 2 plan)
@@ -307,11 +307,11 @@ Step 3 produces a single triage-output object conforming to `pipeline/schemas/tr
 
 Return ONLY valid JSON conforming to pipeline/schemas/triage-output.schema.json:
 {
-  "accepted":  [{ "severity": "blocking|important|suggestion", "file": "...", "line": N, "issue": "...", "fix": "...", "reviewer": "opus|sonnet" }],
+  "accepted":  [{ "severity": "blocking|important|suggestion", "file": "...", "line": N, "issue": "...", "fix": "...", "reviewer": "fable|opus|sonnet|gpt" }],
   "deferred":  [{ "finding": {...}, "reason": "..." }],
   "rejected":  [{ "finding": {...}, "reason": "..." }],
   "approved":  true|false,  // true if no accepted blocking items remain
-  "consensus": { "reviewerCount": N, "verdict": "unanimous-pass|unanimous-block|split|unverified", "disagreements": [{ "file": "...", "line": N, "issue": "...", "note": "Opus blocking, Sonnet approved" }] }  // optional, see 3.6
+  "consensus": { "reviewerCount": N, "verdict": "unanimous-pass|unanimous-block|split|unverified", "disagreements": [{ "file": "...", "line": N, "issue": "...", "note": "Fable blocking, Sonnet approved" }] }  // optional, see 3.6
 }
 ```
 
@@ -352,12 +352,12 @@ Failure fallback (timeout >120s, or agent crash before any JSON is produced): re
 Emit metrics per review pass for Phase 7 cost rollup:
 
 ```bash
-LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.reviewer_call model=opus duration_ms=$OPUS_DURATION tokens_in=$OPUS_IN tokens_out=$OPUS_OUT
+LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.reviewer_call model=fable duration_ms=$R1_DURATION tokens_in=$R1_IN tokens_out=$R1_OUT   # model=opus on Copilot CLI
 # GPT-5.4 metric emitted only on Copilot CLI (skip on Claude Code):
 [ "${CLI_HOST:-claude}" = "copilot" ] && \
   LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.reviewer_call model=gpt-5.4 duration_ms=$GPT_DURATION tokens_in=$GPT_IN tokens_out=$GPT_OUT
 LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.reviewer_call model=sonnet duration_ms=$SONNET_DURATION tokens_in=$SONNET_IN tokens_out=$SONNET_OUT
-LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.triage_call model=opus duration_ms=$TRIAGE_DURATION tokens_in=$TRIAGE_IN tokens_out=$TRIAGE_OUT
+LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.triage_call model=fable duration_ms=$TRIAGE_DURATION tokens_in=$TRIAGE_IN tokens_out=$TRIAGE_OUT
 pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.completed raw_count=$RAW accepted=$ACC deferred=$DEF rejected=$REJ approved=$APPROVED duration_ms=$DURATION
 ```
 
@@ -365,18 +365,18 @@ pipeline/scripts/log-metric.sh "$TASK_ID" 4 review.completed raw_count=$RAW acce
 
 ##### 3.5 Optional cross-check (single-point-of-failure mitigation)
 
-Opt-in via `prefs.global.triageCrossCheck.enabled` (default `false`). Sampled runs dispatch a **Sonnet** triage agent as second opinion, validated via `validate-triage.mjs` (same fallback rules). Disagreements logged as `triage.cross_check_diff`; `blockOnDisagreement` pauses for user (autopilot: proceed with Opus verdict). Doubles triage cost on sampled runs.
+Opt-in via `prefs.global.triageCrossCheck.enabled` (default `false`). Sampled runs dispatch a **Sonnet** triage agent as second opinion, validated via `validate-triage.mjs` (same fallback rules). Disagreements logged as `triage.cross_check_diff`; `blockOnDisagreement` pauses for user (autopilot: proceed with the Fable verdict). Doubles triage cost on sampled runs.
 
 ##### 3.6 Consensus surfacing (anti-correlation)
 
-**Rationale:** Reviewer 1 (Opus) and Reviewer 3 (Sonnet) share a base model family, so unanimous agreement on a *judgment call* is not independent confirmation  -  same-family models drift the same way on ambiguous prompts. Treating "both approved" as proof produces false-consensus passes. Triage therefore records a `consensus` block (schema v3.1.0) and surfaces disagreement and unverified agreement to the user rather than burying it.
+**Rationale:** Reviewer 1 (Fable) and Reviewer 3 (Sonnet) are both Anthropic Claude models, so unanimous agreement on a *judgment call* is not independent confirmation  -  same-family models drift the same way on ambiguous prompts. Treating "both approved" as proof produces false-consensus passes. Triage therefore records a `consensus` block (schema v3.1.0) and surfaces disagreement and unverified agreement to the user rather than burying it.
 
 After the triage verdict is computed, populate `triage.consensus`:
 
 1. `reviewerCount` = number of reviewers dispatched this iteration (`2` on Claude Code, `3` on Copilot CLI).
 2. Classify the iteration `verdict`:
    - `unanimous-block` -> all reviewers returned at least one overlapping `blocking` finding.
-   - `split` -> reviewers disagreed on existence or severity of one or more findings (the Step 2.5 disagreement definition). List each split in `disagreements[]` with a `note` naming who held which position (e.g. "Opus blocking, Sonnet approved").
+   - `split` -> reviewers disagreed on existence or severity of one or more findings (the Step 2.5 disagreement definition). List each split in `disagreements[]` with a `note` naming who held which position (e.g. "Fable blocking, Sonnet approved").
    - `unanimous-pass` -> all reviewers approved AND the diff is low-risk (no security/auth/concurrency surface per Phase 1 `touchedAreas`). Clear-cut; trust it.
    - `unverified` -> all reviewers approved BUT the diff touches a judgment-heavy surface (security, auth, concurrency, money, data migration). Agreement here may be correlated; do NOT treat it as a confirmed pass. Surface it.
 3. `disagreements[]` is populated for `split` and is also used to carry `unverified` notes (e.g. "both approved a keychain change  -  agreement unverified, confirm manually").
@@ -430,7 +430,7 @@ for proj in $(jq -r '.projects[] | "\(.name)\t\(.worktreePath)\t\(.baseBranch)"'
 done
 ```
 
