qfai 1.7.9 → 1.7.13

package/README.md

@@ -17,8 +17,8 @@ The agent reads the repository, produces the required artifacts, and iterates un
 
 ## Release status
 
-- Current package version: `1.7.7`
-- Release posture: v1.7.7 is the correction release that aligns the v1.7.6 remediation line before deeper prototyping work.
+- Current package version: `1.7.13`
+- Release posture: v1.7.13 converges init assets, validators, and docs on the canonical sidecar model.
 - Current repo note: some repo-wide `qfai validate --fail-on error` blockers still come from historical review/evidence/ATDD/TDD artifacts and are being cleaned incrementally.
 
 ## Quick start
@@ -53,12 +53,9 @@ npx qfai report
   - Produces a human-readable report (`report.md` by default) or an internal JSON export (`report.json`) from `validate.json`; use `--base-url` to link file paths in Markdown to your repository viewer.
 - `npx qfai doctor`
   - Diagnoses configuration discovery, path resolution, glob scanning, and `validate.json` inputs before running validate/report; use `--fail-on` to enforce failures in CI.
-- `npx qfai prototyping --autogen-ui-fidelity --base-url <url>`
-  - Auto-generates `uiFidelity` evidence by crawling UI routes and collecting DOM labels;
-    writes to `.qfai/evidence/prototyping.json` (or `--evidence-out <path>`).
-    Requires `--base-url` or `QFAI_PROTOTYPE_BASE_URL` to specify the running application URL.
-    Use `--autogen-only` to fail when generation fails (for CI gates).
-    Enable with `QFAI_PROTOTYPE_FIDELITY_AUTOGEN=1` as an alternative to `--autogen-ui-fidelity`.
+    Note: prototyping evidence (`.qfai/evidence/prototyping.json`) is produced by the AI workflow / skills
+    (`/qfai-prototyping` with `mode=low-cost|standard|full-harness`), not by a CLI command.
+    `qfai validate` consumes the resulting evidence files, including `mode.effective` and `fullHarness` metadata when present.
 
 ## ATDD annotation hard gate
 
@@ -70,43 +67,6 @@ npx qfai report
 - `tests/api/**` and `tests/e2e/**` must not use `TC` annotations.
 - `AC` annotations are not required in code; AC coverage is treated as indirect through full `TC` coverage.
 
-## Prototyping uiFidelity autogen
-
-`qfai prototyping --autogen-ui-fidelity` auto-generates `uiFidelity` evidence by:
-
-1. Extracting expected labels/actions from `contracts/ui/**` (YAML).
-2. Crawling the running application routes via headless fetch + jsdom.
-3. Computing label coverage (found vs. missing).
-4. Heuristically evaluating `mockPaths` (route reachability + navigate targets).
-5. Writing the result to `.qfai/evidence/prototyping.json`.
-
-### Prerequisites
-
-- Labels must be rendered in the DOM (text, aria-label, placeholder, etc.).
-- Routes must be reachable (authentication bypass or test fixtures as needed).
-- `--base-url` must point to a running instance of the application.
-
-### CI integration example
-
-```yaml
-- name: Start app (background)
-  run: npm start &
-  env:
-    DISABLE_AUTH: "true"
-
-- name: Wait for app
-  run: npx wait-on http://localhost:3000
-
-- name: Run qfai prototyping autogen
-  run: |
-    npx qfai prototyping --autogen-ui-fidelity --base-url http://localhost:3000 --autogen-only
-```
-
-### Failure handling
-
-- If autogen fails, `uiFidelityAutogen.status=failed` is recorded in the evidence, but existing `uiFidelity` data is not removed.
-- `--autogen-only` causes exit code 1 on failure; without it, exit code is always 0 (safe fallback).
-
 ## Operating model (skills-driven workflow)
 
