codex-orchestrator 2.0.11 → 2.0.12

package/internal-workflow/docs/agents/bug-workflow-routing.md

@@ -4,21 +4,23 @@ Use the bug skills by user intent and feedback-loop quality:
 
 - `bug-root-cause-explainer`: diagnosis-only. Use when the user asks why, wants root cause, options, or no edits. Stop before implementation.
 - `diagnosing-bugs`: feedback-loop builder. Use when the bug is hard, flaky, unclear, performance-related, or cannot be proven with a tight red/green signal.
-- `code-debugger`: implementation. Use when the user asks to fix, chose a fix path, or the bug is obvious and reproducible.
+- `implement`: implementation. Use when the user asks to fix, chose a fix path, or the bug is obvious and reproducible.
 
 Handoffs:
 
 - Explainer -> Diagnosing Bugs when root cause cannot be proven without a reliable loop.
-- Explainer -> Code Debugger after the user chooses a fix path.
-- Code Debugger -> Diagnosing Bugs when implementation discovers the bug is unclear, flaky, or lacks a red-capable signal.
-- Diagnosing Bugs -> original intent: return diagnosis to the explainer path, or apply the fix through Code Debugger.
+- Explainer -> Implement after the user chooses a fix path.
+- Implement -> Diagnosing Bugs when implementation discovers the bug is unclear, flaky, or lacks a reliable signal.
+- Diagnosing Bugs -> original intent: return diagnosis to the explainer path, or apply the fix through Implement.
 
 Inside an active user-authorized implementation/TDD flow, keep a reviewer repair
 in that same TDD activation only when the defect is high-confidence,
 source-required, inside the approved behavior/Seam, and has bounded trigger,
 cause, and repair. Group related cases by protected invariant before one
-consolidated repair batch. New product intent, a new Seam, or a risky trade-off
-stops for user approval. A separately authorized fix with no active flow, or an
-ambiguous reproduction/cause/repair, still routes through `code-debugger`.
+consolidated repair batch for the current reviewed revision. Continue repair,
+affected proof, and targeted Review until approval. New product intent, a new
+Seam, or a risky trade-off stops for user approval. A separately authorized fix with no active flow routes
+through `implement`; ambiguous reproduction/cause/repair first routes through
+`diagnosing-bugs`.
 
 Do not collapse diagnosis-only, feedback-loop construction, and implementation into one response unless the user explicitly asked for that full flow.

