codex-orchestrator 2.0.11 → 2.0.12

package/internal-workflow/docs/agents/contract-test-ledger.md

@@ -1,71 +0,0 @@
-# Contract Test Ledger
-
-Use this shared ledger for behavior-changing work where a passing happy-path test could still miss a contract defect. The ledger turns review-class risks into testable obligations before implementation.
-
-## When Required
-
-Create or update a ledger only when both are true:
-
-1. The task materially changes an observable or shared contract.
-2. You can name a realistic failure that ordinary targeted proof could miss.
-
-Relevant contract areas include:
-
-- API, DTO, schema, serialization, persistence, or externally visible response shape
-- ordering, lifecycle events, state transitions, retries, idempotency, timeout, cancellation, or background jobs
-- cache keys, invalidation, state merge precedence, fallback behavior, profile/global/mobile overrides, defaults, or feature flags
-- evidence, trace, snapshot, audit, summary, aggregation, score, winner, or generated artifacts
-- shared behavior read by multiple callers, tenants, users, groups, children, or projections
-
-Category alone does not activate the ledger. Ordinary API/DTO edits use targeted
-proof when no missed failure is named. Retry, idempotency, auth, payment,
-shared-trust, and recovery changes usually pass the gate when happy-path proof
-cannot expose their failure mode.
-
-For narrow UI copy, docs-only, formatting, tests-only, or isolated styling changes, the ledger is not required.
-
-## Required Shape
-
-Keep the ledger compact. Use one row per invariant:
-
-```markdown
-## Contract Test Ledger
-
-| Invariant | Risk It Prevents | First Test / Proof | Status |
-| --- | --- | --- | --- |
-| <observable rule> | <real failure mode> | <exact test name/command or manual proof> | planned / red / green / blocked |
-```
-
-Rules:
-
-- The invariant must be observable through the public interface or the same seam real callers use.
-- The risk must name the concrete bug class, not a vague "edge case".
-- The first test/proof must fail before the fix unless the ledger records why a RED signal is impossible.
-- `blocked` requires the missing seam, fixture, service, or decision that prevents proof.
-- Keep the ledger current as implementation proceeds; do not backfill it only at the end.
-
-## Invariant Prompts
-
-Ask the relevant subset before the first RED test:
-
-- **Ordering:** What must happen before/after terminal events, snapshots, persistence writes, notifications, or cleanup?
-- **Precedence:** Which source wins among user input, profile, mobile, global, server, cache, AI, fallback, default, `null`, `false`, `0`, and empty objects?
-- **Threading:** Does each new field survive construction, normalization, cloning, retry, persistence reload, serialization, and every visible consumer?
-- **Runtime contract:** Do validation, internal types, persistence schema, API response, and consumers agree on names, units, nullability, enum values, and date/object formats?
-- **Retry/idempotency:** What changes on retry, and which snapshots, counters, streams, timestamps, writes, or side effects must be rebuilt instead of reused?
-- **Determinism:** When sort keys, timestamps, scores, priorities, or winners tie, what stable tie-breaker makes output repeatable?
-- **Evidence:** Which trace, audit, snapshot, Fresh-Context, summary, or generated artifact proves the behavior actually happened?
-- **Proof compatibility:** Can that source observe the exact claim at the required item/run/aggregate cardinality, and could it pass while the claim is false because of delay, redaction, correlation, or variant differences?
-- **Partial failure:** If a dependency times out, throws, returns stale data, or fails after a side effect, what durable state remains and who repairs it?
-- **Scope/cardinality:** Is data global, per-tenant, per-group, per-child, per-step, or per-item, and can one top-level field collapse multiple meaningful results?
-
-## Review Feedback Loop
-
-When code review finds a real contract defect, add or update one ledger row before fixing it:
-
-- `Invariant`: the rule the implementation violated
-- `Risk It Prevents`: the observed review finding
-- `First Test / Proof`: the regression test or proof that would have caught it
-- `Status`: `red` before the fix, then `green` after verification
-
-If no correct public seam exists for the regression test, record that as `blocked` and name the architecture/testability gap. Do not replace a missing seam with an implementation-detail test unless the task explicitly approves that tradeoff.