-Same 3 reviewers (Opus / GPT-5.4 / Sonnet) receive `COMBINED_DIFF` with a multi-repo prefix in the system prompt:
+Same reviewer set (Fable-or-Opus / GPT-5.4 / Sonnet) receive `COMBINED_DIFF` with a multi-repo prefix in the system prompt:
 
 ```
 This is a multi-repo task spanning {N} repos: {repo names}.

package/pipeline/commands/multi-agent/refs/progress-contract.md

@@ -128,7 +128,7 @@ Every phase that dispatches a billable LLM agent MUST forward the call's token t
 
 ```bash
 LOG_METRIC_FORWARD_TO_TRACKER=1 pipeline/scripts/log-metric.sh "$TASK_ID" <phase-id> <event> \
-  model=<opus|sonnet|haiku|gpt-5.4> \
+  model=<fable|opus|sonnet|haiku|gpt-5.4> \
   tokens_in=$IN tokens_out=$OUT duration_ms=$DUR
 ```
 

package/pipeline/commands/multi-agent/refs/tracker-contract.md

@@ -24,8 +24,7 @@ The agent detects which CLI it's running in and uses the appropriate visual mech
 ```
 1. system prompt mentions "Claude Code"             → claude-code
 2. system prompt mentions "Copilot" / "GitHub Copilot" → copilot
-3. system prompt mentions "Cursor"                   → cursor
-5. None of the above                                 → generic (bash stdout)
+3. None of the above                                 → generic (bash stdout)
 ```
 
 Visual mechanism per CLI:

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

@@ -1,5 +1,5 @@
 ---
-description: "Run parallel review on a branch's diff or a Pull Request: 2 models on Claude Code (Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state."
+description: "Run parallel review on a branch's diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state."
 argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted, the current branch is used."
 ---
 
@@ -112,13 +112,13 @@ Save the diff to `/tmp/multi-agent-review-${TASK_ID}-diff.patch` so reviewers ca
 ### 3. Launch parallel reviewers  -  host-CLI dependent
 
 **Claude Code (2 in parallel):**
-- Agent 1: `claude-opus-4.6` → security + architecture
-- Agent 2: `claude-sonnet-4.6` → general quality
+- Agent 1: `claude-fable-5` → security + architecture
+- Agent 2: `claude-sonnet-4-6` → general quality
 
 **Copilot CLI (3 in parallel):**
-- Agent 1: `claude-opus-4.6` → security + architecture
+- Agent 1: `claude-opus-4-8` → security + architecture (Fable 5 is not offered on Copilot CLI)
 - Agent 2: `gpt-5.4` → edge cases, alternate perspective
-- Agent 3: `claude-sonnet-4.6` → general quality
+- Agent 3: `claude-sonnet-4-6` → general quality
 
 Each reviewer receives the diff plus the standard reviewer system prompt (see `refs/phases/phase-4-review.md` for the prompt contract). Output: structured `findings[]` per reviewer.
 
@@ -137,7 +137,7 @@ Each finding gets the `ruleID` from the catalog plus the platform policy ref:
 
 Catalog-only  -  does NOT invoke binaries. For a full scan, use `/multi-agent:test "store-ready"`.
 
-### 5. Triage (Opus)
+### 5. Triage (Fable)
 
 Classify findings into:
 - 🔴 **Blocking** → must fix
@@ -152,10 +152,10 @@ Triage also marks each finding as `accepted` (real issue), `deferred` (real but
 🔍 Review Complete  ·  PR #1250  ·  3 files +120 -45
 | Model    | Verdict   | Blocking | Important | Suggestion |
 |----------|-----------|----------|-----------|------------|
-| Opus     | approved  | 0        | 1         | 3          |
+| Fable    | approved  | 0        | 1         | 3          |
 | Sonnet   | rejected  | 1        | 2         | 5          |
 
-Consensus: ⚠ DISAGREEMENT  -  see Opus triage
+Consensus: ⚠ DISAGREEMENT  -  see Fable triage
 ```
 