 QFAI assumes you operate the project primarily via prepared custom skills.
@@ -125,9 +85,9 @@ QFAI includes a small set of custom skills (stored under `.qfai/assistant/skills
 - **qfai-configure**: Analyze the repository (language, frameworks, test layout, directory structure)
   and tailor `qfai.config.yaml` accordingly (especially `testFileGlobs`).
   Run this once right after `npx qfai init`, and re-run it when the repository structure changes.
-- **qfai-discussion**: Run a unified structured discussion that merges discuss and require into a single 15-file discussion pack under `.qfai/discussion/discussion-<ts>/`.
+- **qfai-discussion**: Run a unified structured discussion that produces and maintains the latest discussion pack as 15 required markdown files plus required prototyping.yaml under `.qfai/discussion/discussion-<ts>/`.
 - **qfai-sdd**: Unified SDD entrypoint with discussion-pack preflight guard (missing/incomplete/blocking OQ causes stop + next action guidance).
-- **qfai-prototyping**: Build an all-spec contract-aligned skeleton and prove runtime coverage before deep coding.
+- **qfai-prototyping**: Build a contract-aligned implementation skeleton with static-first evidence by default, and escalate to full-harness only when explicitly justified.
 - **qfai-atdd**: Implement acceptance tests driven by specs/scenarios.
 - **qfai-implement**: Unified TDD micro-cycle (Red/Green/Refactor) one test at a time using `test-list.md` as the execution ledger, including ledger status updates and exception closure.
 - **qfai-verify**: Run full-scan local quality gates (`validate --fail-on error`, `report`, repo gates) and produce reviewer-approved evidence under `.qfai/evidence/`.
@@ -196,7 +156,7 @@ Operational notes.
 - Change classification (Primary/Tags) is required in `09_delta.md` and recommended in PRs. See `.qfai/assistant/instructions/change-classification.md`.
 - Verification planning is recorded in `09_delta.md` (`Verification -> Plan`) and validated in CI (`VFY-*` rules).
 - Review gate policies (required/optional layers and reviewers) are defined in `.qfai/assistant/steering/review-gate.rules.yml`.
-- Review roster SSOT is defined in `.qfai/assistant/steering/review-roster.yml`.
+- Agent taxonomy and invocation SSOT are defined in `.qfai/assistant/steering/agent-catalog.yml`, `.qfai/assistant/steering/agent-routing.yml`, and `.qfai/assistant/steering/review-profiles.yml`.
 
 ## Configuration
 
@@ -229,6 +189,8 @@ Notes.
 
 - `validate.json`, `report.json`, `doctor.json`, and `run-*` JSON logs are internal exports and are not a stable external contract; prefer `report.md` for integrations that must survive tool upgrades.
 - Scenario files are expected to use the Gherkin extension `*.feature` (not `*.md`).
+- `prototyping.calibration` in `qfai.config.yaml` connects full-harness scoring thresholds to the report and validator.
+- Observability modules (`src/core/observability/`) exist as foundation code but are **not integrated into blocking validation** in v1.7.13. They are reserved for future operational instrumentation.
 