package/internal-workflow/docs/agents/review-gates.md

@@ -1,42 +0,0 @@
-# Review Gates
-
-This file owns review applicability. Review execution mechanics live in
-[`review-protocol.md`](review-protocol.md); approved-spec review shape lives in
-[`spec-implementer/references/review-loop.md`](../../skills/spec-implementer/references/review-loop.md).
-
-## Final Code Review
-
-Run final `$code-review` for behavior-changing work that affects:
-
-- medium/large shared business behavior;
-- API/DTO/schema, migration, persistence, auth, permission, payment, cache,
-  concurrency, background jobs, or shared-state contracts;
-- shared UI/navigation/middleware/core flows;
-- runtime logic across three or more files when it crosses an owner or
-  validation seam.
-
-Do not invoke it automatically for docs, copy, comments, tests-only or
-styling-only changes, formatting, renames, mechanical refactors, or isolated
-low-risk one-file fixes.
-
-`medium` is the normal review profile. API, persistence, statefulness, file
-count, or orchestration strengthens the review focus only when it creates an
-affected contract; none independently selects `high`.
-
-## Cleanup
-
-Cleanup is a lens inside the same final `$code-review`, never a separate gate.
-Use bounded cleanup by default. Amplify it only when the user, approved source,
-or repository policy names a concrete evidenced simplification risk; follow
-`../../skills/code-review/references/cleanup-lens.md` for that branch.
-
-After one consolidated repair, coordinator verification plus affected
-validation closes ordinary medium/low behavior-preserving findings. Use
-Closure only for the triggers in `review-protocol.md`.
-
-## Validation Depth
-
-For simple and medium work, run targeted behavior proof and the smallest
-affected integration check. Run a full repository suite only when explicitly
-required by repository policy, when broad contract fan-out cannot be isolated,
-or for a genuinely `high` task.

package/internal-workflow/docs/agents/review-protocol.md

@@ -1,98 +0,0 @@
-# Review Protocol
-
-This file owns mechanics shared by artifact and implementation review: bounded
-capsules, Full/Closure, defect lifecycle, no-progress, waiver, and the result
-envelope. Target Modules own authority, profile, topology, durable state, and
-outcome mapping.
-
-## Capsule
-
-Every reviewer receives only:
-
-- target kind/path and pinned revision;
-- one unanswered review question and assigned lenses;
-- authority, approved scope, and relevant evidence;
-- compact affected validation and current defect records;
-- for Closure, the repair diff and mapping from changed targets to defects and
-  affected contracts.
-
-Do not pass raw parent history, old revisions, repeated logs, or unrelated
-inventories. Reuse valid coverage for the same revision, question, and lenses.
-
-## Modes
-
-**Full** covers the complete assigned scope once. It is bounded to the settled
-target, changed owners, authority, and plausible affected contracts. It is not
-a repository-wide audit and does not activate unrelated lenses.
-
-**Closure** verifies a repair only when the finding is critical/high, affects a
-trust boundary, durable data, concurrency/idempotency, shared API/DTO/schema, or
-invalidates mandatory coverage. Closure stays with affected reviewer lineages
-and targets. Do not launch it merely because Full found an ordinary defect.
-
-A repair starts another Full only when mandatory-lens coverage became invalid.
-A live reviewer poll timeout is non-terminal and does not authorize duplicate
-review or cancellation; reconcile the recorded session first.
-
-## Defects
-
-Use one canonical record per distinct invariant and failure mechanism:
-
-```yaml
-id: REVIEW-CONC-003
-class: blocker | execution-risk | improvement
-status: open | fixed | verified | blocked | accepted-risk | superseded
-severity: critical | high | medium | low
-confidence: high | medium | low
-invariant: "<observable rule>"
-failure: "<concrete trigger and impact>"
-evidence: ["<target or source>"]
-repair: "<smallest sufficient change>"
-affected_targets: ["<path, section, contract, or lens>"]
-```
-
-Root assigns stable IDs and deduplicates only when both invariant and failure
-match. A superseded record must point to a distinct canonical replacement.
-Improvements never block. Only an execution risk may become `accepted-risk`,
-and only with explicit authority, reason, scope, and target revision. A blocker
-cannot be accepted or downgraded.
-
-Move blocking defects `open -> fixed -> verified`. For ordinary medium/low
-behavior-preserving repairs, root may verify after checking the cited failure
-path and affected validation. Closure-triggering defects require affected
-independent verification.
-
-In Closure, copy each supplied canonical defect's `id`, `class`, `invariant`,
-`failure`, and introduced target revision byte-for-byte. Never paraphrase those
-immutable fields while describing verification. Record the Closure decision in
-the status, status target revision, evidence, and repair-finding outcome fields.
-
-## Repair And Stop
-
-Repair compatible findings in one consolidated batch. Before repeating review,
-the target, evidence, repair, or source decision must change materially.
-Review count and elapsed time are audit signals, never approval or blocking
-conditions.
-
-Stop when repair requires a product/scope/owner decision, mandatory evidence or
-reviewer is unavailable, no substantive repair exists, or the same failure
-repeats without progress. Do not create micro-cycles for ordinary medium/low
-findings.
-
-Waive review only after explicit user instruction. Record skipped coverage and
-open defects. Waiver is not approval and accepts no defect automatically.
-
-## Result
-
-```text
-Review Mode: <Full | Closure>
-Mandatory Coverage: <covered lenses or gaps>
-Verified Defects: <IDs or None>
-Accepted Risks: <IDs, authority, reason or None>
-Open Defects: <IDs or None>
-```
-
-Target Modules add profile, authority, outcome, and checkpoint without
-redefining these fields. For a normal medium flow, do not report internal
-session accounting unless interruption, Closure, accepted risk, or another
-exception makes it relevant.