 This summary ALWAYS prints, regardless of input mode. The chat is the live conversation; on the PR side, the durable artifacts are inline comments + the review state (Step 7).

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

@@ -58,7 +58,7 @@ Run every step automatically:
 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 2: COPILOT     Claude Code -> Copilot CLI (instructions + 35 sub-command skills)
 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)
@@ -277,11 +277,11 @@ This runs on the Claude <-> Copilot axis — the two CLIs the pipeline supports
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**34 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**35 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, delete, dev,
-dev-autopilot, dev-local, dev-local-autopilot, diff-explain, garbage-collect,
+dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
 help, issue, jira, kill, language, local, local-autopilot, log, manual-test,
 prune-logs, purge, refactor, resume, review, scan, search, setup, stack, status,
 sync, test, update

package/pipeline/commands/multi-agent.md

@@ -1,5 +1,5 @@
 ---
-description: "Task orchestrator  -  full pipeline via Jira ID + branch or GitHub Issue URL: analysis, plan, TDD development, parallel review + Opus triage (CLI-aware: 2-model on Claude Code, 3-model on Copilot CLI), commit, log"
+description: "Task orchestrator  -  full pipeline via Jira ID + branch or GitHub Issue URL: analysis, plan, TDD development, parallel review + Fable triage (CLI-aware: 2-model on Claude Code, 3-model on Copilot CLI), commit, log"
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, NotebookEdit, Skill
 ---
 
@@ -140,14 +140,14 @@ This command uses lazy loading for token efficiency. Read the relevant sub-file
 - Multiple stacks -> load all relevant guides
 
 **Agent definitions** (used in Phase 1 and Phase 4):
-- `$HOME/.claude/agents/code-reviewer.md`  -  Phase 4 reviewer persona (`preferredModel: opus`; Phase 4 overrides Reviewer 3 to `sonnet`)
+- `$HOME/.claude/agents/code-reviewer.md`  -  Phase 4 reviewer persona (`preferredModel: fable`; Phase 4 overrides Reviewer 3 to `sonnet`)
 - `$HOME/.claude/agents/explorer.md`  -  Phase 1 codebase scan persona (`preferredModel: sonnet`  -  scan work, cost-efficient)
-- `$HOME/.claude/agents/ios-architect.md`  -  iOS architecture review (`preferredModel: opus`)
-- `$HOME/.claude/agents/android-architect.md`  -  Android architecture review (`preferredModel: opus`)
-- `$HOME/.claude/agents/backend-architect.md`  -  Backend/API architecture review (`preferredModel: opus`)
+- `$HOME/.claude/agents/ios-architect.md`  -  iOS architecture review (`preferredModel: fable`)
+- `$HOME/.claude/agents/android-architect.md`  -  Android architecture review (`preferredModel: fable`)
+- `$HOME/.claude/agents/backend-architect.md`  -  Backend/API architecture review (`preferredModel: fable`)
 - `$HOME/.claude/agents/security-auditor.md`  -  Security audit (`preferredModel: opus`)
 