package/internal-workflow/docs/agents/coding-skill-routing.md

@@ -1,123 +1,173 @@
 # Coding Skill Routing
 
-This file is the normative global route and ownership policy. Keep repository
-commands, domain facts, credentials, deployment assumptions, and product
-behavior in repository `AGENTS.md`, `CONTEXT.md`, ADRs, or local skills.
-
-## Ownership
-
-- Personal skills live only in `../../skills`.
-- `agents/openai.yaml` owns invocation metadata; `agents/*.toml` owns named-role
-  model and effort.
-- A shared rule has one owner. Callers link to it instead of copying its prose.
-- Skill-specific detail belongs in that skill's `references/` and loads only
-  when its branch is active.
-- Root owns the user dialogue, decisions, critical path, integration, and final
-  handoff. A reviewer child owns independent review.
-
-## Default Implementation Route
-
-`medium` is the default for behavior-changing implementation. Use:
-
-- `simple` only for a tiny local change with one obvious proof;
-- `medium` for a clear coherent outcome with settled authority, one ownership
-  path, and credible affected validation—even across several files, modules,
-  API, persistence, or shared state;
-- `high` only when a sensitive mechanism has both a material failure
-  consequence and an uncertainty amplifier such as unclear ownership,
-  cross-trust effects, non-local recovery, an unproven external contract, or
-  proof that cannot isolate the dangerous state.
-
-Prefer direct root implementation for `simple` and ordinary `medium` work. Use
-`$implementation-spec-maker` only for a real execution decision or coordination
-gap. Use `$tickets-orchestrator` only for an approved ticket graph, real delivery
-dependencies or disjoint parallel slices, or an explicit orchestration request.
-Do not manufacture PRDs, tickets, specs, agents, or review checkpoints from
-file count or generic risk labels.
-
-## Core Routes
-
-| Situation | Route |
+This file is the normative global coding route. Repository commands, product
+facts, runtime constraints, and domain language remain in repository policy.
+
+## Shared Kernel
+
+- **Authority** — perform only the requested outcome and actions authorized by
+  the user, Parent PRD, executable ticket, and repository policy. Planning or
+  publication never authorizes implementation. Normal direct and single-ticket
+  Implement authority includes one scoped local commit after proof and
+  applicable Review unless user or repository policy explicitly forbids or
+  reserves Git. Push and PR require separate authority.
+- **Preservation** — preserve unrelated and concurrent work plus user-owned
+  runtimes. Dirty overlapping or unisolatable scope blocks the affected write
+  and commit.
+- **Proof** — claim only the observable outcome proved through the real caller
+  seam. Missing required proof or independent-review approval blocks completion
+  and the affected commit.
+
+These principles are checks, not workflow state or durable artifacts.
+
+## Main Route
+
+The user-facing coding flow is Plan, Implement, Review.
+
+- [`$plan`](../../skills/plan/SKILL.md) owns product decisions and multi-ticket
+  planning composition. It is the sole planning-composition entrypoint.
+- [`$implement`](../../skills/implement/SKILL.md) is the single execution owner
+  for clear features, fixes, obvious local edits, and executable tickets.
+- [`$code-review`](../../skills/code-review/SKILL.md) is the direct Review
+  entrypoint.
+
+Direct non-ticket work stays in the current root context. Do not create a spec,
+ticket, or worker merely because a change spans files or touches an important
+contract. A real product or ownership decision gap returns to Plan. An approved
+multi-ticket dependency graph routes to `$tickets-orchestrator`; a single
+executable ticket never does.
+
+Grilling uses dependency-aware frontier rounds. `$grilling` is the model-invoked,
+write-free interview primitive; `$domain-modeling` is the model-invoked sole
+domain-document writer. `$grill-me`, `$grill-with-docs`, and `$wait-what` are
+explicit-only. Explicitly typed wrappers win: `$grill-me` remains write-free
+even when its prompt mentions terminology or ADRs, while `$grill-with-docs`
+keeps the whole `$grilling` interview write-free and invokes
+`$domain-modeling` only after an empty frontier and explicit confirmation.
+Implicit `$grilling` is write-free and cannot mutate domain docs.
+
+`$writing-for-agents` is a model-invoked discipline for agent-consumed
+documents and complements `$skill-creator`; it is not a router. Use
+`$resolving-merge-conflicts` only for actual Git conflicts or an explicit
+conflict-resolution request. It composes `$domain-modeling` as sole content
+writer for domain-document conflicts, while each Git operation remains gated by
+existing authority. `$documentation-gardener` may audit domain docs but routes
+every authorized domain-document mutation through `$domain-modeling`.
+
+Diagnosis-only work uses `$bug-root-cause-explainer`. Hard, flaky, unclear, or
+performance bugs use `$diagnosing-bugs` to establish a reliable signal, then
+return to Implement when a fix is authorized. External multi-source uncertainty
+uses `$research`. A requested throwaway logic or UI experiment uses `$prototype`
+to answer one bounded design question, then returns production delivery to
+Implement. Grilling, TDD, to-spec, to-tickets, diagnosis, research, prototype,
+and the graph-only Tickets Orchestrator are internal or side primitives.
+Specialized runtime and platform skills remain side tools and do not compete
+with the main flow.
+
+## Phase boundaries
+
+Make a context choice only when one phase has actually completed and another is
+about to begin; never interrupt a live phase merely because the conversation is
+long. Apply these conditions in order:
+
+1. **Continue** when the next phase uses the current conversation as a primary
+   source and the same active owner and authority still apply.
+2. **Use an existing fresh-context route** only when the active workflow already
+   requires one, such as the single-ticket implementer or independent Review.
+3. **Use an authorized stable-role child** only for bounded AFK work that the
+   active skill already permits; root retains dialogue and integration.
+4. **Compact through the platform** only when relevant same-owner work must
+   continue in the current conversation and observed context pressure makes a
+   lossless continuation unreliable.
+
+These are branch conditions, not a token threshold, a new handoff skill, or a
+competing router. Plan, Implement, Review, prototype, `$to-spec`, and
+`$to-tickets` keep their existing ownership and stop boundaries.
+
+## Implement Context
+
+- A direct request is implemented by root in the current context.
+- One executable ticket launches exactly one fresh `implementer` child. Root
+  supplies the complete ticket, Parent PRD, applicable repository policy, and
+  bounded write scope; verifies the child identity and completed wait; and
+  remains the only Git owner.
+- Multiple executable tickets are graph work and remain owned by
+  `$tickets-orchestrator`.
+
+Children do not talk to the user, spawn grandchildren, or perform Git actions.
+Root integrates only isolated worker output and never overwrites unrelated work.
+
+## TDD, Proof, And Review
+
+Use [`$tdd`](../../skills/tdd/SKILL.md) where possible: an observable behavior
+change has a natural public seam and a meaningful failing signal can precede
+the implementation. Otherwise use direct proof. Do not manufacture tests for
+docs, copy, formatting, mechanical config, deletion, or an outcome that cannot
+fail meaningfully before the edit.
+
+A change is substantial when its behavior or contract goes beyond an obvious
+local edit. This includes a public API, persistence, auth or payment,
+concurrency or shared state, and cross-module interaction. Substantial settled
+work launches one fresh `spec_reviewer` and one fresh `standards_reviewer` in
+parallel. Spec checks the result against the request, issue, or Parent PRD;
+Standards checks correctness, repository rules, cleanup, and legacy or duplicate
+ownership.
+
+The wait must complete and the coordinator must approve the settled diff from
+the completed independent evidence.
+Docs, copy, formatting, mechanical config, and an obvious local correction may
+finish with direct proof and no reviewer. Reviewer failure or timeout blocks
+approval; root does not replace independent review with self-review.
+
+A Review blocker requires a concrete defect or proof gap causally linked to an
+explicit obligation, existing invariant, or mandatory repository rule. The
+reviewer verdict is evidence, not authority: coordinator approval exists when
+the completed independent review has no verified blocker or required-proof
+gap. A Fowler smell, general improvement, preference, or uncertain concern is a
+non-blocking observation without that link. Review remains read-only. Initial
+Review runs both lenses; targeted Review runs only the affected lens, or both
+when the repair is mixed or cannot be isolated.
+
+For direct or single-ticket substantial work, Implement consolidates every
+verified blocker into one repair batch for that revision. The original
+Implement authority covers every verified repair that does not widen the
+authorized outcome without another user
+confirmation. After repair it reruns affected proof and launches the affected
+fresh reviewer or reviewer pair over only the repair delta, repaired blockers,
+direct impact cone, and affected proof. Untouched previously approved scope
+retains approval. This loop continues until approval; reviewer count is not a
+stop condition. A complete two-lens Review repeats only when repair impact
+cannot be isolated from previously approved scope.
+
+Graph children receive no per-ticket delivery Review. After every checkpoint,
+Tickets Orchestrator owns the initial cumulative review over the complete Parent
+range, then follows the same unlimited repair loop with targeted Review of each
+repair delta and directly affected Parent obligations.
+
+Proof and applicable review must approve before staging or commit. Direct and
+single-ticket Implement creates one scoped local commit by default when the
+worktree is isolatable. Explicit user or repository policy that forbids or
+reserves Git overrides that default. Push and PR always require separate
+authority.
+
+## Stable Roles
+
+Skills request only these stable roles; concrete model and reasoning effort are
+central configuration details:
+
+| Need | Role |
 | --- | --- |
-| Tiny, clear, low-risk edit | `$small-task-implementer` after its Fit Gate |
-| Clear feature or fix | Apply the TDD Fit Gate; when it fits, use Root + one `$tdd` activation, otherwise affected validation |
-| Missing execution detail | `$implementation-spec-maker` -> artifact review -> `$spec-implementer` |
-| Approved implementation spec | `$spec-implementer` |
-| Approved dependency graph or explicit orchestration | `$tickets-orchestrator` |
-| Product discovery or ticket decomposition | `$to-spec`, `$spec-to-tickets`, or `$wayfinder` as applicable; stop before delivery |
-| Explain-only bug | `$bug-root-cause-explainer`; no edits |
-| Confirmed bounded bug fix | Apply the TDD Fit Gate, then `$tdd` + `$code-debugger` when it fits; otherwise `$code-debugger` + affected validation |
-| Hard, flaky, unclear, or performance bug | `$diagnosing-bugs` before the explain/fix route |
-| Review request | `$code-review` in the profile-selected reviewer child |
-| External multi-source uncertainty | `$research`; narrow documentation lookup stays inline |
-| Commit request | `$commit`; push/PR still require separate authority |
-
-Generated planning artifacts and labels never authorize implementation. One
-deterministic approved ticket may run directly; a graph follows the authorized
-delivery workflow.
-
-## TDD And Review
-
-Apply `$tdd` only when all three Fit Gate conditions hold:
-
-1. The change alters observable behavior.
-2. A natural public seam can prove that behavior.
-3. A new test will fail before the change for the intended behavioral reason.
-
-Otherwise use existing regression tests plus affected validation. Do not invoke
-TDD merely because implementation files change, and do not manufacture RED
-tests for behavior-preserving cleanup, dead-code deletion, documentation, copy,
-formatting, generated assets, package maintenance, simple config, builds, or
-read-only work. For mixed tasks, activate `$tdd` only for the behavioral slice.
-An absence or architecture guard added after cleanup is validation, not a TDD
-cycle.
-
-Review applicability lives in [`review-gates.md`](review-gates.md). Shared
-Full/Closure mechanics live in [`review-protocol.md`](review-protocol.md).
-Artifact review is owned by
-[`implementation-spec-review/references/review-loop.md`](../../skills/implementation-spec-review/references/review-loop.md);
-approved-spec implementation review is owned by
-[`spec-implementer/references/review-loop.md`](../../skills/spec-implementer/references/review-loop.md).
-
-Root never substitutes self-review for a required independent reviewer. Use one
-`reviewer_fast` for `simple`, one `reviewer_standard` for `medium`, and two
-disjoint `reviewer_deep` tracks for `high`. A reviewer Adapter executes inline
-only after it is already inside that assigned child.
-
-## Delegation
-
-Run work inline by default. Delegate only when the user, an invoked skill, or
-repository policy authorizes it and the task benefits from independent review,
-isolated deep analysis, or disjoint implementation ownership.
-
-| Need | Named role |
-| --- | --- |
-| Mechanical inventory | `explorer_quick` |
-| Bounded cross-module trace | `explorer_fast` |
-| Ambiguous architecture, contract, or cause | `analyst_deep` |
-| Primary-source external research | `researcher_standard` |
-| Independent review | `reviewer_fast`, `reviewer_standard`, or `reviewer_deep` by profile |
-| Approved isolated implementation slice | `implementer_standard`; `implementer_deep` only for material uncertainty |
-
-Keep the root critical path local. Use at most two explorers for disjoint
-questions and at most two parallel implementers with disjoint write scopes.
-Children do not conduct user dialogue or spawn grandchildren.
-
-## Validation And Runtime Safety
-
-Use targeted behavior proof plus the smallest affected integration check for
-simple and medium work. Run a full repository suite only when repository policy
-requires it, a broad shared contract cannot be isolated, or the task is `high`.
-
-For Flutter UI, follow [`tool-usage.md`](tool-usage.md): platform QA owns UI
-work and `$flutter-attach-session` is only the attach-safe runtime layer. Treat
-live app, IDE, VM Service, and `flutter run` sessions as user-owned.
-
-Read local evidence before external search: applicable `AGENTS.md`, `CONTEXT.md`,
-ADRs, manifests, lockfiles, tests, scripts, and code owners. Mark missing facts
-unconfirmed rather than inventing them.
-
-Contract-risk implementation uses
-[`contract-test-ledger.md`](contract-test-ledger.md) only for material
-invariants. Long framework lenses, examples, and recipes remain skill-local and
-load on demand.
+| Root dialogue, integration, and Git ownership | `root` |
+| One isolated executable ticket | `implementer` |
+| Requirement fidelity and scope drift | `spec_reviewer` |
+| Correctness and repository standards | `standards_reviewer` |
+| Bounded repository exploration | `explorer` |
+| Independent bounded design alternative | `explorer` |
+| Primary-source external research | `researcher` |
+
+## Runtime Safety
+
+For Flutter UI, follow [`tool-usage.md`](tool-usage.md). Treat live app, IDE, VM
+Service, and `flutter run` sessions as user-owned. Use the documented
+non-destructive attach path only after ownership discovery; never replace or
+terminate a user-owned session without explicit authority.

package/internal-workflow/docs/agents/tool-usage.md

@@ -4,13 +4,13 @@
 
 Local Flutter UI work always uses a platform QA skill plus the runtime ownership gate:
 
-- Android emulator: use `$flutter-android-debug` as the lifecycle orchestrator and
-  `test-android-apps:android-emulator-qa` for navigation, interaction, UI trees,
-  screenshots, and logcat.
+- Android emulator: always use `$flutter-android-debug` as the lifecycle orchestrator
+  and `test-android-apps:android-emulator-qa` for navigation, interaction, UI trees,
+  screenshots, and logcat, including inspection-only and screenshot-only requests.
 - iOS Simulator: use `$flutter-ios-debug` for environment/login gates, navigation,
   interaction, screenshots, and visual comparison.
-- Use `$flutter-attach-session` only to discover the runtime owner and perform
-  reload/restart when that session is safe for this agent to control.
+- Use `$flutter-attach-session` to discover the runtime owner and perform
+  reload/restart against the selected live session.
 