 ## Specifications and contracts (SDD)
 
@@ -329,18 +291,24 @@ Typical customizations.
 │   ├── assistant
 │   │   ├── agents
 │   │   │   ├── README.md
-│   │   │   ├── architect.md
+│   │   │   ├── acceptance-test-engineer.md
+│   │   │   ├── architecture-reviewer.md
 │   │   │   ├── backend-engineer.md
-│   │   │   ├── code-reviewer.md
-│   │   │   ├── contract-designer.md
+│   │   │   ├── completion-reviewer.md
+│   │   │   ├── delivery-planner.md
 │   │   │   ├── devops-ci-engineer.md
-│   │   │   ├── facilitator.md
+│   │   │   ├── discovery-analyst.md
 │   │   │   ├── frontend-engineer.md
-│   │   │   ├── interviewer.md
-│   │   │   ├── planner.md
-│   │   │   ├── qa-engineer.md
+│   │   │   ├── implementation-reviewer.md
+│   │   │   ├── orchestrator.md
+│   │   │   ├── product-experience-architect.md
+│   │   │   ├── product-surface-reviewer.md
+│   │   │   ├── qa-gatekeeper.md
+│   │   │   ├── qa-strategist.md
 │   │   │   ├── requirements-analyst.md
-│   │   │   └── test-engineer.md
+│   │   │   ├── requirements-reviewer.md
+│   │   │   ├── solution-architect.md
+│   │   │   └── test-design-analyst.md
 │   │   ├── instructions
 │   │   │   ├── README.md
 │   │   │   ├── agent-selection.md
@@ -372,18 +340,22 @@ Typical customizations.
 │   │   │   └── README.md
 │   │   ├── steering
 │   │   │   ├── README.md
+│   │   │   ├── agent-catalog.yml
+│   │   │   ├── agent-routing.yml
 │   │   │   ├── review-gate.rules.yml
-│   │   │   ├── review-roster.yml
+│   │   │   ├── review-profiles.yml
 │   │   │   ├── product.md
 │   │   │   ├── structure.md
 │   │   │   └── tech.md
 │   │   └── README.md
-│   ├── discuss
+│   ├── discussion
 │   │   ├── README.md
-│   │   └── discuss-20260215205220203
+│   │   └── discussion-YYYYMMDDhhmmssSSS
 │   │       ├── 01_Context.md
 │   │       ├── ...
-│   │       └── 09_delta.md
+│   │       ├── 14_Review-Request.md
+│   │       ├── 99_delta.md
+│   │       └── prototyping.yaml
 │   ├── contracts
 │   │   ├── api
 │   │   │   └── README.md
@@ -400,14 +372,6 @@ Typical customizations.
 │   │       ├── validator.json
 │   │       ├── traceability.json
 │   │       └── summary.md
-│   ├── require
-│   │   ├── README.md
-│   │   └── require-20260215205220203
-│   │       ├── 01_Sources.md
-│   │       ├── 02_Scope.md
-│   │       ├── 03_REQ.md
-│   │       ├── ...
-│   │       └── 09_delta.md
 │   ├── review
 │   │   ├── .gitignore
 │   │   └── README.md
@@ -420,8 +384,8 @@ Typical customizations.
 Integration wrappers are also generated for immediate use:
 
 - Agents/Codex VS Code: `.agents/skills/**`
-- Claude Code: `.claude/commands/**`, `.claude/agents/**`
-- GitHub Copilot: `.github/prompts/**`, `.github/agents/**`
+- Claude Code: `.claude/skills/**`, `.claude/agents/**`
+- GitHub Copilot: `.github/skills/**`, `.github/agents/**`
 - Codex: `.codex/skills/**`
 