-**Per-persona model routing:** Before each Agent dispatch, the orchestrator reads `preferredModel` from the persona file and exports `CLAUDE_CODE_SUBAGENT_MODEL` (Claude Code) / passes `--model` (Copilot CLI). Precedence: per-dispatch `PHASE_MODEL_OVERRIDE` > persona `preferredModel` > `opus`. Full contract: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`.
+**Per-persona model routing:** Before each Agent dispatch, the orchestrator reads `preferredModel` from the persona file and exports `CLAUDE_CODE_SUBAGENT_MODEL` (Claude Code) / passes `--model` (Copilot CLI). Precedence: per-dispatch `PHASE_MODEL_OVERRIDE` > persona `preferredModel` > `fable` (falls back per `refs/features/model-fallback.md`). Full contract: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`.
 
 ---
 
@@ -247,7 +247,7 @@ When called with `review`:
 1. Detect current branch and project from cwd (or ask)
 2. Get diff: `git diff HEAD` (unstaged + staged)
 3. If no diff, get diff against base branch: `git diff origin/{baseBranch}...HEAD`
-4. Launch Phase 4 review (parallel + Opus triage  -  2-model on Claude Code, 3-model on Copilot CLI) on the diff
+4. Launch Phase 4 review (parallel + Fable triage  -  2-model on Claude Code, 3-model on Copilot CLI) on the diff
 5. No worktree, no state file  -  lightweight one-shot review
 6. Print findings to terminal
 

package/pipeline/schemas/agent-state.schema.json

@@ -183,7 +183,7 @@
             "planEditRequests": {
               "type": "array",
               "items": { "type": "string" },
-              "description": "v5.3.0 Phase 2  -  free-text edit instructions the user typed between plan renders. Preserved verbatim for audit; Opus parses them conversationally to revise the plan."
+              "description": "v5.3.0 Phase 2  -  free-text edit instructions the user typed between plan renders. Preserved verbatim for audit; the planning model (Fable top tier) parses them conversationally to revise the plan."
             }
           }
         }

package/pipeline/schemas/prefs.schema.json

@@ -831,9 +831,9 @@
             },
             "pricingModel": {
               "type": "string",
-              "enum": ["opus", "sonnet", "haiku"],
-              "default": "opus",
-              "description": "Which cost-table.json rate to price accumulated tokens at. Defaults to opus for a deliberately conservative (upper-bound) estimate, so the ceiling trips early rather than late."
+              "enum": ["fable", "opus", "sonnet", "haiku"],
+              "default": "fable",
+              "description": "Which cost-table.json rate to price accumulated tokens at. Defaults to fable (the top tier since v10.6.0) for a deliberately conservative (upper-bound) estimate, so the ceiling trips early rather than late."
             }
           }
         },

package/pipeline/schemas/reviewer-output.schema.json

@@ -19,7 +19,7 @@
     },
     "reviewer": {
       "type": "string",
-      "description": "Model label for this output (e.g. 'opus', 'sonnet', 'gpt'). Present once the parallel reviewer outputs are merged into the Phase 4 array so triage/consensus can attribute each finding to its source. Optional on a single reviewer's raw pre-merge output."
+      "description": "Model label for this output (e.g. 'fable', 'opus', 'sonnet', 'gpt'). Present once the parallel reviewer outputs are merged into the Phase 4 array so triage/consensus can attribute each finding to its source. Optional on a single reviewer's raw pre-merge output."
     }
   },
   "$defs": {

package/pipeline/schemas/triage-output.schema.json

@@ -74,8 +74,8 @@
     },
     "reviewer": {
       "type": "string",
-      "enum": ["opus", "sonnet"],
-      "description": "Which reviewer produced the raw finding. Haiku was removed in v2.1.0."
+      "enum": ["fable", "opus", "sonnet", "gpt"],
+      "description": "Which reviewer produced the raw finding. Claude Code Reviewer 1 is fable (opus when fallback engages); Copilot CLI adds gpt. Haiku was removed in v2.1.0."
     },
     "consensus": {
       "type": "object",

package/pipeline/scripts/README.md

@@ -64,12 +64,11 @@ Installed into `~/.claude/scripts/` and invoked by settings.json hook configurat
 - `pre-push-check.sh`  -  runs before `git push` (smoke-cross-cli-behavior + smoke-personal-data)
 - `output-quality-check.sh`  -  runs after PR body / Jira comment generation (newline / HTML entity guard)
 
-## Runtime helpers (13 files)
+## Runtime helpers
 Shell scripts invoked during pipeline execution.
 
