haiku-method 2.2.0

package/studios/quality-assurance/stages/analyze/STAGE.md

@@ -0,0 +1,17 @@
+---
+name: analyze
+description: Analyze test results and compute quality metrics
+hats: [analyst, statistician, verifier]
+fix_hats: [analyst, feedback-assessor]
+review: ask
+elaboration: autonomous
+inputs:
+  - stage: execute-tests
+    output: test-results
+  - stage: plan
+    discovery: test-strategy
+---
+
+# Analyze
+
+Analyze test results and compute quality metrics.

package/studios/quality-assurance/stages/analyze/discovery/QUALITY-REPORT.md

@@ -0,0 +1,29 @@
+---
+name: quality-report
+location: .haiku/intents/{intent-slug}/knowledge/QUALITY-REPORT.md
+scope: intent
+format: text
+required: true
+---
+
+# Quality Report
+
+Quality metrics, defect pattern analysis, and improvement recommendations.
+
+## Content Guide
+
+Structure the report for quality decision-making:
+
+- **Quality metrics** -- defect density, severity distribution, pass rates, and coverage
+- **Defect patterns** -- clusters and categories with root cause analysis
+- **Trend analysis** -- comparison against historical baselines with significance assessment
+- **Risk assessment** -- unresolved defects mapped to business impact
+- **Root cause analysis** -- systemic quality issues grouped by category
+- **Improvement recommendations** -- prioritized actions for quality improvement
+
+## Quality Signals
+
+- Metrics are accurately computed with verified underlying data
+- Pattern analysis identifies systemic issues, not just individual defects
+- Trend comparisons control for scope and complexity differences
+- Recommendations are specific, actionable, and prioritized by impact

package/studios/quality-assurance/stages/analyze/hats/analyst.md

@@ -0,0 +1,13 @@
+**Focus:** Analyze test results to identify quality patterns, root causes, and actionable improvement opportunities.
+
+**Responsibilities:**
+- Compute quality metrics (defect density, severity distribution, pass rates)
+- Identify defect patterns and clusters that indicate systemic issues
+- Perform root cause analysis grouping defects by category
+- Produce a quality report with findings and improvement recommendations
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** report metrics without analyzing what they mean
+- The agent **MUST NOT** treat each defect in isolation without looking for patterns
+- The agent **MUST NOT** comput averages that mask important variation
+- The agent **MUST NOT** produce analysis that is descriptive but not actionable

package/studios/quality-assurance/stages/analyze/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/quality-assurance/stages/analyze/hats/statistician.md

@@ -0,0 +1,13 @@
+**Focus:** Validate quality metrics with statistical rigor and ensure trend analysis is sound.
+
+**Responsibilities:**
+- Validate metric calculations and confirm data integrity
+- Apply statistical methods to trend analysis to distinguish signal from noise
+- Compare current release quality against historical baselines with significance testing
+- Identify whether quality differences between components or releases are statistically meaningful
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** present trends without enough data points to be meaningful
+- The agent **MUST NOT** draw conclusions from metrics without considering sample sizes
+- The agent **MUST NOT** compar releases without controlling for scope or complexity differences
+- The agent **MUST NOT** use complex statistics when simple descriptive metrics would be more useful

package/studios/quality-assurance/stages/analyze/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the analyze stage of quality-assurance. Units here are analysis finding — knowledge artifacts that downstream stages consume. Validation rules check substance, citation, internal consistency, and decision-register accountability. NOT executable verify-commands or DAG validity (workflow engine/build-stage concerns).
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Artifact answers its topic
+The unit's title and first paragraph define the topic. The remaining body MUST deliver substantive content on that topic. Reject placeholders, content-free outlines, or redirects.
+
+### 2. Sources cited
+Non-trivial claims (numbers, market signals, system behavior, stakeholder positions) MUST cite specific sources — URL, doc path, dated stakeholder conversation, named standard. Reject "industry common knowledge" or unsourced numerical claims.
+
+### 3. Internal consistency
+Title, mission, and body must align. Numerical/categorical claims must be consistent across the body. Recommendations must follow from the evidence presented.
+
+### 4. Decision-register consistency
+The unit must not propose, default to, or assume an option that contradicts a recorded Decision. Cite the Decision ID in any rejection.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted with veto-style approval, OR flagged `(needs human escalation)`.