 ## Agent integrations

package/assets/init/.qfai/README.md

@@ -28,8 +28,15 @@ flowchart TD
 ```text
 .qfai/
 ├── README.md
-├── discuss/
-│   └── README.md
+├── discussion/
+│   ├── README.md
+│   └── discussion-YYYYMMDDhhmmssSSS/
+│       ├── 01_Context.md
+│       ├── 02_Inception-Deck.md
+│       ├── ...
+│       ├── 14_Review-Request.md
+│       ├── 99_delta.md
+│       └── prototyping.yaml
 ├── assistant/
 │   ├── skills/               # canonical skills (SSOT)
 │   ├── skills.local/         # project-specific overrides
@@ -37,18 +44,6 @@ flowchart TD
 │   ├── templates/            # shared assistant templates (RCP footer SSOT)
 │   ├── steering/             # project steering inputs and review roster
 │   └── instructions/         # workflow and guardrail docs
-├── require/
-│   ├── README.md
-│   └── require-YYYYMMDDhhmmssSSS/
-│       ├── 01_Sources.md
-│       ├── 02_Scope.md
-│       ├── 03_REQ.md
-│       ├── 04_NFR.md
-│       ├── 05_Glossary.md
-│       ├── 06_Constraints.md
-│       ├── 07_Policy.md
-│       ├── 08_OQ.md
-│       └── 09_delta.md
 ├── report/
 │   ├── .gitignore
 │   └── README.md
@@ -104,7 +99,7 @@ It is useful for local review but should not pollute version control.
 
 ### R5. init is an empty scaffold
 
-- `qfai init` creates README-centric directories for `discuss`, `require`, `report`, `contracts`, and `specs`.
+- `qfai init` creates README-centric directories for `discussion`, `report`, `contracts`, and `specs`.
 - Sample artifacts are provided under skill templates (for example, `assistant/skills/qfai-sdd/templates/contracts/`).
 
 ## Skills (SSOT)
@@ -114,7 +109,7 @@ Invoke canonical skills from this tree directly.
 
 ## Where to look next
 
-- Requirements format: `require/README.md`
+- Discussion format: `discussion/README.md`
 - Review gate format: `review/README.md`
 - Contracts format: `contracts/README.md` and child READMEs
 - Layered spec format: `specs/README.md`

package/assets/init/.qfai/assistant/agents/acceptance-test-engineer.md

@@ -0,0 +1,51 @@
+# Acceptance Test Engineer
+
+## Mission
+
+- Design and implement executable acceptance tests across E2E, API, and integration layers.
+
+## Domain Responsibilities
+
+- Implement E2E coverage for required user stories.
+- Implement API coverage for declared `CON-API-*` contracts.
+- Implement integration coverage for required `TC-*` behavior.
+- Keep test-layer responsibilities separated while coordinating shared fixtures and evidence.
+
+## Inputs you must read
+
+- .qfai/assistant/instructions/\*
+- .qfai/assistant/steering/\*
+- .qfai/assistant/steering/test-layers.md
+- .qfai/specs/spec-\*/09_delta.md
+- .qfai/specs/spec-\*/02_User-stories.md
+- .qfai/specs/spec-\*/06_Test-Cases.md
+- .qfai/contracts/api/\*\*
+
+## Deliverables
+
+- Acceptance test plan and implemented coverage
+- Mapping from US / TC / CON-API to test assets
+- Execution proof and evidence summary
+- Gaps and follow-up actions
+
+## Stop conditions
+
+- Governing specs, routing rules, or required source artifacts are missing.
+- The requested output belongs to another specialist's ownership without an explicit handoff.
+- The task would bypass required validation or reviewer gates.
+
+## Sign-off
+
+- [ ] Deliverables are complete
+- [ ] Ownership boundaries were respected
+- [ ] Required gates and follow-up evidence are recorded
+
+## When to use
+
+- Use when `agent-routing.yml` assigns this domain to the current phase.
+- Use when the task needs this specialist's owned artifacts or decisions.
+
+## When not to use
+
+- Do not use when the task is primarily review-only and needs a reviewer instead.
+- Do not use when another specialist owns the main artifact or decision surface.

package/assets/init/.qfai/assistant/agents/architecture-reviewer.md

@@ -0,0 +1,57 @@
+# Architecture Reviewer
+
+## Mission
+
+- Review architecture and contract decisions for correctness, consistency, and rejected-option safety.
+
+## Domain Responsibilities
+