package/internal-workflow/evals/coding-skill-evals.json

@@ -1,373 +0,0 @@
-{
-  "schema_version": 1,
-  "purpose": "Cross-skill routing and handoff regressions only; skill-local behavior belongs in each owner's evals directory.",
-  "cases": [
-    {
-      "id": "route-feature-tdd",
-      "prompt": "Implement a behavior-changing feature in this repository.",
-      "expected": ["read local evidence", "activate tdd before behavior edits", "run affected validation"],
-      "forbidden": ["invent repository commands", "create planning artifacts without an execution gap"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/behavior-change",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["code-review", "tdd"],
-        "should_not_trigger": ["implementation-spec-maker", "small-task-implementer", "tickets-orchestrator"],
-        "assertions": [{"kind": "route_equals", "value": "direct-medium"}],
-        "ablation_skill": "tdd"
-      }
-    },
-    {
-      "id": "route-diagnosis-only",
-      "prompt": "Explain the confirmed root cause documented in this repository and do not fix it yet.",
-      "expected": ["use bug-root-cause-explainer", "cite concrete evidence", "stop before edits"],
-      "forbidden": ["edit files", "present an inference as proven"],
-      "execution": {
-        "level": "behavior",
-        "fixture": "behavior/diagnosis-only",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["bug-root-cause-explainer"],
-        "should_not_trigger": ["code-debugger", "diagnosing-bugs"],
-        "assertions": [
-          {"kind": "route_equals", "value": "diagnosis-only"},
-          {"kind": "tree_unchanged"}
-        ],
-        "ablation_skill": "bug-root-cause-explainer"
-      }
-    },
-    {
-      "id": "route-flaky-bug",
-      "prompt": "Debug the intermittent failure described by this repository; its cause is not confirmed.",
-      "expected": ["use diagnosing-bugs", "improve reproduction or signal before repair"],
-      "forbidden": ["jump directly to a fix"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/flaky-bug",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["diagnosing-bugs"],
-        "should_not_trigger": ["bug-root-cause-explainer", "code-debugger"],
-        "assertions": [{"kind": "route_equals", "value": "diagnose-first"}],
-        "ablation_skill": "diagnosing-bugs"
-      }
-    },
-    {
-      "id": "profile-medium-default",
-      "prompt": "Implement the settled stateful API and persistence feature described in this repository.",
-      "expected": ["select medium", "implement directly when authority and proof are clear"],
-      "forbidden": ["select high from statefulness or file count", "manufacture a PRD, tickets, or spec"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/direct-medium",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["tdd"],
-        "should_not_trigger": ["implementation-spec-maker", "tickets-orchestrator"],
-        "assertions": [{"kind": "route_equals", "value": "direct-medium"}]
-      }
-    },
-    {
-      "id": "profile-high-threshold",
-      "prompt": "Classify the ordinary refactor and the irreversible data-loss scenario documented in this repository.",
-      "expected": ["keep the broad ordinary refactor medium", "select high only for material consequence plus uncertainty"],
-      "forbidden": ["accumulate generic risk labels into high"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/profile-classification",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": [],
-        "should_not_trigger": ["implementation-spec-maker", "tickets-orchestrator"],
-        "assertions": [{"kind": "route_equals", "value": "profile-classification"}]
-      }
-    },
-    {
-      "id": "planning-does-not-deliver",
-      "prompt": "Use wayfinder to resolve the documented decision frontier and publish the resulting tickets, then stop before delivery.",
-      "expected": ["stop after the planning package", "require separate delivery authorization"],
-      "forbidden": ["start implementation from publication or labels"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/planning",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["to-tickets", "wayfinder"],
-        "should_not_trigger": ["spec-implementer", "tickets-orchestrator"],
-        "assertions": [{"kind": "route_equals", "value": "planning-only"}],
-        "ablation_skill": "wayfinder"
-      }
-    },
-    {
-      "id": "spec-only-for-gap",
-      "prompt": "Choose the route for the implementation request whose unresolved execution contract is documented in this repository.",