 Before any install, launch, attach, reload, restart, terminate, or force-stop:
 
@@ -18,17 +18,28 @@ Before any install, launch, attach, reload, restart, terminate, or force-stop:
    owner, and expected backend/environment.
 2. Treat any live PID, VM Service, IDE debug adapter, `flutter run`, or visible app as
    user-owned state.
-3. If an IDE/debug adapter or machine run owns DevFS, do not create a second attach
-   controller. Use the owning IDE/terminal reload action or ask the user to trigger it.
-   A standalone interactive terminal run is the only exception, and only when
-   discovery marks it attach-safe and the helper receives its confirmed PID.
+3. If an IDE/debug adapter or machine run owns DevFS, never attach a second Flutter
+   compiler/controller. Preserve the session, continue only with inspection or in-app
+   navigation, and ask the user to trigger `r`/`R` through the owning controller when
+   reload/restart is necessary. Unknown owners remain blocked.
 4. Use `r` for widget/layout/style/rendering changes and `R` for startup state,
    dependency injection, providers, globals, routes, or initialization changes.
-5. For a safely attachable standalone runtime, pass the PID confirmed by
-   `discover --json` as `--expected-pid`; never execute the raw discovered attach command.
-6. Verify that the same PID and expected environment remain after each runtime or
+5. Always pass the PID confirmed by `discover --json` as `--expected-pid`; never
+   execute the raw discovered attach command.
+6. Confirm that the generated attach command preserves the selected run's effective
+   target and every `--dart-define` / `--dart-define-from-file`. Missing compile
+   identity must block runtime control rather than fall back to defaults.
+   Treat raw define values as sensitive; inspect only the helper's redacted display.
+7. Verify that the same PID and expected environment remain after each runtime or
    navigation action.
 
+The bundled `flutter_session_ctl.py` helper is the only allowed reload/restart
+transport for safely attachable standalone sessions. Never activate, open, focus, or
+automate an IDE for this purpose. Do not use IDE menus, Command Palette, keyboard
+shortcuts, `osascript`, System Events, or other GUI automation. If the helper fails or
+times out, preserve the app process and report its exact failure; do not fall back to
+the IDE.
+
 Requests to inspect, debug, navigate, capture screenshots, or verify UI do not authorize
 build/install, uninstall, app-data clearing, force-stop, process termination, replacement
 launch, or a new `flutter run`. Use those only when no live target exists and the user