+- Audit architecture boundaries, trade-offs, and technical consistency.
+- Audit contract decisions across UI, API, and DB surfaces.
+- Block reintroduction of rejected architecture options without RE-OPEN.
+- Review design against SOLID, KISS, YAGNI, DRY, separation of concerns, coupling/cohesion, and composition-over-inheritance where relevant.
+- Check that extensions are justified by current requirements and do not introduce speculative abstraction or over-engineering.
+- Verify contracts, module boundaries, and public interfaces obey least astonishment and design-by-contract expectations.
+
+## Inputs you must read
+
+- .qfai/assistant/instructions/\*
+- .qfai/assistant/instructions/drift-protocol.md
+- .qfai/assistant/steering/\*
+- .qfai/assistant/steering/test-layers.md
+- .qfai/specs/spec-\*/09_delta.md
+- .github/instructions/code-review.instructions.md
+- .github/instructions/principles.instructions.md
+- .instruction/00_universal/development-principles-checklist.md
+- .instruction/01_specialties/design.md
+- Architecture decisions, diagrams, and `.qfai/contracts/**`
+
+## Deliverables
+
+- Review decision with findings
+- Required changes to architecture or contracts
+- Evidence summary and unresolved technical risks
+- Explicit trade-off notes when principles conflict (for example KISS vs OCP, DRY vs YAGNI)
+
+## Stop conditions
+
+- Required evidence, governing specs, or target artifacts are missing.
+- The request requires implementation or file editing instead of independent review.
+- The issue falls outside this review domain and must be rerouted to another specialist first.
+- The design direction depends on hypothetical future use cases rather than accepted scope.
+
+## Sign-off
+
+- [ ] Review verdict is explicit
+- [ ] Findings cite concrete artifacts or evidence
+- [ ] Required gates and residual risks are recorded
+
+## When to use
+
+- Use when this review domain is required by `agent-routing.yml` or explicitly requested.
+- Use when an independent specialist check is needed before completion.
+
+## When not to use
+
+- Do not use as a substitute for implementation or planning work.
+- Do not use when another reviewer domain is the primary concern.

package/assets/init/.qfai/assistant/agents/backend-engineer.md

@@ -2,49 +2,58 @@
 
 ## Mission
 
-- Implement backend behavior aligned with specs and contracts.
+- Implement backend behavior aligned with specs, contracts, and operational constraints.
+
+## Domain Responsibilities
+
+- Build API, domain, persistence, and service boundary behavior.
+- Respect API and DB contracts plus reliability expectations.
+- Coordinate with test and CI agents on runtime and integration implications.
+- Implement with SOLID, KISS, YAGNI, and DRY: prefer simple contracts, explicit invariants, and minimal moving parts over speculative extensibility.
+- Keep business logic, transport, persistence, and infrastructure concerns separated to reduce coupling and surprise.
+- Apply fail-fast validation, defensive programming, and least-privilege thinking to inputs, permissions, data access, and operational behavior.
 
 ## Inputs you must read
 
 - .qfai/assistant/instructions/\*
 - .qfai/assistant/steering/\*
-- .qfai/assistant/steering/test-layers.md (US/TC/CON-API hard obligations)
-- .qfai/specs/spec-\*/09_delta.md (Decision Records; check rejected)
+- .qfai/assistant/steering/test-layers.md
+- .qfai/specs/spec-\*/09_delta.md
 - .qfai/specs/spec-\*/01_Spec.md
-- Optional legacy input: `.qfai/specs/spec-*/scenario.feature`
+- .github/instructions/principles.instructions.md
+- .instruction/00_universal/development-principles-checklist.md
+- .instruction/01_specialties/implementation.md
+- .instruction/01_specialties/design.md
 - .qfai/contracts/api/\*\*
 - .qfai/contracts/db/\*\*
 
-## Deliverables (MANDATORY)
+## Deliverables
 
-- Decision Records referenced (DR-IDs) + rejected check (or RE-OPEN request)
-- Implementation mapping (contract/spec obligations -> file/function)
-- Backend code changes (minimal, traceable)