-      "expected": ["use implementation-spec-maker for the unresolved execution delta"],
-      "forbidden": ["start implementation before the contract is resolved", "create a ticket graph"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/spec-gap",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["implementation-spec-maker"],
-        "should_not_trigger": ["spec-implementer", "tickets-orchestrator"],
-        "assertions": [{"kind": "route_equals", "value": "spec-gap"}],
-        "ablation_skill": "implementation-spec-maker"
-      }
-    },
-    {
-      "id": "approved-spec-execution",
-      "prompt": "Execute the approved implementation spec in this repository and stop at its stated delivery boundary.",
-      "expected": ["use spec-implementer", "follow the approved checklist through observable proof", "update reached checklist items truthfully"],
-      "forbidden": ["create a replacement spec", "route through tickets", "commit or push"],
-      "execution": {
-        "level": "end_to_end",
-        "fixture": "end-to-end-approved-spec",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["spec-implementer", "tdd"],
-        "should_not_trigger": ["implementation-spec-maker", "tickets-orchestrator"],
-        "assertions": [
-          {"kind": "route_equals", "value": "spec-implementer"},
-          {"kind": "file_contains", "path": ".eval/red.json", "text": "\"status\": \"red\""},
-          {"kind": "command_exit", "argv": ["python3", "verify_outcome.py"], "exit_code": 0, "boundary": false},
-          {"kind": "file_contains", "path": "docs/implementation-specs/approved-greeting.md", "text": "- [x] Implement the greeting"},
-          {"kind": "file_contains", "path": "docs/implementation-specs/approved-greeting.md", "text": "- [x] Run the focused test"},
-          {"kind": "event_present", "event": "file_write", "value": "greeting.py"},
-          {"kind": "event_order", "before": {"event": "skill_read", "value": "spec-implementer"}, "after": {"event": "file_write", "value": "greeting.py"}},
-          {"kind": "event_absent", "event": "git_push", "value": "origin"}
-        ],
-        "ablation_skill": "spec-implementer"
-      }
-    },
-    {
-      "id": "ticket-direct-vs-graph",
-      "prompt": "Deliver the approved dependency graph documented in this repository through its public tests and stop at the local delivery boundary.",
-      "expected": ["use tickets-orchestrator for the graph", "deliver independent tickets before their dependent", "prove the completed graph"],
-      "forbidden": ["manufacture a wave-level spec", "skip a dependency", "commit or push"],
-      "execution": {
-        "level": "end_to_end",
-        "fixture": "end-to-end-ticket-graph",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["tdd", "tickets-orchestrator"],
-        "should_not_trigger": ["implementation-spec-maker", "spec-implementer"],
-        "assertions": [
-          {"kind": "route_equals", "value": "ticket-graph"},
-          {"kind": "file_contains", "path": ".eval/red.json", "text": "\"status\": \"red\""},
-          {"kind": "command_exit", "argv": ["python3", "verify_outcome.py"], "exit_code": 0, "boundary": false},
-          {"kind": "file_contains", "path": "delivery-state.md", "text": "- [x] Ticket A"},
-          {"kind": "file_contains", "path": "delivery-state.md", "text": "- [x] Ticket B"},
-          {"kind": "file_contains", "path": "delivery-state.md", "text": "- [x] Ticket C"},
-          {"kind": "event_present", "event": "file_write", "value": "summary.py"},
-          {"kind": "event_order", "before": {"event": "skill_read", "value": "tickets-orchestrator"}, "after": {"event": "file_write", "value": "summary.py"}},
-          {"kind": "path_absent", "path": "PLAN.md"},
-          {"kind": "event_absent", "event": "git_push", "value": "origin"}
-        ],
-        "ablation_skill": "tickets-orchestrator"
-      }
-    },
-    {
-      "id": "review-topology",
-      "prompt": "Run the final review for the ordinary medium change documented in this repository.",
-      "expected": ["launch one reviewer_standard", "keep correctness and standards in one bounded Full review"],
-      "forbidden": ["root self-review", "launch reviewer_deep for ordinary medium"],
-      "execution": {
-        "level": "behavior",
-        "fixture": "behavior/review",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["code-review"],
-        "should_not_trigger": ["implementation-spec-review"],
-        "assertions": [
-          {"kind": "route_equals", "value": "review-topology"},