package/studios/quality-assurance/stages/analyze/outputs/QUALITY-REPORT.md

@@ -0,0 +1,25 @@
+---
+name: quality-report
+location: .haiku/intents/{intent-slug}/stages/analyze/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Quality Report
+
+Test result analysis with quality metrics, root cause categorization, and release recommendation.
+
+## Expected Artifacts
+
+- **Quality metrics** -- defect density, severity distribution, and trend analysis
+- **Root cause analysis** -- defects grouped by category (design, code, environment, data) with distribution
+- **Risk assessment** -- unresolved defects mapped to business impact
+- **Release recommendation** -- release, defer, or block with supporting rationale
+
+## Quality Signals
+
+- Defect density and severity distribution are computed with trend analysis
+- Root causes are categorized with distribution percentages
+- Unresolved defects are mapped to business impact
+- Release recommendation is evidence-based with clear rationale

package/studios/quality-assurance/stages/analyze/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Analyze Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Quality report includes defect density, severity distribution, and trend analysis compared to previous releases"
+- "Root cause analysis groups defects into categories (design, code, environment, data) with distribution percentages"
+- "Risk assessment maps unresolved defects to business impact with recommendation for release, defer, or block"
+
+### Bad criteria — vague (no clear check)
+
+- "Results are analyzed"
+- "Metrics are computed"
+- "Quality is assessed"
+

package/studios/quality-assurance/stages/analyze/review-agents/insight.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify quality analysis produces actionable insights, not just metrics.
+
+**Check:**
+- The agent **MUST** verify that quality metrics are accurately computed with verified underlying data
+- The agent **MUST** verify that defect pattern analysis identifies root causes, not just categories
+- The agent **MUST** verify that trend comparisons use appropriate baselines and account for scope differences
+- The agent **MUST** verify that improvement recommendations are specific and prioritized by impact

package/studios/quality-assurance/stages/certify/STAGE.md

@@ -0,0 +1,19 @@
+---
+name: certify
+description: Quality sign-off and release readiness assessment
+hats: [certifier, reviewer]
+fix_hats: [certifier, feedback-assessor]
+review: external
+elaboration: autonomous
+inputs:
+  - stage: analyze
+    discovery: quality-report
+  - stage: execute-tests
+    output: test-results
+  - stage: plan
+    discovery: test-strategy
+---
+
+# Certify
+
+Quality sign-off and release readiness assessment.

package/studios/quality-assurance/stages/certify/discovery/CERTIFICATION-REPORT.md

@@ -0,0 +1,29 @@
+---
+name: certification-report
+location: .haiku/intents/{intent-slug}/knowledge/CERTIFICATION-REPORT.md
+scope: intent
+format: text
+required: true
+---
+
+# Certification Report
+
+Quality certification determination with evidence, known issues, and release readiness assessment.
+
+## Content Guide
+
+Structure the report as the official quality record:
+
+- **Exit criteria evaluation** -- each criterion from the test strategy with evidence and pass/fail
+- **Certification determination** -- certify/reject with explicit rationale
+- **Known issues** -- unresolved defects with risk acceptance and product owner acknowledgment
+- **Release readiness** -- assessment across all quality dimensions
+- **Conditions** -- any conditions or caveats attached to the certification
+- **Sign-off record** -- certifier and reviewer approvals with dates
+
+## Quality Signals
+
+- Every exit criterion is evaluated with specific supporting evidence
+- Known issues have documented risk acceptance from the product owner
+- Certification rationale is explicit and auditable
+- Release readiness covers all quality dimensions, not just functional testing

package/studios/quality-assurance/stages/certify/hats/certifier.md

@@ -0,0 +1,13 @@
+**Focus:** Evaluate all quality evidence against exit criteria and make a certification determination.
+
+**Responsibilities:**
+- Assess each exit criterion from the test strategy with supporting evidence
+- Document the certification determination with explicit rationale
+- Compile the known issues list with risk acceptance for unresolved defects
+- Produce the certification report as the official quality record
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** certify based on gut feel rather than evidence against defined criteria
+- The agent **MUST NOT** accept risk for unresolved defects without product owner acknowledgment
+- The agent **MUST NOT** certify quality while ignoring categories of testing that were not completed
+- The agent **MUST** document the rationale for certification decisions

package/studios/quality-assurance/stages/certify/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/quality-assurance/stages/certify/hats/reviewer.md