-- Validation gate evidence (`qfai validate --fail-on error`) for touched scope
-- Execution proof (commands + key outputs)
-- Evidence summary for `.qfai/evidence/` (gitignored; do not commit)
+- Backend implementation summary
+- Changed files and affected contracts
+- Local verification notes
+- Evidence summary for `.qfai/evidence/`
+- Notes on invariants, validation, and why added abstractions/configuration are necessary now
 
-## Stop conditions (Blockers)
+## Stop conditions
 
-- Rejected option would be reintroduced without RE-OPEN DR
-- Required contracts/specs are missing or ambiguous
-- Evidence is missing or incomplete
-- Tests or quality gates fail and cannot be made green
-- Scope ambiguity prevents a safe decision
+- Governing specs, routing rules, or required source artifacts are missing.
+- The requested output belongs to another specialist's ownership without an explicit handoff.
+- The task would bypass required validation or reviewer gates.
+- The requested change would introduce unnecessary indirection, unused extension points, or unverifiable operational complexity.
 
-## Sign-off checklist (Check Last)
+## Sign-off
 
 - [ ] Deliverables are complete
-- [ ] Evidence is present (gitignored)
-- [ ] No silent gaps remain
-- [ ] Handoff includes actionable next steps
-
-## Output format (structured)
-
-- Decision Records (DR-IDs) / rejected check
-- Findings
-- Decisions
-- Proposed edits (files/sections)
-- Evidence summary
-- Open Questions / Risks
-- Confidence (High/Medium/Low + reason)
+- [ ] Ownership boundaries were respected
+- [ ] Required gates and follow-up evidence are recorded
+
+## When to use
+
+- Use when `agent-routing.yml` assigns this domain to the current phase.
+- Use when the task needs this specialist's owned artifacts or decisions.
+
+## When not to use
+
+- Do not use when the task is primarily review-only and needs a reviewer instead.
+- Do not use when another specialist owns the main artifact or decision surface.

package/assets/init/.qfai/assistant/agents/completion-reviewer.md

@@ -0,0 +1,48 @@
+# Completion Reviewer
+
+## Mission
+
+- Independently audit Completion Contract, prompt DoD, and drift-protocol compliance.
+
+## Domain Responsibilities
+
+- Return pass/fail only with actionable rework instructions.
+- Enforce validate evidence, required coverage obligations, and no self-approval.
+- Verify rejected options are not reintroduced without RE-OPEN.
+
+## Inputs you must read
+
+- .qfai/assistant/instructions/\*
+- .qfai/assistant/instructions/drift-protocol.md
+- .qfai/assistant/steering/\*
+- .qfai/assistant/steering/test-layers.md
+- .qfai/specs/spec-\*/09_delta.md
+- Validation evidence and gate results
+
+## Deliverables
+
+- PASS or FAIL with concrete rework list
+- Evidence summary and gaps
+- Open risks or blocking assumptions
+
+## Stop conditions
+
+- Required evidence, governing specs, or target artifacts are missing.
+- The request requires implementation or file editing instead of independent review.
+- The issue falls outside this review domain and must be rerouted to another specialist first.
+
+## Sign-off
+
+- [ ] Review verdict is explicit
+- [ ] Findings cite concrete artifacts or evidence
+- [ ] Required gates and residual risks are recorded
+
+## When to use
+
+- Use when this review domain is required by `agent-routing.yml` or explicitly requested.
+- Use when an independent specialist check is needed before completion.
+
+## When not to use
+
+- Do not use as a substitute for implementation or planning work.
+- Do not use when another reviewer domain is the primary concern.

package/assets/init/.qfai/assistant/agents/delivery-planner.md

@@ -0,0 +1,52 @@
+# Delivery Planner
+
+## Mission
+
+- Create phased execution plans with risks, dependencies, ownership, and DoD.
+- Own delivery sequencing, priority decisions, and parallelization policy.
+
+## Domain Responsibilities
+
+- Decompose work into phases and checkpoints.
+- Define parallel-safe slices and post-merge verification conditions.