-          {"kind": "event_present", "event": "subagent_launch", "value": "reviewer_standard"},
-          {"kind": "event_absent", "event": "subagent_launch", "value": "reviewer_deep"},
-          {"kind": "tree_unchanged"}
-        ]
-      }
-    },
-    {
-      "id": "review-closure-bounded",
-      "prompt": "Execute the already-authorized Closure for the repaired shared-contract defect documented in this repository.",
-      "expected": ["launch the recorded reviewer_standard lineage for affected Closure", "leave the already-repaired tree unchanged"],
-      "forbidden": ["restart broad Full review", "launch reviewer_deep or a separate cleanup gate"],
-      "execution": {
-        "level": "behavior",
-        "fixture": "behavior/review-closure",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["code-review"],
-        "should_not_trigger": ["implementation-spec-review"],
-        "assertions": [
-          {"kind": "route_equals", "value": "review-closure"},
-          {"kind": "event_present", "event": "subagent_launch", "value": "reviewer_standard:closure"},
-          {"kind": "event_absent", "event": "subagent_launch", "value": "reviewer_deep"},
-          {"kind": "tree_unchanged"}
-        ]
-      }
-    },
-    {
-      "id": "ledger-needs-material-missed-failure",
-      "prompt": "Choose proof for the ordinary DTO edit documented in this repository; its targeted caller test covers the only realistic failure.",
-      "expected": ["use targeted proof without a contract ledger"],
-      "forbidden": ["create a ledger from the DTO category alone"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/ledger",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["tdd"],
-        "should_not_trigger": ["implementation-spec-maker"],
-        "assertions": [{"kind": "route_equals", "value": "targeted-proof"}]
-      }
-    },
-    {
-      "id": "ledger-protects-retry-contract",
-      "prompt": "Change the payment retry behavior documented in this repository, where a happy-path test could miss duplicate side effects.",
-      "expected": ["create a contract ledger", "name duplicate payment as the missed failure"],
-      "forbidden": ["rely on the happy path alone"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/ledger",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["tdd"],
-        "should_not_trigger": ["implementation-spec-maker"],
-        "assertions": [{"kind": "route_equals", "value": "contract-ledger"}]
-      }
-    },
-    {
-      "id": "direct-medium-no-extra-route",
-      "prompt": "Implement the clear medium feature documented in this repository; behavior, ownership, and affected proof are settled.",
-      "expected": ["implement directly"],
-      "forbidden": ["create tickets, a spec, or orchestration from file count, statefulness, or generic risk"],
-      "execution": {
-        "level": "end_to_end",
-        "fixture": "end-to-end-direct-medium",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["code-review", "tdd"],
-        "should_not_trigger": ["implementation-spec-maker", "small-task-implementer", "tickets-orchestrator"],
-        "assertions": [
-          {"kind": "route_equals", "value": "direct-medium"},
-          {"kind": "file_contains", "path": ".eval/red.json", "text": "\"status\": \"red\""},
-          {"kind": "command_exit", "argv": ["python3", "verify_outcome.py"], "exit_code": 0, "boundary": false},
-          {"kind": "path_absent", "path": "PLAN.md"},
-          {"kind": "path_absent", "path": "docs/implementation-specs"},
-          {"kind": "event_present", "event": "file_write", "value": "store.py"},
-          {"kind": "event_order", "before": {"event": "skill_read", "value": "tdd"}, "after": {"event": "file_write", "value": "store.py"}},
-          {"kind": "event_present", "event": "subagent_launch", "value": "reviewer_standard"},
-          {"kind": "event_absent", "event": "git_push", "value": "origin"}
-        ]
-      }
-    },
-    {
-      "id": "route-copy-config",
-      "prompt": "Apply the exact copy and configuration-only update documented in this repository.",
-      "expected": ["use the small-task route", "run affected validation without manufacturing RED"],
-      "forbidden": ["activate tdd", "create an implementation spec"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/nonbehavior",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["small-task-implementer"],
-        "should_not_trigger": ["implementation-spec-maker", "tdd"],
-        "assertions": [{"kind": "route_equals", "value": "direct-simple"}],
-        "ablation_skill": "small-task-implementer"