 - `phase-banner.sh`  -  renders phase headers
 - `phase-tracker.sh`  -  live tracker state + tokens accumulation + render
-- `stack-swap.sh`  -  stack detection + skill set swap
 - `keychain-save.sh`  -  store PAT in macOS Keychain
 - `audit-log.sh` + `audit-log-rotate.sh`  -  opt-in audit trail
 - `log-metric.sh`  -  opt-in metric capture

package/pipeline/scripts/cost-budget-check.mjs

@@ -66,7 +66,7 @@ if (flags.help || flags.h) {
 }
 
 // --- resolve config: prefs first, CLI overrides -----------------------------
-const cfg = { enabled: false, maxUsd: 5.0, warnPct: 80, onExceed: "warn", pricingModel: "opus" };
+const cfg = { enabled: false, maxUsd: 5.0, warnPct: 80, onExceed: "warn", pricingModel: "fable" };
 
 if (flags.prefs) {
   if (!existsSync(flags.prefs)) die(`prefs file not found: ${flags.prefs}`);

package/pipeline/scripts/cost-table.json

@@ -2,6 +2,13 @@
   "_readme": "Per-model unit prices in USD per million tokens. Source: Anthropic public pricing (verified 2026-04-21). Update when Anthropic publishes new tiers. Unknown models render USD as ' - ' and emit a footnote  -  never block PR-body generation. cacheReadPerMtok is the discounted rate for prompt-cache hits (~10% of inPerMtok); the renderer prices a phase's tokens_cached at this rate when the tracker records it, so resume/cache reuse is visible in the ledger.",
   "schemaVersion": "1.1.0",
   "prices": {
+    "fable": {
+      "inPerMtok": 10.0,
+      "outPerMtok": 50.0,
+      "cacheReadPerMtok": 1.0,
+      "modelId": "claude-fable-5",
+      "note": "Top tier (restored v10.6.0)  -  architects, Reviewer 1, triage. Verified against Anthropic pricing 2026-07-02."
+    },
     "opus": {
       "inPerMtok": 5.0,
       "outPerMtok": 25.0,

package/pipeline/scripts/fixtures/install-layout.tsv

@@ -1,16 +1,16 @@
 .claude/CLAUDE.md	1
 .claude/agents	8
-.claude/commands	87
+.claude/commands	88
 .claude/lib	23
 .claude/multi-agent-preferences.json	1
 .claude/rules	12
 .claude/schemas	23
-.claude/scripts	174
+.claude/scripts	167
 .claude/settings.json	1
-.claude/skills	555
+.claude/skills	560
 .copilot/agents	8
 .copilot/copilot-instructions.md	1
 .copilot/lib	23
 .copilot/schemas	23
-.copilot/scripts	174
-.copilot/skills	590
+.copilot/scripts	167
+.copilot/skills	596

package/pipeline/scripts/uninstall.mjs

@@ -2,15 +2,17 @@
 
 /**
  * @file Token-preserving uninstaller  -  removes the multi-agent-pipeline
- * footprint from Claude Code, Copilot CLI, Cursor, Antigravity, and VS Code
- * Copilot Chat without touching personal access tokens stored in the OS credential store
- * (macOS Keychain / Windows Credential Manager / Linux libsecret).
+ * footprint from Claude Code and Copilot CLI without touching personal access
+ * tokens stored in the OS credential store (macOS Keychain / Windows
+ * Credential Manager / Linux libsecret). The legacy adapter flags
+ * (--cursor / --copilot-chat / --antigravity / --codex) clean up files left
+ * behind by pre-v10.7.0 adapter installs; the adapters themselves are gone.
  *
  * Invocation:
  *   node uninstall.mjs                  # interactive, removes from all installed targets
  *   node uninstall.mjs --yes            # skip prompts, remove from all
  *   node uninstall.mjs --claude         # only Claude Code
- *   node uninstall.mjs --cursor --target=/path/to/repo
+ *   node uninstall.mjs --cursor --target=/path/to/repo   # legacy adapter-file cleanup
  *   node uninstall.mjs --dry-run        # report what would be removed, change nothing
  *
  * Targeted by:
@@ -29,12 +31,9 @@
  */
 
 import { existsSync, readdirSync, readFileSync, rmSync, writeFileSync } from "fs";
-import { join, dirname } from "path";
-import { fileURLToPath } from "url";
+import { join } from "path";
 import { createInterface } from "readline";
 