package/internal-workflow/manifest.json

@@ -1 +1 @@
-{"evals":{"shared/coding-skill-evals":{"owner":null,"path":"evals/coding-skill-evals.json"},"skill/implementation-spec-review":{"owner":"implementation-spec-review","path":"skills/implementation-spec-review/evals/evals.json"},"skill/spec-implementer":{"owner":"spec-implementer","path":"skills/spec-implementer/evals/evals.json"},"skill/tdd":{"owner":"tdd","path":"skills/tdd/evals/evals.json"}},"files":[{"mode":420,"path":"docs/agents/bug-workflow-routing.md","sha256":"a37c59676bcb8b938a7c82bce8a6ea5becf58ba367866d2712cd469391aea931","size":1603},{"mode":420,"path":"docs/agents/bugfix-quality-gate.md","sha256":"caaed6c923adfe56f4b6dd89222a83493ef4dd4e8bdd2bad694f8a11f93541ae","size":709},{"mode":420,"path":"docs/agents/coding-skill-routing.md","sha256":"958f4e7c7177c062b2a24fb7db2287be2cfa6e5281f2d156f7eb67b6cb3a0741","size":6434},{"mode":420,"path":"docs/agents/confidence-rubric.md","sha256":"42c947db2775380867e7adcfbdbe0f67b8f511b9ddf33a6eef8e1b0e995912c2","size":1883},{"mode":420,"path":"docs/agents/contract-test-ledger.md","sha256":"37424d9dac94f143c0485efc81c85be3806551149c33b4ea9a5e1db2305f0031","size":4424},{"mode":420,"path":"docs/agents/review-gates.md","sha256":"5ca48066b263cf869549c383814cfbdbbad711e5c247a8253bc2996d8fdec496","size":1857},{"mode":420,"path":"docs/agents/review-protocol.md","sha256":"9af5b44c545d76f3a048de424a4ccc78aa7e018bd193e4e5a787b2cef47af071","size":4086},{"mode":420,"path":"docs/agents/tool-usage.md","sha256":"b6ade11865a46a5a28d4823c1b70318453f4d350cfc62d2969aa06d73c47be4b","size":4321},{"mode":420,"path":"evals/coding-skill-evals.json","sha256":"83bdb0333546d2553637916879d8aee0a54cbaa102ac5c7e369e02193b084315","size":18943},{"mode":420,"path":"operations/acceptance-proof/SKILL.md","sha256":"c33a04bf8dfcb59982f60b232633b0e48e9de4ec375cd02f52ec71f9fce30de6","size":440},{"mode":420,"path":"operations/ambiguity-review/SKILL.md","sha256":"20371f30015afef12a2b9dd608d21cc93a93f011873927f7a64e29b36a4fcf99","size":427},{"mode":420,"path":"operations/code-review/SKILL.md","sha256":"c415e4383dd7ddeb4b371a0a141a39c4296d95222b26ca3fcc51a34704e10f25","size":1246},{"mode":420,"path":"operations/implementation/SKILL.md","sha256":"6f0c9b900d252d9a833d7fdac6868d84900787debf2964e22ffbf86851af45d2","size":1461},{"mode":420,"path":"operations/qualification-repair/SKILL.md","sha256":"b038a0ff20d9cdbb0dbdfc80f72c9d5bd7dd08f07021f97c91176e2d03900680","size":955},{"mode":420,"path":"operations/spec-author/SKILL.md","sha256":"5170f275bd7bc346578028d74d5814a5edd36ccd90d0615c4d5e3d6b6f8af049","size":627},{"mode":420,"path":"operations/spec-review/SKILL.md","sha256":"6cb7b8ea245faa2587ebde07ebe3d364eff41d18d5464ccd2749cf2b9b49f701","size":653},{"mode":420,"path":"operations/triage/SKILL.md","sha256":"39e8301b90a59795dc2b93917d4674c22dc3e4380f011a54ade1de4c7cdc18ae","size":647},{"mode":420,"path":"profiles/analyst_deep.toml","sha256":"06335e3a13b07ef3d7deb9b546a6dad5d765edfa6dbf21c1c4d516e843a4352f","size":380},{"mode":420,"path":"profiles/implementer_standard.toml","sha256":"4074f45ea6fb615382de7ddf04e4ab824185e01932290b95764ff63a3711824e","size":750},{"mode":420,"path":"profiles/proof_agent.toml","sha256":"2fbaf1145a11cb5c574bf1ed7333187d284ed0c3c3d6260c628f82057b8b04e7","size":446},{"mode":420,"path":"profiles/reviewer_deep.toml","sha256":"15ef121b641265a85d0647c46f6dd93d4a9abd8c09bcc746c41e4ca6b4c9af41","size":648},{"mode":420,"path":"profiles/reviewer_standard.toml","sha256":"0a26b24f98b7e8d0ec049cb6fbe623d5da838b2fe71b5accd59bf364a9c97e5c","size":585},{"mode":420,"path":"schemas/ambiguity-review-v1.json","sha256":"48d946ad8e91bd1908d8993ef631b1701ad3cd7a79f34368a07942d7774afeff","size":524},{"mode":420,"path":"schemas/code-review-v1.json","sha256":"b11b266e0a7e0aa19eaf90ebf2b5c33f3bc7263e9c697cbf206e9865084e3439","size":2555},{"mode":420,"path":"schemas/implementation-report-v1.json","sha256":"a1b580dad03af9be74d895d38a2f6aa9398b6d772c944dc398dac5aca0630d2e","size":1573},{"mode":420,"path":"schemas/proof-report-v1.json","sha256":"50d5c610aba30a8d2c5b2fe3f15d235509f8f4e239becbef77529a7eb7a3b570","size":21167},{"mode":420,"path":"schemas/spec-author-v1.json","sha256":"49f945362d1184ad628584b91fbbe75323d13bafa4ca3876093387a9fca06214","size":420},{"mode":420,"path":"schemas/spec-review-v1.json","sha256":"fe9fdd389bcb4c3b7d19609184caf3af4b89e7c1d1e71a7ba0c55c72c5d5562d","size":1386},{"mode":420,"path":"schemas/triage-route-v1.json","sha256":"3ca7ed29237f42e12567797d145d90dd4f1f48fa1e81a7da67434c19747753d8","size":5894},{"mode":420,"path":"skills/acceptance-proof/SKILL.md","sha256":"6f2d85dfebfd47b2ec7ede95f2e02417b3f0ad860d333360b040d31e3c609525","size":1777},{"mode":420,"path":"skills/acceptance-proof/agents/openai.yaml","sha256":"d602d9f2e1bf618a71171729c6f354dd137c939cb433bd49afec678360e1189f","size":265},{"mode":420,"path":"skills/acceptance-proof/references/android.md","sha256":"b62fea63f53f79a8978df81608a7c1f48fa9f06084fba8382904a8f8c8dff9bc","size":2940},{"mode":420,"path":"skills/acceptance-proof/references/browser.md","sha256":"ceefa4fd7db475b6162368511c2742b6d9c6af58d48e7d5d8a773ed5cc3938c4","size":2281},{"mode":420,"path":"skills/acceptance-proof/references/ios.md","sha256":"ae18be2632e1f7c3aa0810a1bafafc7760c807b30b1269408825aa14c224d493","size":2486},{"mode":420,"path":"skills/acceptance-proof/tools/ios-lease.mjs","sha256":"6e1e0d95c6a8b2d42c34de05bd4446eac23e3916bffccb027f236b8a8a1809a3","size":13834},{"mode":420,"path":"skills/agent-auto/SKILL.md","sha256":"450c28f7a712f881cdf9f3e48555a47022b46f79df875bac35843a1c15135451","size":1415},{"mode":420,"path":"skills/agent-auto/agents/openai.yaml","sha256":"79a70421300891e3130fc7535c4aa37e01931ff353fbd7b83262c6fcf2032b71","size":266},{"mode":420,"path":"skills/code-debugger/SKILL.md","sha256":"914cf2a1a9971d5d932954b908fbf3fcfea040d46b4d612c2e7932979256bb88","size":7692},{"mode":420,"path":"skills/code-debugger/agents/openai.yaml","sha256":"8dd2f301bee632585371bd6f62dbdcdec95201f553392515342da5d0fc563305","size":322},{"mode":420,"path":"skills/code-review/SKILL.md","sha256":"8b3b2f28e6eea29a2a5abd4e0fa6dce9cf1e81d9a642403254dd0ab12e4df67f","size":17541},{"mode":420,"path":"skills/code-review/agents/openai.yaml","sha256":"c2697212427a5e119d9127e2f9000594e6c2eb7696e7a40604da7149c79ce478","size":278},{"mode":420,"path":"skills/code-review/references/bug-classes.md","sha256":"1f8648af9914cbd7553d045915f959df0f3b50a88e97c3beefeb955342e7b12d","size":4062},{"mode":420,"path":"skills/code-review/references/cleanup-lens.md","sha256":"6406350bf8ff00f9d2de2d5a8871aa1a9ab0efa33dcc35453eeebe9c96623e69","size":2846},{"mode":420,"path":"skills/code-review/references/framework-lenses.md","sha256":"ca9e7cb09f32f729cec5522e8ff7c7dcc43f76ef986e701e9c0a226514912cd8","size":1820},{"mode":420,"path":"skills/code-review/references/targeted-recipes.md","sha256":"921b422958c97e606637d3fa2d2628239d9176f0316c7e45bbc55b20a22fe3c1","size":2564},{"mode":420,"path":"skills/diagnosing-bugs/SKILL.md","sha256":"9a3457d4f12e3810041def93456a0c020df0842200737bf7ecaf06471991c16c","size":9097},{"mode":420,"path":"skills/diagnosing-bugs/agents/openai.yaml","sha256":"eca84840bc193ce63cc7aad93d9e7b5f2541739b7bf682e5fa9eded3a8060787","size":262},{"mode":420,"path":"skills/diagnosing-bugs/scripts/hitl-loop.template.sh","sha256":"b2932630950e5210075bcd6f850e5accf30c101c5367b29eac3a29b4dd8084c8","size":1164},{"mode":420,"path":"skills/implementation-spec-maker/SKILL.md","sha256":"8148a41ad05e4a2c42a79ec4d056f635e2f21cff0bb1676995a507fd9dce2ead","size":9783},{"mode":420,"path":"skills/implementation-spec-maker/agents/openai.yaml","sha256":"5e9988125a4b69ec62ddfdb141793bebf8e117188d3c9c841031a0020b6d0b8e","size":421},{"mode":420,"path":"skills/implementation-spec-maker/references/source-modes.md","sha256":"e110ae155809d79b7ee3d1c84b121d015222822f4b0f6d74beff3d28f9639d17","size":2145},{"mode":420,"path":"skills/implementation-spec-maker/references/spec-template.md","sha256":"0ba380125eb2e0c114aed6b0f064ac2643edf75bb78c10de72b741776edee6ff","size":5319},{"mode":420,"path":"skills/implementation-spec-review/SKILL.md","sha256":"333ff2e71a6400afbc5a617483067c7d42972788880266d2b5746697dba4714a","size":7152},{"mode":420,"path":"skills/implementation-spec-review/agents/openai.yaml","sha256":"600f9cc4e4f42596e3bf48601a508ddf055efcc396478d5e339d024973f4fb05","size":277},{"mode":420,"path":"skills/implementation-spec-review/evals/evals.json","sha256":"eedf8e60e6eb03e8266f15e88ea099b0709a3e8323133499ecaf7ec3c3efa10c","size":5360},{"mode":420,"path":"skills/implementation-spec-review/references/review-loop.md","sha256":"914e8adf57a1ea400a217e10658aae2fcb79aa198e2653d93406636705988867","size":5829},{"mode":420,"path":"skills/small-task-implementer/SKILL.md","sha256":"a246daa00f5d6c2f20b661f689562627d611738961480c884ec944f8ce46f56f","size":4755},{"mode":420,"path":"skills/small-task-implementer/agents/openai.yaml","sha256":"948c51d9f8026732d3c78f3f590e48ecdd924a9c25fafa72aaeaf20f873cf17a","size":329},{"mode":420,"path":"skills/spec-implementer/SKILL.md","sha256":"007489dd287a705ee69b30ac931f240452b166f4e5c158ec77a7b1c23e4f97d2","size":5924},{"mode":420,"path":"skills/spec-implementer/agents/openai.yaml","sha256":"84ef664ae3538e264fe6746917f081d34eac0738dc28764ddf27d7a448b3615d","size":341},{"mode":420,"path":"skills/spec-implementer/evals/evals.json","sha256":"23d73ddd6e2205b601a36cd07a7dd5ee228ae587d5b9cc5adab9b0993a312ba8","size":1361},{"mode":420,"path":"skills/spec-implementer/references/review-loop.md","sha256":"6f6c088daf1c4fcb9811583ddfdfb9d0357e924fba8a6ef1662faa4b533f499f","size":4713},{"mode":420,"path":"skills/tdd/SKILL.md","sha256":"ed184bb3f12b527c3dd25d3c4cdecbbe549ae5c5781ecb52929435524836eeec","size":4200},{"mode":420,"path":"skills/tdd/agents/openai.yaml","sha256":"cc49a11a2c08733862d1a406123cda7a050d4a70fa92a4b3ec37f318694b1581","size":301},{"mode":420,"path":"skills/tdd/evals/evals.json","sha256":"8c16ca88cdd4556c803e267dfd8ea82fab11aae7ae9959277bab8bab6f093031","size":692},{"mode":420,"path":"skills/tdd/interface-design.md","sha256