-      }
-    },
-    {
-      "id": "route-bounded-fix",
-      "prompt": "Implement the confirmed bounded bug fix documented in this repository through its existing public test seam.",
-      "expected": ["activate tdd", "use code-debugger", "run affected validation"],
-      "forbidden": ["restart open-ended diagnosis", "create an implementation spec"],
-      "execution": {
-        "level": "end_to_end",
-        "fixture": "end-to-end-bounded-fix",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["code-debugger", "tdd"],
-        "should_not_trigger": ["diagnosing-bugs", "implementation-spec-maker"],
-        "assertions": [
-          {"kind": "route_equals", "value": "bounded-fix"},
-          {"kind": "file_contains", "path": ".eval/red.json", "text": "\"status\": \"red\""},
-          {"kind": "command_exit", "argv": ["python3", "verify_outcome.py"], "exit_code": 0, "boundary": false},
-          {"kind": "event_present", "event": "file_write", "value": "calculator.py"},
-          {"kind": "event_order", "before": {"event": "skill_read", "value": "tdd"}, "after": {"event": "file_write", "value": "calculator.py"}},
-          {"kind": "path_absent", "path": "PLAN.md"},
-          {"kind": "event_absent", "event": "git_push", "value": "origin"}
-        ],
-        "ablation_skill": "code-debugger"
-      }
-    },
-    {
-      "id": "route-commit-only",
-      "prompt": "Commit only the already validated scoped changes described in this repository and stop without pushing.",
-      "expected": ["use commit", "stage only intended paths", "stop after the local commit"],
-      "forbidden": ["push", "open a pull request", "start another implementation workflow"],
-      "execution": {
-        "level": "behavior",
-        "fixture": "behavior/commit-only",
-        "sandbox": "workspace-write",
-        "trials": 2,
-        "should_trigger": ["commit"],
-        "should_not_trigger": ["code-review", "tickets-orchestrator"],
-        "assertions": [
-          {"kind": "route_equals", "value": "commit-only"},
-          {"kind": "command_exit", "argv": ["python3", "verify_commit.py"], "exit_code": 0, "boundary": true},
-          {"kind": "event_present", "event": "git_commit", "value": "commit"},
-          {"kind": "event_absent", "event": "git_push", "value": "origin"},
-          {"kind": "tree_unchanged"}
-        ],
-        "ablation_skill": "commit"
-      }
-    },
-    {
-      "id": "route-evidence-answers",
-      "prompt": "Implement the tiny change using the exact target, expected value, and validation command already documented in this repository.",
-      "expected": ["use repository evidence", "continue without an obvious clarification question"],
-      "forbidden": ["ask for details already present", "create planning artifacts"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/evidence-first",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["small-task-implementer"],
-        "should_not_trigger": ["implementation-spec-maker", "wayfinder"],
-        "assertions": [{"kind": "route_equals", "value": "evidence-first"}]
-      }
-    },
-    {
-      "id": "route-invented-defaults",
-      "prompt": "Prepare the implementation route for the configurable lookback and cooldown requirement documented in this repository.",
-      "expected": ["identify the missing authority values", "use implementation-spec-maker and block the unresolved decision"],
-      "forbidden": ["invent defaults", "start implementation"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/authority-gap",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["implementation-spec-maker"],
-        "should_not_trigger": ["small-task-implementer", "spec-implementer"],
-        "assertions": [{"kind": "route_equals", "value": "authority-blocked"}]
-      }
-    },
-    {
-      "id": "route-preserve-existing",
-      "prompt": "Prepare an implementation spec for the request documented in this repository, preserving behavior that repository evidence proves already exists.",
-      "expected": ["classify existing behavior as preserve plus regression proof", "scope only the remaining delta"],
-      "forbidden": ["plan a second implementation", "ignore current code evidence"],
-      "execution": {
-        "level": "trigger",
-        "fixture": "routing/preserve-existing",
-        "sandbox": "read-only",
-        "trials": 2,
-        "should_trigger": ["implementation-spec-maker"],
-        "should_not_trigger": ["code-debugger", "tdd"],
-        "assertions": [{"kind": "route_equals", "value": "preserve-existing"}]
-      }
-    }
-  ]
-}