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const PIPELINE_ROOT = join(__dirname, "..");
 const HOME = process.env.HOME || process.env.USERPROFILE;
 
 const flags = process.argv.slice(2).filter((a) => a !== "uninstall");
@@ -106,6 +105,23 @@ function rmMatchingDirs(parent, predicate) {
   return count;
 }
 
+/**
+ * Remove every plain file under `parent` whose name matches a predicate.
+ * Used by the legacy adapter cleanup (pre-v10.7.0 generated files).
+ * @param {string} parent
+ * @param {(name: string) => boolean} predicate
+ */
+function rmMatchingFiles(parent, predicate) {
+  if (!existsSync(parent)) return 0;
+  let count = 0;
+  for (const entry of readdirSync(parent, { withFileTypes: true })) {
+    if (!entry.isFile()) continue;
+    if (!predicate(entry.name)) continue;
+    if (rmIfExists(join(parent, entry.name))) count++;
+  }
+  return count;
+}
+
 /**
  * Strip a marker-wrapped `<!-- multi-agent-pipeline:begin/end -->` block from
  * a user-owned file. Preserves everything outside the markers. Deletes the
@@ -287,68 +303,48 @@ async function main() {
     stripManagedBlock(join(COP, "copilot-instructions.md"));
   }
 
+  // Legacy adapter-file cleanup (adapters removed in v10.7.0). These blocks
+  // delete files a pre-v10.7.0 install generated; they never touch user files
+  // outside the multi-agent-* namespace / managed markers.
   if (forCursor) {
     console.log("");
-    console.log(`  [Cursor] Removing from ${adapterTarget}...`);
-    if (!dryRun) {
-      try {
-        const adapter = (await import(join(PIPELINE_ROOT, "adapters", "cursor.mjs"))).default;
-        const result = adapter.uninstall({ target: adapterTarget });
-        console.log(`    removed: ${result.removed} file(s)`);
-      } catch (e) {
-        console.log(`    skipped (adapter unavailable): ${e.message}`);
-      }
-    } else {
-      report("would invoke", "cursor adapter uninstall");
-    }
+    console.log(`  [Cursor  -  legacy cleanup] Removing from ${adapterTarget}...`);
+    const isOurs = (name) => name.startsWith("multi-agent-") || name.startsWith("multi-agent.");
+    const n = rmMatchingFiles(join(adapterTarget, ".cursor", "rules"), isOurs);
+    if (n > 0) console.log(`    removed ${n} rule file(s)`);
+    stripManagedBlock(join(adapterTarget, ".cursorrules"));
   }
 
   if (forCopilotChat) {
     console.log("");
-    console.log(`  [GitHub Copilot Chat] Removing from ${adapterTarget}...`);
-    if (!dryRun) {
-      try {
-        const adapter = (await import(join(PIPELINE_ROOT, "adapters", "copilot-chat.mjs"))).default;
-        const result = adapter.uninstall({ target: adapterTarget });
-        console.log(`    main: ${result.mainStatus} · per-skill removed: ${result.perSkillRemoved}`);
-      } catch (e) {
-        console.log(`    skipped (adapter unavailable): ${e.message}`);
-      }
-    } else {
-      report("would invoke", "copilot-chat adapter uninstall");
-    }
+    console.log(`  [GitHub Copilot Chat  -  legacy cleanup] Removing from ${adapterTarget}...`);
+    stripManagedBlock(join(adapterTarget, ".github", "copilot-instructions.md"));
+    const n = rmMatchingFiles(join(adapterTarget, ".github", "instructions"), (name) =>
+      name.startsWith("multi-agent-"),
+    );
+    if (n > 0) console.log(`    removed ${n} instruction file(s)`);
   }
 