":"764c5ff0e3fa6b4ab7095eb65ccc7201e090baf19fa16051dfdb72c06d27417d","size":653},{"mode":420,"path":"skills/tdd/mocking.md","sha256":"e26596e305ce4c56ee4c31f166a4eb37ce289ac6ef0ce4c7aadfa41ce0bf8191","size":519},{"mode":420,"path":"skills/tdd/refactoring.md","sha256":"b05bcb10cfa43c7053abba2984c80c486afc10ef9ab180689427f56c86068fe6","size":362},{"mode":420,"path":"skills/tdd/tests.md","sha256":"6773173a074569b2e51653bd7b95c097d602dbb4815d1cf1c87344705c4e0d1c","size":2228},{"mode":420,"path":"skills/triage/AGENT-BRIEF.md","sha256":"053cd013e1c2c9275111aa6e4b5a12e9838f8d6cd888e8ca0ccaaac576fd74df","size":7070},{"mode":420,"path":"skills/triage/OUT-OF-SCOPE.md","sha256":"8ed8cf27833444060c81b3961a83c0e3d8e6cf2fcb2ddf6f8b07c6655cbb0d85","size":4282},{"mode":420,"path":"skills/triage/SKILL.md","sha256":"5c7c84189fd5146ec1ae55a5669c74372ed7bce588fa7b8523417aa55b312a2e","size":8273},{"mode":420,"path":"skills/triage/agents/openai.yaml","sha256":"466bc430f95132bc6b28d077d50865d4b1fd9218307582343c35b0baf66d7894","size":283}],"generationHash":"6f066ad7c94bff761c9e4ccda31f14c4eeffd51e95f1f23a608d5c528d6bc3e7","operations":{"acceptance-proof":{"dependencySkills":[],"entry":"operations/acceptance-proof/SKILL.md","files":["operations/acceptance-proof/SKILL.md","profiles/proof_agent.toml","schemas/proof-report-v1.json","skills/acceptance-proof/SKILL.md","skills/acceptance-proof/agents/openai.yaml","skills/acceptance-proof/references/android.md","skills/acceptance-proof/references/browser.md","skills/acceptance-proof/references/ios.md","skills/acceptance-proof/tools/ios-lease.mjs"],"id":"acceptance-proof","outputSchema":"schemas/proof-report-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"proof-only","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["worktree"]},"profile":"proof_agent","resources":[],"sourceSkill":"acceptance-proof"},"ambiguity-review":{"dependencySkills":[],"entry":"operations/ambiguity-review/SKILL.md","files":["docs/agents/confidence-rubric.md","operations/ambiguity-review/SKILL.md","profiles/reviewer_deep.toml","schemas/ambiguity-review-v1.json"],"id":"ambiguity-review","outputSchema":"schemas/ambiguity-review-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"report-only","sandboxMode":"read-only","worktreeAccess":"read-only","writableRootClasses":[]},"profile":"reviewer_deep","resources":["docs/agents/confidence-rubric.md"],"sourceSkill":null},"code-review":{"dependencySkills":[],"entry":"operations/code-review/SKILL.md","files":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md","docs/agents/review-gates.md","docs/agents/review-protocol.md","operations/code-review/SKILL.md","profiles/reviewer_standard.toml","schemas/code-review-v1.json","skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/bug-classes.md","skills/code-review/references/cleanup-lens.md","skills/code-review/references/framework-lenses.md","skills/code-review/references/targeted-recipes.md"],"id":"code-review","outputSchema":"schemas/code-review-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"report-only","sandboxMode":"read-only","worktreeAccess":"read-only","writableRootClasses":[]},"profile":"reviewer_standard","resources":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md","docs/agents/review-gates.md","docs/agents/review-protocol.md"],"sourceSkill":"code-review"},"implementation":{"dependencySkills":["code-debugger","diagnosing-bugs","small-task-implementer","tdd"],"entry":"operations/implementation/SKILL.md","files":["docs/agents/bug-workflow-routing.md","docs/agents/coding-skill-routing.md","docs/agents/contract-test-ledger.md","docs/agents/review-gates.md","docs/agents/tool-usage.md","operations/implementation/SKILL.md","profiles/implementer_standard.toml","schemas/implementation-report-v1.json","skills/agent-auto/SKILL.md","skills/agent-auto/agents/openai.yaml","skills/code-debugger/SKILL.md","skills/code-debugger/agents/openai.yaml","skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh","skills/small-task-implementer/SKILL.md","skills/small-task-implementer/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"id":"implementation","outputSchema":"schemas/implementation-report-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"change-set","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["worktree"]},"profile":"implementer_standard","resources":["docs/agents/bug-workflow-routing.md","docs/agents/coding-skill-routing.md","docs/agents/contract-test-ledger.md","docs/agents/review-gates.md","docs/agents/tool-usage.md"],"sourceSkill":"agent-auto"},"qualification-repair":{"dependencySkills":["code-debugger","diagnosing-bugs","tdd"],"entry":"operations/qualification-repair/SKILL.md","files":["operations/qualification-repair/SKILL.md","profiles/implementer_standard.toml","schemas/implementation-report-v1.json","skills/code-debugger/SKILL.md","skills/code-debugger/agents/openai.yaml","skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"id":"qualification-repair","outputSchema":"schemas/implementation-report-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"change-set","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["worktree"]},"profile":"implementer_standard","resources":[],"sourceSkill":null},"spec-author":{"dependencySkills":[],"entry":"operations/spec-author/SKILL.md","files":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md","operations/spec-author/SKILL.md","profiles/implementer_standard.toml","schemas/spec-author-v1.json","skills/implementation-spec-maker/SKILL.md","skills/implementation-spec-maker/agents/openai.yaml","skills/implementation-spec-maker/references/source-modes.md","skills/implementation-spec-maker/references/spec-template.md"],"id":"spec-author","outputSchema":"schemas/spec-author-v1.json","policy":{"approvalCeiling":"never","cwdClass":"target-state","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"spec-only","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["target-state"]},"profile":"implementer_standard","resources":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md"],"sourceSkill":"implementation-spec-maker"},"spec-review":{"dependencySkills":[],"entry":"operations/spec-review/SKILL.md","files":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md","docs/agents/review-protocol.md","operations/spec-review/SKILL.md","profiles/reviewer_deep.toml","schemas/spec-review-v1.json","skills/implementation-spec-review/SKILL.md","skills/implementation-spec-review/agents/openai.yaml","skills/implementation-spec-review/references/review-loop.md"],"id":"spec-review","outputSchema":"schemas/spec-review-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"report-only","sandboxMode":"read-only","worktreeAccess":"read-only","writableRootClasses":[]},"profile":"reviewer_deep","resources":["docs/agents/confidence-rubric.md","docs/agents/contract-test-ledger.md","docs/agents/review-protocol.md"],"sourceSkill":"implementation-spec-review"},"triage":{"dependencySkills":[],"entry":"operations/triage/SKILL.md","files":["docs/agents/coding-skill-routing.md","operations/triage/SKILL.md","profiles/analyst_deep.toml","schemas/triage-route-v1.json","skills/triage/AGENT-BRIEF.md","skills/triage/OUT-OF-SCOPE.md","skills/triage/SKILL.md","skills/triage/agents/openai.yaml"],"id":"triage","outputSchema":"schemas/triage-route-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"report-only","sandboxMode":"read-only","worktreeAccess":"read-only","writableRootClasses":[]},"profile":"analyst_deep","resources":["docs/agents/coding-skill-routing.md"],"sourceSkill":"triage"}},"profiles":{"analyst_deep":"profiles/analyst_deep.toml","implementer_standard":"profiles/implementer_standard.toml","proof_agent":"profiles/proof_agent.toml","reviewer_deep":"profiles/reviewer_deep.toml","reviewer_standard":"profiles/reviewer_standard.toml"},"skills":{"acceptance-proof":{"entry":"skills/acceptance-proof/SKILL.md","files":["skills/acceptance-proof/SKILL.md","skills/acceptance-proof/agents/openai.yaml","skills/acceptance-proof/references/android.md","skills/acceptance-proof/references/browser.md","skills/acceptance-proof/references/ios.md","skills/acceptance-proof/tools/ios-lease.mjs"],"metadata":"skills/acceptance-proof/agents/openai.yaml"},"agent-auto":{"entry":"skills/agent-auto/SKILL.md","files":["skills/agent-auto/SKILL.md","skills/agent-auto/agents/openai.yaml"],"metadata":"skills/agent-auto/agents/openai.yaml"},"code-debugger":{"entry":"skills/code-debugger/SKILL.md","files":["skills/code-debugger/SKILL.md","skills/code-debugger/agents/openai.yaml"],"metadata":"skills/code-debugger/agents/openai.yaml"},"code-review":{"entry":"skills/code-review/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/bug-classes.md","skills/code-review/references/cleanup-lens.md","skills/code-review/references/framework-lenses.md","skills/code-review/references/targeted-recipes.md"],"metadata":"skills/code-review/agents/openai.yaml"},"diagnosing-bugs":{"entry":"skills/diagnosing-bugs/SKILL.md","files":["skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh"],"metadata":"skills/diagnosing-bugs/agents/openai.yaml"},"implementation-spec-maker":{"entry":"skills/implementation-spec-maker/SKILL.md","files":["skills/implementation-spec-maker/SKILL.md","skills/implementation-spec-maker/agents/openai.yaml","skills/implementation-spec-maker/references/source-modes.md","skills/implementation-spec-maker/references/spec-template.md"],"metadata":"skills/implementation-spec-maker/agents/openai.yaml"},"implementation-spec-review":{"entry":"skills/implementation-spec-review/SKILL.md","files":["skills/implementation-spec-review/SKILL.md","skills/implementation-spec-review/agents/openai.yaml","skills/implementation-spec-review/references/review-loop.md"],"metadata":"skills/implementation-spec-review/agents/openai.yaml"},"small-task-implementer":{"entry":"skills/small-task-implementer/SKILL.md","files":["skills/small-task-implementer/SKILL.md","skills/small-task-implementer/agents/openai.yaml"],"metadata":"skills/small-task-implementer/agents/openai.yaml"},"spec-implementer":{"entry":"skills/spec-implementer/SKILL.md","files":["skills/spec-implementer/SKILL.md","skills/spec-implementer/agents/openai.yaml","skills/spec-implementer/references/review-loop.md"],"metadata":"skills/spec-implementer/agents/openai.yaml"},"tdd":{"entry":"skills/tdd/SKILL.md","files":["skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/tdd/agents/openai.yaml"},"triage":{"entry":"skills/triage/SKILL.md","files":["skills/triage/AGENT-BRIEF.md","skills/triage/OUT-OF-SCOPE.md","skills/triage/SKILL.md","skills/triage/agents/openai.yaml"],"metadata":"skills/triage/agents/openai.yaml"}},"sourceFingerprint":"06f1a4ee3020139e29e0025f0db0e413fb97530885911649a7effc779975c776","version":2}