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

@@ -1,5 +0,0 @@
-# Fresh Ambiguity Review Operation
-
-Independently verify that a supplied waiting candidate contains at least two materially different product outcomes and no source-authorized choice. Technical, architecture, test, and tool choices are never product ambiguity. Do not edit files or external state. Return only `schemas/ambiguity-review-v1.json`.
-
-Apply the packaged [confidence rubric](../../docs/agents/confidence-rubric.md).

package/internal-workflow/operations/qualification-repair/SKILL.md

@@ -1,17 +0,0 @@
-# Qualification Repair Operation
-
-Repair only the scoped check failures supplied by the Runner. This operation
-does not authorize implementation of the issue acceptance criteria. Use the
-smallest relevant debugging or TDD workflow needed to make the supplied checks
-pass, and do not broaden validation beyond those commands.
-
-Use [Code Debugger](../../skills/code-debugger/SKILL.md) for a confirmed check
-failure, [Diagnosing Bugs](../../skills/diagnosing-bugs/SKILL.md) only when its
-cause is unclear, and [TDD](../../skills/tdd/SKILL.md) only when the repair
-changes observable behavior.
-
-The Runner owns issue implementation, review, final checks, commits,
-publication, retries, and external state. Never commit, push, publish, mutate
-GitHub, or expose credentials. In the final report, `changedFiles` is the
-complete current worktree change set, including changes that existed before
-this attempt. Return only `schemas/implementation-report-v1.json`.

package/internal-workflow/operations/spec-author/SKILL.md

@@ -1,12 +0,0 @@
-# Spec Author Operation
-
-Follow the authoring and minimum-solution contract in the packaged
-[Implementation Spec Maker](../../skills/implementation-spec-maker/SKILL.md)
-for the supplied issue authority. Use the declared
-[confidence rubric](../../docs/agents/confidence-rubric.md) and
-[contract ledger](../../docs/agents/contract-test-ledger.md) only when
-applicable.
-The Runner owns artifact review, revision state, and approval, so do not invoke
-the skill's review/save workflow or create reviewer state. Write the complete
-revision only to the Runner-provided spec artifact location and return
-`schemas/spec-author-v1.json`.

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

@@ -1,12 +0,0 @@
-# Spec Review Operation
-
-You are already the independent reviewer selected and persisted by the Runner.
-Follow the packaged
-[Implementation Spec Review](../../skills/implementation-spec-review/SKILL.md)
-inline and use its owner-local review loop only for semantics matching the
-supplied mode and immutable state. Apply the declared
-[confidence rubric](../../docs/agents/confidence-rubric.md),
-[contract ledger](../../docs/agents/contract-test-ledger.md), and
-[review protocol](../../docs/agents/review-protocol.md). Do not launch another
-reviewer, edit the spec, change review state, or mutate external state. Return
-only `schemas/spec-review-v1.json`.