+- Own schedule, priority, and risk trade-offs across roles.
+- Produce actionable work orders for workers and reviewers.
+
+## Inputs you must read
+
+- .qfai/assistant/instructions/\*
+- .qfai/assistant/steering/\*
+- .qfai/specs/spec-\*/09_delta.md
+- .qfai/specs/spec-\*/01_Spec.md
+- .qfai/discussion/discussion-\*/04_Sources.md
+- .qfai/discussion/discussion-\*/06_REQ.md
+- .qfai/discussion/discussion-\*/11_OQ-Register.md
+
+## Deliverables
+
+- Phased plan with owners, dependencies, and risks
+- Explicit DoD and gate commands
+- Parallelization decision and rerun policy
+- Evidence summary for `.qfai/evidence/`
+
+## Stop conditions
+
+- Governing specs, routing rules, or required source artifacts are missing.
+- The requested output belongs to another specialist's ownership without an explicit handoff.
+- The task would bypass required validation or reviewer gates.
+
+## Sign-off
+
+- [ ] Deliverables are complete
+- [ ] Ownership boundaries were respected
+- [ ] Required gates and follow-up evidence are recorded
+
+## When to use
+
+- Use when `agent-routing.yml` assigns this domain to the current phase.
+- Use when the task needs this specialist's owned artifacts or decisions.
+
+## When not to use
+
+- Do not use when the task is primarily review-only and needs a reviewer instead.
+- Do not use when another specialist owns the main artifact or decision surface.

package/assets/init/.qfai/assistant/agents/devops-ci-engineer.md

@@ -2,44 +2,47 @@
 
 ## Mission
 
-- Run quality gates and provide reproducible CI evidence.
+- Run quality gates and produce reproducible CI and runtime evidence.
+
+## Domain Responsibilities
+
+- Execute build, lint, typecheck, test, validate, and report workflows.
+- Record commands, key outputs, environment assumptions, and reproducibility notes.
+- Surface CI/runtime blockers with minimal ambiguity.
 
 ## Inputs you must read
 
 - .qfai/assistant/instructions/\*
 - .qfai/assistant/steering/\*
-- .qfai/specs/spec-\*/09_delta.md (Decision Records; check rejected)
-- package.json scripts and CI config
+- .qfai/specs/spec-\*/09_delta.md
+- package.json scripts, CI config, and runbooks
 - Evidence summaries under `.qfai/evidence/`
 
-## Deliverables (MANDATORY)
+## Deliverables
 
-- Decision Records referenced (DR-IDs) + rejected check (or RE-OPEN request)
-- Exact commands executed and key outputs
-- Reproducibility notes (env, versions, prerequisites)
-- Gate status summary (PASS/FAIL)
-- Evidence summary for `.qfai/evidence/` (gitignored; do not commit)
+- Executed commands and key outputs
+- CI / runtime evidence summary
+- Reproducibility notes
+- Blockers and required follow-up
 
-## Stop conditions (Blockers)
+## Stop conditions
 
-- Rejected option would be reintroduced without RE-OPEN DR
-- Cannot run end-to-end locally
-- Missing environment setup instructions
-- Evidence is missing or incomplete
+- Governing specs, routing rules, or required source artifacts are missing.
+- The requested output belongs to another specialist's ownership without an explicit handoff.
+- The task would bypass required validation or reviewer gates.
 
-## Sign-off checklist (Check Last)
+## Sign-off
 
 - [ ] Deliverables are complete
-- [ ] Evidence is present (gitignored)
-- [ ] No silent gaps remain
-- [ ] Gate results are explicit
-
-## Output format (structured)
-
-- Decision Records (DR-IDs) / rejected check
-- Commands executed
-- Gate results
-- Evidence summary
-- Risks and blockers
-- Open Questions
-- Confidence (High/Medium/Low + reason)
+- [ ] Ownership boundaries were respected
+- [ ] Required gates and follow-up evidence are recorded
+
+## When to use
+
+- Use when `agent-routing.yml` assigns this domain to the current phase.
+- Use when the task needs this specialist's owned artifacts or decisions.
+
+## When not to use
+
+- Do not use when the task is primarily review-only and needs a reviewer instead.
+- Do not use when another specialist owns the main artifact or decision surface.