@@ -0,0 +1,16 @@
+---
+interpretation: lens
+---
+**Focus:** Independently validate the certification evidence and approve or reject the release readiness determination.
+
+**Responsibilities:**
+- Review certification evidence for completeness and accuracy
+- Verify that the certifier's determination is supported by the evidence
+- Challenge any assumptions or gaps in the certification rationale
+- Provide an independent release readiness opinion
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** rubber-stamp the certifier's determination without independent review
+- The agent **MUST NOT** review only the summary without checking the underlying evidence
+- The agent **MUST NOT** approve release readiness under pressure without adequate quality evidence
+- The agent **MUST** escalate when certification evidence is insufficient

package/studios/quality-assurance/stages/certify/outputs/CERTIFICATION-REPORT.md

@@ -0,0 +1,25 @@
+---
+name: certification-report
+location: .haiku/intents/{intent-slug}/stages/certify/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Certification Report
+
+Quality sign-off confirming exit criteria are met with release readiness assessment.
+
+## Expected Artifacts
+
+- **Exit criteria verification** -- each criterion from the test strategy confirmed with evidence
+- **Known issues list** -- unresolved defects with risk acceptance rationale
+- **Release readiness checklist** -- functional quality, performance, security, and regression status
+- **Sign-off record** -- certification approval with any conditions
+
+## Quality Signals
+
+- All exit criteria from the test strategy are met with evidence
+- Known issues have risk acceptance rationale signed by the product owner
+- Release readiness covers functional, performance, security, and regression dimensions
+- Certification is documented with any conditions noted

package/studios/quality-assurance/stages/certify/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Certify Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Certification report confirms all exit criteria from the test strategy are met with evidence for each criterion"
+- "Known issues list documents every unresolved defect with risk acceptance rationale signed by the product owner"
+- "Release readiness checklist covers functional quality, performance benchmarks, security scan results, and regression status"
+
+### Bad criteria — vague (no clear check)
+
+- "Quality is certified"
+- "Release is ready"
+- "Sign-off is obtained"
+

package/studios/quality-assurance/stages/certify/review-agents/standards.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify certification determination is evidence-based and meets all exit criteria.
+
+**Check:**
+- The agent **MUST** verify that every exit criterion from the test strategy is evaluated with supporting evidence
+- The agent **MUST** verify that known issues have documented risk acceptance from the product owner
+- The agent **MUST** verify that certification rationale is explicit and auditable
+- The agent **MUST** verify that release readiness assessment covers all quality dimensions, not just functional testing

package/studios/quality-assurance/stages/design-tests/STAGE.md

@@ -0,0 +1,15 @@
+---
+name: design-tests
+description: Design test cases and plan automation
+hats: [designer, automator, verifier]
+fix_hats: [designer, feedback-assessor]
+review: auto
+elaboration: autonomous
+inputs:
+  - stage: plan
+    discovery: test-strategy
+---
+
+# Design Tests
+
+Design test cases and plan automation.

package/studios/quality-assurance/stages/design-tests/discovery/TEST-SUITE-SPEC.md

@@ -0,0 +1,29 @@
+---
+name: test-suite-spec
+location: .haiku/intents/{intent-slug}/knowledge/TEST-SUITE-SPEC.md
+scope: intent
+format: text
+required: true
+---
+
+# Test Suite Spec
+
+Test case inventory with requirement traceability and automation plan.
+
+## Content Guide
+
+Structure the spec for efficient test execution:
+
+- **Traceability matrix** -- mapping of test cases to requirements
+- **Test cases** -- for each: ID, description, preconditions, steps, expected results, pass/fail criteria
+- **Test data requirements** -- data sets needed including boundary conditions and edge cases
+- **Automation plan** -- which tests to automate, framework, and tooling requirements
+- **Coverage analysis** -- coverage targets vs planned coverage with gap justification
+- **Execution priority** -- test execution order based on strategy priorities
+
+## Quality Signals
+
+- Every requirement has at least one associated test case
+- Test cases have explicit expected results, not just steps
+- Automation candidates are selected based on ROI analysis
+- Coverage meets the targets defined in the test strategy

package/studios/quality-assurance/stages/design-tests/hats/automator.md

@@ -0,0 +1,13 @@
+**Focus:** Assess automation feasibility and design the automation strategy for the test suite.
+
+**Responsibilities:**
+- Evaluate which test cases are candidates for automation based on ROI
+- Define the automation framework and tooling requirements
+- Design automation architecture for maintainability and reliability
+- Establish automation standards and patterns for the team
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** automat everything without considering maintenance cost vs execution frequency
+- The agent **MUST NOT** choose automation tools before understanding the test requirements
+- The agent **MUST NOT** design automation that is tightly coupled to implementation details
+- The agent **MUST** account for test data management and environment setup in automation