   if (forAntigravity) {
     console.log("");
-    console.log(`  [Antigravity] Removing from ${adapterTarget}...`);
-    if (!dryRun) {
-      try {
-        const adapter = (await import(join(PIPELINE_ROOT, "adapters", "antigravity.mjs"))).default;
-        const result = adapter.uninstall({ target: adapterTarget });
-        console.log(`    .agent + AGENTS.md artifacts removed: ${result.removed}`);
-      } catch (e) {
-        console.log(`    skipped (adapter unavailable): ${e.message}`);
-      }
-    } else {
-      report("would invoke", "antigravity adapter uninstall");
-    }
+    console.log(`  [Antigravity  -  legacy cleanup] Removing from ${adapterTarget}...`);
+    const isOurs = (name) => name.startsWith("multi-agent-") || name.startsWith("multi-agent.");
+    let n = rmMatchingFiles(join(adapterTarget, ".agent", "rules"), isOurs);
+    n += rmMatchingFiles(join(adapterTarget, ".agent", "workflows"), isOurs);
+    if (n > 0) console.log(`    removed ${n} .agent file(s)`);
+    stripManagedBlock(join(adapterTarget, "AGENTS.md"));
+    if (existsSync(join(adapterTarget, ".agent", "mcp_config.json")))
+      console.log("    note: .agent/mcp_config.json left untouched (may hold user servers)  -  remove pipeline entries manually if present");
   }
 
-  if (forCodex) {
+  if (forCodex && HOME) {
     console.log("");
-    console.log("  [OpenAI Codex CLI] Removing from ~/.codex...");
-    if (!dryRun) {
-      try {
-        const adapter = (await import(join(PIPELINE_ROOT, "adapters", "codex.mjs"))).default;
-        const result = adapter.uninstall();
-        console.log(`    ~/.codex artifacts removed: ${result.removed}`);
-      } catch (e) {
-        console.log(`    skipped (adapter unavailable): ${e.message}`);
-      }
-    } else {
-      report("would invoke", "codex adapter uninstall");
-    }
+    console.log("  [OpenAI Codex CLI  -  legacy cleanup] Removing from ~/.codex...");
+    const CODEX = join(HOME, ".codex");
+    rmIfExists(join(CODEX, "prompts", "multi-agent.md"));
+    stripManagedBlock(join(CODEX, "AGENTS.md"));
+    if (existsSync(join(CODEX, "config.toml")))
+      console.log("    note: ~/.codex/config.toml left untouched (may hold user MCP servers)  -  remove pipeline entries manually if present");
   }
 
   console.log("");

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

@@ -1,7 +1,7 @@
 ---
 name: multi-agent
 language: en
-description: "Task orchestrator: runs the full pipeline from a Jira ID or GitHub Issue URL  -  analysis → plan → TDD development → parallel review (Opus + Sonnet on Claude Code, GPT + Opus + Sonnet on Copilot CLI) → commit → log. Every step is written to agent-log.md."
+description: "Task orchestrator: runs the full pipeline from a Jira ID or GitHub Issue URL  -  analysis → plan → TDD development → parallel review (Fable + Sonnet on Claude Code, GPT + Opus + Sonnet on Copilot CLI) → commit → log. Every step is written to agent-log.md."
 user-invocable: true
 argument-hint: '"PROJ-12345" "feature/PROJ-12345-flight-filter" | "https://github.com/.../issues/316" | status | log #1 | resume #1 | kill #1 | clear-logs | purge | review'
 ---
@@ -397,7 +397,7 @@ Full contract: `refs/tracker-contract.md` section "TaskCreate ordering (strict)"
 
 **IMPORTANT**: Update `agent-state.json` at EVERY phase transition. This file is the resume source of truth.
 
-### Phase 1: Analysis (claude-opus-4.6)
+### Phase 1: Analysis (claude-fable-5)
 1. Launch **explore agents** (parallel) to scan codebase:
    - Related files to the task
    - Existing patterns and conventions
@@ -406,17 +406,17 @@ Full contract: `refs/tracker-contract.md` section "TaskCreate ordering (strict)"
 3. Summarize findings
 4. Log: `📊 Phase 1: Analysis  -  {N} files identified, {summary}`
 
-### Phase 2: Planning (claude-opus-4.6)
+### Phase 2: Planning (claude-fable-5)
 1. Create task breakdown → todos with dependencies
 2. Launch **ios-architect** agent for architecture review (if structural changes)
 3. Determine development approach per todo (new file, modify, refactor)
 4. Log: `🧠 Phase 2: Plan  -  {N} todos created`
 5. **Plan Approval Gate** (normal mode only  -  skipped for `--dev`, `autopilot`, `--dev autopilot`). Full flow in `refs/phases/phase-2-planning.md` Step 5:
    - **5a  -  Clarification** (conditional, max 2 rounds): if the Jira/issue description is ambiguous (vague acceptance, UI task without Figma, API task without endpoint contract, `ambiguityScore >= 2`, parent-story scope drift), ask structured questions before rendering the plan. User answers → plan regenerated. If it is still unclear after the 2nd round, render the plan with a "best-effort" banner.
-   - **5b  -  Approval loop**: render plan → user: `onayla`/`iptal`/free-text. A free-text edit request → Opus revises the plan → show it again. No iteration cap; user controls exit via `onayla` or `iptal`.
+   - **5b  -  Approval loop**: render plan → user: `onayla`/`iptal`/free-text. A free-text edit request → the planning model (Fable) revises the plan → show it again. No iteration cap; user controls exit via `onayla` or `iptal`.
    - Persist `clarificationRounds`, `clarificationQuestions`, `clarificationAnswers`, `planIterations`, `planApprovedAt`, `planEditRequests` to `state.phases["2"]`.
 