+{"evals":{"skill/bug-root-cause-explainer":{"owner":"bug-root-cause-explainer","path":"skills/bug-root-cause-explainer/evals/evals.json"},"skill/code-review":{"owner":"code-review","path":"skills/code-review/evals/evals.json"},"skill/diagnosing-bugs":{"owner":"diagnosing-bugs","path":"skills/diagnosing-bugs/evals/evals.json"},"skill/grilling":{"owner":"grilling","path":"skills/grilling/evals/evals.json"},"skill/implement":{"owner":"implement","path":"skills/implement/evals/evals.json"},"skill/plan":{"owner":"plan","path":"skills/plan/evals/evals.json"},"skill/prototype":{"owner":"prototype","path":"skills/prototype/evals/evals.json"},"skill/research":{"owner":"research","path":"skills/research/evals/evals.json"},"skill/tdd":{"owner":"tdd","path":"skills/tdd/evals/evals.json"},"skill/tickets-orchestrator":{"owner":"tickets-orchestrator","path":"skills/tickets-orchestrator/evals/evals.json"},"skill/to-spec":{"owner":"to-spec","path":"skills/to-spec/evals/evals.json"},"skill/to-tickets":{"owner":"to-tickets","path":"skills/to-tickets/evals/evals.json"}},"files":[{"mode":420,"path":"docs/agents/bug-workflow-routing.md","sha256":"96c35629bdf29fcaf7114bc2835d4ef94ac08d77ae218496c12c2a4e2419734b","size":1709},{"mode":420,"path":"docs/agents/bugfix-quality-gate.md","sha256":"caaed6c923adfe56f4b6dd89222a83493ef4dd4e8bdd2bad694f8a11f93541ae","size":709},{"mode":420,"path":"docs/agents/coding-skill-routing.md","sha256":"7ffc29b0d8bf7480d8e55bd1154ae266127ddfb73b80401f039343c750275486","size":9253},{"mode":420,"path":"docs/agents/confidence-rubric.md","sha256":"42c947db2775380867e7adcfbdbe0f67b8f511b9ddf33a6eef8e1b0e995912c2","size":1883},{"mode":420,"path":"docs/agents/tool-usage.md","sha256":"7e1f52fff6c2a9c573851d682cacf85ef7c22d67c00eb2667ca6f06ec5a6f9b0","size":5069},{"mode":420,"path":"operations/acceptance-proof/SKILL.md","sha256":"c33a04bf8dfcb59982f60b232633b0e48e9de4ec375cd02f52ec71f9fce30de6","size":440},{"mode":420,"path":"operations/code-review/SKILL.md","sha256":"5483d29364ab73d16fd28e8117fae17e300b7ea80235e3ceb5415b296b7defed","size":2594},{"mode":420,"path":"operations/implementation/SKILL.md","sha256":"61ca8965bfcfc5a57240e214727ddb2c59712761283edccbc8d93e50a2af68e6","size":1771},{"mode":420,"path":"profiles/implementer.toml","sha256":"3e3edd16fd54f810cb381e0c0c6e2933ce323267222a497fe8749d0f281e12b1","size":550},{"mode":420,"path":"profiles/review_coordinator.toml","sha256":"ef9197959946e141334c182897e3335d0243f05afd4ad81288a8481e0efd3795","size":681},{"mode":420,"path":"profiles/spec_reviewer.toml","sha256":"2dd198709c887f5b613461d4ae2b04405ff928cf566a43a731a5f51d67d745bb","size":770},{"mode":420,"path":"profiles/standards_reviewer.toml","sha256":"327c477315595dd50489873a05c7aa0c5ff51afb877bb0746d569ff4e33180fb","size":896},{"mode":420,"path":"schemas/code-review-v1.json","sha256":"756d7aecacb47f1a90d63933a8564fca3211a10bb929b804808c395c385499e1","size":2615},{"mode":420,"path":"schemas/implementation-report-v1.json","sha256":"70161d4afafabcc6544620a9e6021262738c26a7b62cfb18947e694603c89c21","size":1725},{"mode":420,"path":"schemas/proof-report-v1.json","sha256":"104db803c066e42ed5493fec7eecc7e3788fce622df33d5ad4016aba7946f8c8","size":21244},{"mode":420,"path":"skills/acceptance-proof/SKILL.md","sha256":"6f2d85dfebfd47b2ec7ede95f2e02417b3f0ad860d333360b040d31e3c609525","size":1777},{"mode":420,"path":"skills/acceptance-proof/agents/openai.yaml","sha256":"d602d9f2e1bf618a71171729c6f354dd137c939cb433bd49afec678360e1189f","size":265},{"mode":420,"path":"skills/acceptance-proof/references/android.md","sha256":"b62fea63f53f79a8978df81608a7c1f48fa9f06084fba8382904a8f8c8dff9bc","size":2940},{"mode":420,"path":"skills/acceptance-proof/references/browser.md","sha256":"ceefa4fd7db475b6162368511c2742b6d9c6af58d48e7d5d8a773ed5cc3938c4","size":2281},{"mode":420,"path":"skills/acceptance-proof/references/ios.md","sha256":"ae18be2632e1f7c3aa0810a1bafafc7760c807b30b1269408825aa14c224d493","size":2486},{"mode":420,"path":"skills/acceptance-proof/tools/ios-lease.mjs","sha256":"6e1e0d95c6a8b2d42c34de05bd4446eac23e3916bffccb027f236b8a8a1809a3","size":13834},{"mode":420,"path":"skills/bug-root-cause-explainer/SKILL.md","sha256":"972305d2d4231b6eb7b39196eb49bc167e0a7f89ab86918ef5ad71a34d9bda43","size":5474},{"mode":420,"path":"skills/bug-root-cause-explainer/agents/openai.yaml","sha256":"a65d3f3b50d38309ef54618e0c00f656ac17a5bee5cc5a5c5faf3bc10954caef","size":403},{"mode":420,"path":"skills/bug-root-cause-explainer/evals/evals.json","sha256":"a2783a1e6be8fd7ca5af3821379cff7a6b8565ae33a8ed194b38573eabba4414","size":656},{"mode":420,"path":"skills/code-review/SKILL.md","sha256":"a50c99dc1de7bbad8b78670f7dbb79bc4914f0a506affada59b8e6ace318671d","size":4861},{"mode":420,"path":"skills/code-review/agents/openai.yaml","sha256":"cfc3d99b7fbe8cfe04ac994acaacf11ae73dcf1da59dcd2c248d779d415c8413","size":314},{"mode":420,"path":"skills/code-review/evals/evals.json","sha256":"23183a3d13dff991df68b45897b10778ee97884a3cd909f7892ae4fffde7df98","size":3467},{"mode":420,"path":"skills/code-review/references/standards-smells.md","sha256":"e14cf49716f832ea9e6b43cadcac255b8cf3ffe0712b923e68c7c9a69d46a387","size":2408},{"mode":420,"path":"skills/diagnosing-bugs/SKILL.md","sha256":"95c48af453d9d99fbcd8ceb1335c1794d110d94a7783dec9185f41d71b7e21c6","size":11826},{"mode":420,"path":"skills/diagnosing-bugs/agents/openai.yaml","sha256":"0ae35c16a55e0efa5de2ac756e07a2b058c562a89c53e149145f5de1584e24e6","size":373},{"mode":420,"path":"skills/diagnosing-bugs/evals/evals.json","sha256":"9881149ebe47c9443ff8e7f2dcf02725d742a84806de6e33ec2ba49d31dbc2a2","size":2557},{"mode":420,"path":"skills/diagnosing-bugs/scripts/hitl-loop.template.sh","sha256":"b2932630950e5210075bcd6f850e5accf30c101c5367b29eac3a29b4dd8084c8","size":1164},{"mode":420,"path":"skills/grilling/SKILL.md","sha256":"ff7a5707e1320212c9f9bec18507566ce5eed0eee1a4990e9d09074ca76a335b","size":2552},{"mode":420,"path":"skills/grilling/agents/openai.yaml","sha256":"16acd9a4929237685beb879ad38e6235f02e11475cf2a865c443c4d50997c5d8","size":358},{"mode":420,"path":"skills/grilling/evals/evals.json","sha256":"30c3e7137d296156d74b69ee25640e43c82ae650f0f07ed76f12206b34124c39","size":1778},{"mode":420,"path":"skills/implement/SKILL.md","sha256":"f3c09dd6a68d721eb71b3ae9e8640749c4a4ba391dc7d06a6b0a98e3a9c23117","size":7439},{"mode":420,"path":"skills/implement/agents/openai.yaml","sha256":"2ef457435557419cb11139b4172813ee0ca711630df81a1192532c7e8cf8006e","size":266},{"mode":420,"path":"skills/implement/evals/evals.json","sha256":"d8ab1bd16d5143231e65213998f47bed516c772427f4aef8542b412287a469a0","size":6828},{"mode":420,"path":"skills/plan/SKILL.md","sha256":"d551fbe3eeedbd2b45e2a5053a3c15e55d991f4189943d8c3d308629966a5908","size":2874},{"mode":420,"path":"skills/plan/agents/openai.yaml","sha256":"8fffc0a16f3577c93988233529a671db94a6dea55be0ae3fd29e7a6109ae13cf","size":311},{"mode":420,"path":"skills/plan/evals/evals.json","sha256":"4b35ca204b999ac81166f3300e9bfde2a57ca31f999881bd4ba3c1070d265e91","size":2263},{"mode":420,"path":"skills/prototype/LOGIC.md","sha256":"1a6a50011e81db9bf786eb98131d5125b4965681cc5c4d5db3b6dd2a39478c07","size":5828},{"mode":420,"path":"skills/prototype/SKILL.md","sha256":"b185dde586efa763c1fc5dec7b44ed54b0b02a07183e95d7658e5dea4d31424b","size":4027},{"mode":420,"path":"skills/prototype/UI.md","sha256":"39d6c54ad1ece13e87157dbb80fdfe7b627d21368d93889d787af6a9be3c1467","size":6798},{"mode":420,"path":"skills/prototype/agents/openai.yaml","sha256":"b84be88538b40eb72f6b819c939b11d92e29dcb2bed91fba7cd67a0ca6ac3bad","size":301},{"mode":420,"path":"skills/prototype/evals/evals.json","sha256":"7619c1c5b41c3c62c870c557623d49d788d6672828f887b31fff2ab3a390a82a","size":2928},{"mode":420,"path":"skills/research/SKILL.md","sha256":"3effbfd0db25f32330fc34887e6c553b2b062ca605f0df98462a207df44b1373","size":4757},{"mode":420,"path":"skills/research/agents/openai.yaml","sha256":"4475cf777225f81a1c45937389d55f2b485b039b36e8378ef6b001e24f3fd1fe","size":254},{"mode":420,"path":"skills/research/evals/evals.json","sha256":"ba1c1f1a9c841ca3d25faebcfe84dd30993a50dbd9d04274e215c2f44a369554","size":1973},{"mode":420,"path":"skills/tdd/SKILL.md","sha256":"c4ef54fe809fb8fa4c55de2810210f9991f85fa442c73797e575d59c9b99d4fe","size":4397},{"mode":420,"path":"skills/tdd/agents/openai.yaml","sha256":"62f91ed072157ada9471fece9e9265a9bb7c9eb07fc1453794f4ccf5d107083c","size":285},{"mode":420,"path":"skills/tdd/evals/evals.json","sha256":"58cfcd7c2fedc80e4f1431e4c52481849522944730639265323516c12c70b905","size":1202},{"mode":420,"path":"skills/tdd/interface-design.md","sha256":"764c5ff0e3fa6b4ab7095eb65ccc7201e090baf19fa16051dfdb72c06d27417d","size":653},{"mode":420,"path":"skills/tdd/mocking.md","sha256":"36891842b9ff463daf1c68e65eb25df6bcc734f476a0d23c930e757c150c7451","size":1817},{"mode":420,"path":"skills/tdd/refactoring.md","sha256":"28e5278dac743bc1a37bf5b5e3beba84fe90c0d63ea59abfb5cc206b8667684e","size":398},{"mode":420,"path":"skills/tdd/tests.md","sha256":"6773173a074569b2e51653bd7b95c097d602dbb4815d1cf1c87344705c4e0d1c","size":2228},{"mode":420,"path":"skills/tickets-orchestrator/SKILL.md","sha256":"d8660e3efe05084a21cd6f774b72a123d2641e5e401ab65267b486ff51a85f19","size":11608},{"mode":420,"path":"skills/tickets-orchestrator/agents/openai.yaml","sha256":"a130bb5c109e9385bdcca4edc583f63c0199fe9673c334ba5e336900e9de606a","size":412},{"mode":420,"path":"skills/tickets-orchestrator/evals/evals.json","sha256":"76182497e64cef0458bc74cf7718b0311ea8f45b10359f7b3f969b0740ce0687","size":9936},{"mode":420,"path":"skills/tickets-orchestrator/references/delegate-integrate.md","sha256":"41663556a3817a386dfb292188df9616c5aae1d13af4f989687c8e934c6b6015","size":4463},{"mode":420,"path":"skills/tickets-orchestrator/references/finish-delivery.md","sha256":"cdcafc0f908ff67c810301934721d006f4b791087b9362e29a41c92e88dd1121","size":4246},{"mode":420,"path":"skills/tickets-orchestrator/references/stop-completion.md","sha256":"21ec3fcfc9acbdc9db040b1cf8a1740cc4e18be1dc8827b7f66edca0d611c3dd","size":3568},{"mode":420,"path":"skills/to-spec/SKILL.md","sha256":"25a8c7fd97d5ecf5f734fb3a2f4a0c823aa773910d003e50ab11373eb8174692","size":5450},{"mode":420,"path":"skills/to-spec/agents/openai.yaml","sha256":"02221785807ff9219a80d71f66759f354c417ee003b1ed56787962220c272e21","size":292},{"mode":420,"path":"skills/to-spec/evals/evals.json","sha256":"6790746a293746befa83f7852a4b303da9509ba583099e92d23e4f9df504155e","size":1290},{"mode":420,"path":"skills/to-tickets/SKILL.md","sha256":"4fcf63df1575f84a392667e4165ced78d583824cae84738ab21d5a040ff829d4","size":9236},{"mode":420,"path":"skills/to-tickets/agents/openai.yaml","sha256":"cd9afe48f7a57469c496d99714c872248b71fd4ab9c6e1b94b27e0f9dc046621","size":358},{"mode":420,"path":"skills/to-tickets/evals/evals.json","sha256":"a0682f0317440f24b8f3ba74f1ccc2334c22d1a1abf64f85de2d2617f6a66ac0","size":4949},{"mode":420,"path":"skills/to-tickets/references/publishing-details.md","sha256":"242b9caa3878b71ea333565c1e04a0e867ab11302ddfd8cf8bf7c2589f52acfb","size":4380}],"generationHash":"92ca6a544a9216e40b8d94e1e8c724086dfa571c9b8b006320651e3daf7d78da","operations":{"acceptance-proof":{"dependencySkills":[],"entry":"operations/acceptance-proof/SKILL.md","files":["operations/acceptance-proof/SKILL.md","profiles/implementer.toml","schemas/proof-report-v1.json","skills/acceptance-proof/SKILL.md","skills/acceptance-proof/agents/openai.yaml","skills/acceptance-proof/references/android.md","skills/acceptance-proof/references/browser.md","skills/acceptance-proof/references/ios.md","skills/acceptance-proof/tools/ios-lease.mjs"],"id":"acceptance-proof","outputSchema":"schemas/proof-report-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"proof-only","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["worktree"]},"profile":"implementer","resources":[],"reviewers":[],"sourceSkill":"acceptance-proof"},"code-review":{"dependencySkills":[],"entry":"operations/code-review/SKILL.md","files":["docs/agents/confidence-rubric.md","operations/code-review/SKILL.md","profiles/review_coordinator.toml","profiles/spec_reviewer.toml","profiles/standards_reviewer.toml","schemas/code-review-v1.json","skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md"],"id":"code-review","outputSchema":"schemas/code-review-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"report-only","sandboxMode":"read-only","worktreeAccess":"read-only","writableRootClasses":[]},"profile":"review_coordinator","resources":["docs/agents/confidence-rubric.md"],"reviewers":["spec_reviewer","standards_reviewer"],"sourceSkill":"code-review"},"implementation":{"dependencySkills":["diagnosing-bugs","tdd"],"entry":"operations/implementation/SKILL.md","files":["docs/agents/bug-workflow-routing.md","docs/agents/bugfix-quality-gate.md","docs/agents/coding-skill-routing.md","docs/agents/confidence-rubric.md","docs/agents/tool-usage.md","operations/implementation/SKILL.md","profiles/implementer.toml","schemas/implementation-report-v1.json","skills/bug-root-cause-explainer/SKILL.md","skills/bug-root-cause-explainer/agents/openai.yaml","skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh","skills/grilling/SKILL.md","skills/grilling/agents/openai.yaml","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/plan/SKILL.md","skills/plan/agents/openai.yaml","skills/prototype/LOGIC.md","skills/prototype/SKILL.md","skills/prototype/UI.md","skills/prototype/agents/openai.yaml","skills/research/SKILL.md","skills/research/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md","skills/tickets-orchestrator/SKILL.md","skills/tickets-orchestrator/agents/openai.yaml","skills/tickets-orchestrator/references/delegate-integrate.md","skills/tickets-orchestrator/references/finish-delivery.md","skills/tickets-orchestrator/references/stop-completion.md","skills/to-spec/SKILL.md","skills/to-spec/agents/openai.yaml","skills/to-tickets/SKILL.md","skills/to-tickets/agents/openai.yaml","skills/to-tickets/references/publishing-details.md"],"id":"implementation","outputSchema":"schemas/implementation-report-v1.json","policy":{"approvalCeiling":"never","cwdClass":"worktree","externalWrite":false,"mcpTools":[],"network":"deny","networkHosts":[],"runnerPostcondition":"change-set","sandboxMode":"workspace-write","worktreeAccess":"write","writableRootClasses":["worktree"]},"profile":"implementer","resources":["docs/agents/bug-workflow-routing.md","docs/agents/coding-skill-routing.md","docs/agents/tool-usage.md"],"reviewers":[],"sourceSkill":"implement"}},"profiles":{"implementer":"profiles/implementer.toml","review_coordinator":"profiles/review_coordinator.toml","spec_reviewer":"profiles/spec_reviewer.toml","standards_reviewer":"profiles/standards_reviewer.toml"},"skills":{"acceptance-proof":{"dependencySkills":[],"entry":"skills/acceptance-proof/SKILL.md","files":["skills/acceptance-proof/SKILL.md","skills/acceptance-proof/agents/openai.yaml","skills/acceptance-proof/references/android.md","skills/acceptance-proof/references/browser.md","skills/acceptance-proof/references/ios.md","skills/acceptance-proof/tools/ios-lease.mjs"],"metadata":"skills/acceptance-proof/agents/openai.yaml"},"bug-root-cause-explainer":{"dependencySkills":["diagnosing-bugs"],"entry":"skills/bug-root-cause-explainer/SKILL.md","files":["docs/agents/bug-workflow-routing.md","docs/agents/bugfix-quality-gate.md","docs/agents/confidence-rubric.md","skills/bug-root-cause-explainer/SKILL.md","skills/bug-root-cause-explainer/agents/openai.yaml","skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/bug-root-cause-explainer/agents/openai.yaml"},"code-review":{"dependencySkills":[],"entry":"skills/code-review/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md"],"metadata":"skills/code-review/agents/openai.yaml"},"diagnosing-bugs":{"dependencySkills":[],"entry":"skills/diagnosing-bugs/SKILL.md","files":["docs/agents/bug-workflow-routing.md","docs/agents/bugfix-quality-gate.md","docs/agents/confidence-rubric.md","skills/bug-root-cause-explainer/SKILL.md","skills/bug-root-cause-explainer/agents/openai.yaml","skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/diagnosing-bugs/SKILL.md","skills/diagnosing-bugs/agents/openai.yaml","skills/diagnosing-bugs/scripts/hitl-loop.template.sh","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/diagnosing-bugs/agents/openai.yaml"},"grilling":{"dependencySkills":[],"entry":"skills/grilling/SKILL.md","files":["skills/grilling/SKILL.md","skills/grilling/agents/openai.yaml"],"metadata":"skills/grilling/agents/openai.yaml"},"implement":{"dependencySkills":[],"entry":"skills/implement/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/implement/agents/openai.yaml"},"plan":{"dependencySkills":[],"entry":"skills/plan/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/grilling/SKILL.md","skills/grilling/agents/openai.yaml","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/plan/SKILL.md","skills/plan/agents/openai.yaml","skills/research/SKILL.md","skills/research/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md","skills/to-spec/SKILL.md","skills/to-spec/agents/openai.yaml","skills/to-tickets/SKILL.md","skills/to-tickets/agents/openai.yaml","skills/to-tickets/references/publishing-details.md"],"metadata":"skills/plan/agents/openai.yaml"},"prototype":{"dependencySkills":[],"entry":"skills/prototype/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/prototype/LOGIC.md","skills/prototype/SKILL.md","skills/prototype/UI.md","skills/prototype/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/prototype/agents/openai.yaml"},"research":{"dependencySkills":[],"entry":"skills/research/SKILL.md","files":["skills/research/SKILL.md","skills/research/agents/openai.yaml"],"metadata":"skills/research/agents/openai.yaml"},"tdd":{"dependencySkills":[],"entry":"skills/tdd/SKILL.md","files":["skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md"],"metadata":"skills/tdd/agents/openai.yaml"},"tickets-orchestrator":{"dependencySkills":[],"entry":"skills/tickets-orchestrator/SKILL.md","files":["skills/code-review/SKILL.md","skills/code-review/agents/openai.yaml","skills/code-review/references/standards-smells.md","skills/implement/SKILL.md","skills/implement/agents/openai.yaml","skills/tdd/SKILL.md","skills/tdd/agents/openai.yaml","skills/tdd/interface-design.md","skills/tdd/mocking.md","skills/tdd/refactoring.md","skills/tdd/tests.md","skills/tickets-orchestrator/SKILL.md","skills/tickets-orchestrator/agents/openai.yaml","skills/tickets-orchestrator/references/delegate-integrate.md","skills/tickets-orchestrator/references/finish-delivery.md","skills/tickets-orchestrator/references/stop-completion.md"],"metadata":"skills/tickets-orchestrator/agents/openai.yaml"},"to-spec":{"dependencySkills":[],"entry":"skills/to-spec/SKILL.md","files":["skills/research/SKILL.md","skills/research/agents/openai.yaml","skills/to-spec/SKILL.md","skills/to-spec/agents/openai.yaml","skills/to-tickets/SKILL.md","skills/to-tickets/agents/openai.yaml","skills/to-tickets/references/publishing-details.md"],"metadata":"skills/to-spec/agents/openai.yaml"},"to-tickets":{"dependencySkills":[],"entry":"skills/to-tickets/SKILL.md","files":["skills/research/SKILL.md","skills/research/agents/openai.yaml","skills/to-tickets/SKILL.md","skills/to-tickets/agents/openai.yaml","skills/to-tickets/references/publishing-details.md"],"metadata":"skills/to-tickets/agents/openai.yaml"}},"sourceFingerprint":"594146470640ca35f7af6d6998710a6b0958e09a5cccfc6e35e1287b57db7f83","version":2}