package/studios/quality-assurance/stages/design-tests/hats/designer.md

@@ -0,0 +1,13 @@
+**Focus:** Design test cases that provide comprehensive coverage of requirements while enabling efficient execution.
+
+**Responsibilities:**
+- Create test cases with clear preconditions, steps, expected results, and pass/fail criteria
+- Build traceability matrix linking test cases to requirements
+- Design test data sets that cover boundary conditions and edge cases
+- Optimize test suite to minimize redundancy while maximizing coverage
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** write test cases without explicit expected results
+- The agent **MUST NOT** design tests that only cover the happy path
+- The agent **MUST** maintain traceability between tests and requirements
+- The agent **MUST NOT** create unnecessarily verbose test cases that slow down execution

package/studios/quality-assurance/stages/design-tests/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/quality-assurance/stages/design-tests/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit design/synthesis artifact for the design-tests stage of quality-assurance. Units here are test design — designed outputs that downstream stages execute against. Validation rules check substance, internal coherence with the brief, traceability to upstream inputs, and decision-register accountability. NOT executable verify-commands.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Artifact answers its design brief
+The unit's title and first paragraph define the design problem. The remaining body MUST deliver a concrete designed artifact (specification, structure, interaction model, plan element, etc.) — not an outline, not a deferral, not a "we'll figure this out later".
+
+### 2. Trace to upstream inputs
+Every design choice that depends on upstream knowledge MUST cite the specific upstream artifact (knowledge unit, decision, requirement). Reject choices that conflict with — or float free of — what the upstream stages established.
+
+### 3. Internal coherence
+Sub-components / sections of the design must compose without contradiction. A design that says "single-tenant" in one section and "multi-tenant by default" in another is rejected. Cite the contradicting paragraphs.
+
+### 4. Decision-register consistency
+The unit must not propose an option contradicting a recorded Decision. Cite the Decision ID.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted, OR flagged `(needs human escalation)`. Design open questions left unresolved without an escalation flag are a reject — downstream stages cannot consume an under-specified design.

package/studios/quality-assurance/stages/design-tests/outputs/TEST-SUITE-SPEC.md

@@ -0,0 +1,25 @@
+---
+name: test-suite-spec
+location: .haiku/intents/{intent-slug}/stages/design-tests/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Test Suite Specification
+
+Test cases with traceability matrix, automation plan, and test data requirements.
+
+## Expected Artifacts
+
+- **Test cases** -- each with preconditions, steps, expected results, and pass/fail criteria
+- **Traceability matrix** -- tests linked to requirements ensuring coverage
+- **Automation plan** -- which tests to automate vs manual with rationale
+- **Test data requirements** -- data needed for test execution documented
+
+## Quality Signals
+
+- Every requirement has at least one test case linked via traceability matrix
+- Test cases have explicit preconditions, steps, and expected results
+- Automation feasibility is assessed with framework and tooling identified
+- Coverage meets the strategy targets

package/studios/quality-assurance/stages/design-tests/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Design Tests Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Test suite spec includes test cases for every requirement with traceability matrix linking tests to requirements"
+- "Each test case has explicit preconditions, steps, expected results, and pass/fail criteria"
+- "Automation feasibility assessment identifies which tests to automate, which to run manually, and the rationale"
+
+### Bad criteria — vague (no clear check)
+
+- "Test cases are designed"
+- "Automation is planned"
+- "Tests are ready"
+

package/studios/quality-assurance/stages/design-tests/review-agents/traceability.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify test cases are traceable to requirements and provide the coverage defined in the strategy.
+
+**Check:**
+- The agent **MUST** verify that every requirement has at least one associated test case
+- The agent **MUST** verify that test cases include explicit preconditions, steps, and expected results
+- The agent **MUST** verify that automation candidates are selected based on ROI analysis, not convenience
+- The agent **MUST** verify that test data requirements cover boundary conditions and edge cases

package/studios/quality-assurance/stages/execute-tests/STAGE.md

@@ -0,0 +1,17 @@
+---
+name: execute-tests
+description: Execute tests and log defects
+hats: [tester, reporter, verifier]
+fix_hats: [tester, feedback-assessor]
+review: auto
+elaboration: autonomous
+inputs:
+  - stage: design-tests
+    discovery: test-suite-spec
+  - stage: plan
+    discovery: test-strategy
+---
+
+# Execute Tests
+
+Execute tests and log defects.