-### Phase 3: Dev (claude-sonnet-4.6)
+### Phase 3: Dev (claude-sonnet-4-6)
 For each todo (respecting dependency order):
 1. Update todo status: `in_progress`
 2. **TDD cycle**:
@@ -431,9 +431,9 @@ For each todo (respecting dependency order):
 ### Phase 4: Review (parallel + triage)
 0. **Diff Risk Scoring (advisory, v8.3+)**  -  before reviewer dispatch run `node pipeline/scripts/diff-risk-score.mjs --base "$BASE_BRANCH" --top 5` and inject the top-N risk-ranked files as a `${PRIORITY_FILES}` block into each reviewer's prompt. Heuristic, deterministic, sub-second, never gates the pipeline. Disabled when `prefs.global.diffRiskAdvisory = false`. Signals: security paths (×3), schema migrations (×4), public API surfaces (×2), no-test-change (×2.5), complexity delta (×1.5), UI-critical paths (×1.5), loc changed (×1).
 1. Launch **code-reviewer** agents in parallel. Reviewer set depends on which CLI is hosting the pipeline:
-   - **Claude Code** (2 reviewers): `claude-opus-4.6` (deep security + architecture) + `claude-sonnet-4.6` (quality + correctness)
-   - **Copilot CLI** (3 reviewers): `gpt-5.4` (edge cases, different perspective) + `claude-opus-4.6` + `claude-sonnet-4.6`
-   - Triage (both CLIs): single `claude-opus-4.6` pass over merged findings
+   - **Claude Code** (2 reviewers): `claude-fable-5` (deep security + architecture) + `claude-sonnet-4-6` (quality + correctness)
+   - **Copilot CLI** (3 reviewers): `gpt-5.4` (edge cases, different perspective) + `claude-opus-4-8` + `claude-sonnet-4-6` (Fable 5 is not offered on Copilot CLI)
+   - Triage: single top-tier pass over merged findings (`claude-fable-5` on Claude Code, `claude-opus-4-8` on Copilot CLI)
 2. Collect findings, classify:
    - 🔴 **Blocking** → must fix → back to Phase 3 (max 3 iterations)
    - 🟡 **Important** → fix and re-review
@@ -872,11 +872,11 @@ First show how it works:
 ```
 🤖 How it works (8 phases):
   0. Init       -  Project detection, worktree creation, state file
-  1. Analysis   -  Codebase scan (parallel explore agents, Opus)
+  1. Analysis   -  Codebase scan (parallel explore agents, Fable)
   2. Planning   -  Task breakdown, architecture review, user approval
   3. Dev        -  TDD loop: write test → write code → build (Sonnet)
-  4. Review     -  Parallel review + Opus triage. Reviewer set by CLI:
-                 • Claude Code → Opus + Sonnet (2 parallel)
+  4. Review     -  Parallel review + Fable triage. Reviewer set by CLI:
+                 • Claude Code → Fable + Sonnet (2 parallel)
                  • Copilot CLI → GPT-5.4 + Opus + Sonnet (3 parallel)
   5. Test  -  Optional: switch to the branch, manual test in Xcode
   6. Commit     -  Commit + push + PR + issue body update (PR links + progress flags)

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

@@ -35,7 +35,7 @@ Phase 7: Report     → Short terminal summary
 
 1. **Parse the input**  -  Normal multi-agent formats (Issue URL, Jira ID, free-text)
 2. **Phase 0: Init**  -  `"mode": "dev", "autopilot": true` in `agent-state.json`
-3. **Phase 3: Dev**  -  Write code + build directly with `claude-opus-4.6`
+3. **Phase 3: Dev**  -  Write code + build directly with `claude-opus-4-8`
 4. **Phase 6: Commit**  -  Create automatic commit + push + PR
 5. **Phase 7: Report**  -  Terminal summary