package/internal-workflow/operations/code-review/SKILL.md

@@ -1,23 +1,42 @@
 # Code Review Operation
 
-You are already the independent reviewer selected by the Runner. Follow the
-packaged [Code Review skill](../../skills/code-review/SKILL.md) inline with
-correctness and spec/standards lenses. Cleanup is its bounded lens, never a
-separate operation. Use the declared resources for
-[confidence](../../docs/agents/confidence-rubric.md),
-[contract tests](../../docs/agents/contract-test-ledger.md),
-[review applicability](../../docs/agents/review-gates.md), and
-[Full/Closure mechanics](../../docs/agents/review-protocol.md). The supplied
-review capsule is the exact target and authority.
+You own one packaged Review invocation selected by the Runner. Follow the
+procedural and lens semantics of packaged
+[Review](../../skills/code-review/SKILL.md). The available roles and their
+packaged profiles are the sole concrete role authority for this invocation;
+do not infer a fixed role inventory from examples in that skill. Launch roles
+available in the supplied capsule through its packaged named agent profile.
+For complete Review launch every available role. For targeted Review select
+only the affected role, or all affected roles when the repair crosses lenses
+or cannot be isolated. Launch each selected role as a fresh child without
+inherited history. The Runner binds every available role to its immutable
+`../../profiles/<role>.toml`; never substitute an ambient profile.
+Capture each non-empty identity, and complete the wait for every child. Apply
+the declared [confidence rubric](../../docs/agents/confidence-rubric.md). The
+supplied review capsule is the exact target and authority.
 
-For Closure, copy every supplied canonical defect's `id`, `class`, `invariant`,
-`failure`, and `introducedTargetRevision` exactly. Do not paraphrase immutable
-defect fields; express verification through the allowed status, revision,
-evidence, and repair-finding outcome fields.
+For `complete`, review the full authorized result for requirement fidelity and
+correctness. For `targeted`, review the supplied exact tree-to-tree repair patch
+against its previous and current immutable target identities, blocker/source
+IDs, and current proof; preserve approval outside the changed scope. Use
+complete review after repair only when the exact repair delta itself cannot be
+proven or safely supplied. Account for every supplied previous finding ID and
+copy canonical defect identity fields exactly. Express verification through
+status, revision, evidence, and finding outcomes.
 
 Use `needs-work` for concrete defects that the bounded implementation cycle can
 repair. Reserve `rejected` for a target or authority that cannot safely proceed
 through the normal repair lifecycle.
 
-Do not launch another reviewer, edit files, repair findings, or mutate external
-state. Return only `schemas/code-review-v1.json` with operation `code-review`.
+For each repairable defect, use exact identities already present in the capsule
+and exact repository paths when relevant. Do not infer impact from partial
+words or command/criterion prose. An unknown validation subset expands the
+Runner-owned checks and Acceptance Proof conservatively; it does not reopen
+untouched Review scope while the exact tree repair delta remains proven.
+
+Do not edit files, repair findings, or mutate external state. Reconcile the
+independent reviewer results without erasing a verified blocker. Include every
+selected reviewer role, identity, and verdict in `reviewers`; approval requires
+all selected reviewers to approve. Complete Review selects every available
+reviewer.
+Return only `schemas/code-review-v1.json` with operation `code-review`.