package/studios/quality-assurance/stages/execute-tests/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/quality-assurance/stages/execute-tests/hats/reporter.md

@@ -0,0 +1,13 @@
+**Focus:** Log defects with complete reproduction information and maintain test execution metrics.
+
+**Responsibilities:**
+- Create defect reports with reproduction steps, environment details, and severity classification
+- Include root cause hypothesis where determinable
+- Track test execution progress and coverage metrics
+- Categorize defects for efficient triage and assignment
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** fil defects without reproduction steps or environment context
+- The agent **MUST NOT** misclassify defect severity based on personal judgment rather than defined criteria
+- The agent **MUST** track execution progress metrics during the test cycle
+- The agent **MUST NOT** fil duplicate defects without checking for existing reports

package/studios/quality-assurance/stages/execute-tests/hats/tester.md

@@ -0,0 +1,13 @@
+**Focus:** Execute test cases systematically, document results with evidence, and ensure test environment fidelity.
+
+**Responsibilities:**
+- Execute test cases according to the test suite spec and test strategy priorities
+- Verify the test environment matches production conditions before execution
+- Capture evidence (screenshots, logs, output) for each test result
+- Identify and document any blocked or unexecutable tests with reasons
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** execute tests in an environment that does not match production
+- The agent **MUST NOT** record pass/fail without capturing supporting evidence
+- The agent **MUST NOT** skip tests without documentation and approval
+- The agent **MUST** retest after environment issues are resolved

package/studios/quality-assurance/stages/execute-tests/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit build artifact for the execute-tests stage of quality-assurance. Units here are test-execution surface — discrete pieces of work with executable acceptance criteria. Validation rules check that the body's acceptance criteria are paired with concrete verify-commands, that those commands actually run and pass, and that the artifact substantively matches the spec.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Body matches the spec it claims to satisfy
+The unit body MUST substantively address every acceptance criterion declared in the unit's spec section. Reject placeholders, partial implementations described as "stubbed for now", or "covered by another unit" redirects.
+
+### 2. Acceptance criteria paired with verify-commands
+Every acceptance criterion in the body MUST be paired with a concrete shell command (or test invocation) that returns a clear pass/fail signal. Vague criteria ("works correctly", "tests pass") are a reject. Map verify-commands to the project's actual stack — read `package.json` / `pyproject.toml` / `Cargo.toml` / `go.mod` to know which test runner / coverage tool / linter the project uses.
+
+### 3. Verify-commands actually pass
+Run the named verify-commands. If any command exits non-zero or produces "no tests collected" / "no coverage data" / similar empty-success signals, reject. Cite the failing command and its exit code in the rejection reason.
+
+### 4. Decision-register consistency
+The unit must not introduce an approach contradicting a recorded Decision (e.g., a sync API when Decision N chose async). Cite the Decision ID.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted, OR flagged `(needs human escalation)`. Build-stage open questions block downstream consumers — be strict.

package/studios/quality-assurance/stages/execute-tests/outputs/TEST-RESULTS.md

@@ -0,0 +1,27 @@
+---
+name: test-results
+location: .haiku/intents/{intent-slug}/stages/execute-tests/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Test Results
+
+Test execution results with evidence, defect reports, and coverage metrics.
+
+## Content Guide
+
+- **Execution summary** -- pass/fail/skip counts with overall coverage percentage
+- **Test results** -- each test case with status and evidence (screenshots, logs for failures)
+- **Defect reports** -- each defect with reproduction steps, environment, severity, and root cause hypothesis
+- **Blocked tests** -- tests that could not be executed with reasons and impact assessment
+- **Coverage metrics** -- execution percentage against planned suite with gap justification
+- **Environment record** -- test environment configuration confirming production fidelity
+
+## Quality Signals
+
+- All planned tests are accounted for (pass, fail, skip, blocked)
+- Failures include evidence sufficient for defect reproduction
+- Defect reports have reproduction steps, severity, and environment details
+- Coverage metrics are accurate against the planned test suite

package/studios/quality-assurance/stages/execute-tests/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Execute Tests Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Test results document pass/fail status for every test case with evidence (screenshots, logs, or output) for each failure"
+- "Defect reports include reproduction steps, environment details, severity classification, and root cause hypothesis"
+- "Coverage report confirms execution percentage against the planned test suite with justification for any unexecuted tests"
+
+### Bad criteria — vague (no clear check)
+
+- "Tests are run"
+- "Defects are logged"
+- "Testing is complete"
+