Agent skill
nw-mutation-test
Runs feature-scoped mutation testing to validate test suite quality. Use after implementation to verify tests catch real bugs (kill rate >= 80%).
Install this agent skill to your Project
npx add-skill https://github.com/nWave-ai/nWave/tree/main/nWave/skills/nw-mutation-test
SKILL.md
NW-MUTATION-TEST: Feature-Scoped Mutation Testing
Wave: QUALITY_GATE Agent: Crafter (nw-software-crafter)
Overview
Run mutation testing against implementation files from the current feature. Extracts targets from execution-log.json|generates feature-scoped configs|delegates to software-crafter. Uses cosmic-ray (Python)|PIT (Java)|Stryker (JS/TS/C#).
Context Files Required
docs/feature/{feature-id}/deliver/execution-log.json- Implementation file extractionscripts/mutation/generate_scoped_configs.py- Automated config generation (if available)
Pre-Invocation
Orchestrator performs before delegating:
- Extract files — Read
execution-log.json, extract implementation files fromcompleted_steps[].files_modified.implementation. Gate: file list non-empty. - Verify on disk — Check all extracted files exist on disk. Gate: zero missing files.
- Detect language — Scan config files (pyproject.toml, pom.xml, package.json, etc.) to select tool. Gate: language identified.
- Confirm tests pass — Run
pytest -x {test_scope}(or equivalent). Gate: exit code 0, no failures. - Ensure mutation venv — For Python, verify
.venv-mutation/exists with cosmic-ray installed. Gate:cosmic-ray --versionsucceeds.
Agent Invocation
@nw-software-crafter
Execute mutation testing for project {feature-id}.
Context to pass inline (agent has no Skill access):
- Project ID
- Implementation file list (from execution-log.json)
- Test scope path (e.g.,
tests/des/) - Kill rate threshold (default: 80%)
- Language and tool selection
Configuration:
- threshold: 80 (percentage, minimum kill rate)
- approach: feature-scoped (one config per component, scoped test commands)
- config_generator:
scripts/mutation/generate_scoped_configs.py(preferred over manual)
Output file: docs/feature/{feature-id}/deliver/mutation/mutation-report.md
Examples
Example 1: Python project with config generator
/nw-mutation-test des-hook-enforcement tests/des/
Reads execution-log.json, runs generate_scoped_configs.py des-hook-enforcement, delegates to software-crafter with per-component configs. Agent runs cosmic-ray, produces mutation-report.md.
Example 2: Python project without config generator
/nw-mutation-test auth-upgrade tests/auth/
Extracts files manually from execution-log.json, creates single cosmic-ray config with module-path = [file1, file2, ...] and test-command = "pytest -x tests/auth/", delegates to agent.
Example 3: Non-Python project
/nw-mutation-test payment-gateway tests/payment/
Detects package.json, selects Stryker, delegates with Stryker-specific instructions.
Success Criteria
- Implementation files extracted from execution-log.json
- All implementation files verified on disk
- Mutation testing executed without errors
- Per-file breakdown in mutation-report.md
- Kill rate meets threshold (>= 80% PASS, 70-80% WARN, < 70% FAIL)
- Source files restored to HEAD after mutation run (git checkout -- src/ tests/)
Post-Mutation Safety (mandatory)
After EVERY mutation run (success, failure, or interruption):
- Restore source files — Run
git checkout -- src/ tests/. Gate: working tree clean (no mutations remain). - Verify no corruption — Confirm test suite still passes after restore. Gate:
pytest -x {test_scope}exits 0.
Mutation tools apply mutations directly to source files. An interrupted run can leave corrupted code (e.g. is not None -> is None). Agent MUST execute these steps even if the run errors out.
Quality Gate
Kill rate thresholds:
- >= 80% PASS — Proceed to next wave.
- 70-80% WARN — Review surviving mutants, document findings, proceed with caution.
- < 70% FAIL — Add tests targeting surviving mutants before proceeding.
Skip conditions (each requires documented justification in mutation-report.md):
- No tool for language — No mutation framework available for detected language.
- Project opt-out —
.mutation-config.yamlhasskip: truewith justification. - Broken test suite — Pre-invocation step 4 fails; fix tests before mutation testing.
Note: Python projects require mutation testing. All skips need documented justification.
Next Wave
Handoff To: Phase 8 - Finalize (orchestrator continues develop.md workflow)
Deliverables: docs/feature/{feature-id}/deliver/mutation/mutation-report.md
Expected Outputs
docs/feature/{feature-id}/deliver/mutation/
mutation-report.md
cosmic-ray-*.toml (ephemeral)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
nw-research
Gathers knowledge from web and files, cross-references across multiple sources, and produces cited research documents. Use when investigating technologies, patterns, or decisions that need evidence backing.
nw-distill
Acceptance test creation methodology for the DISTILL wave. Domain knowledge for the acceptance designer agent: port-to-port principle, prior wave reading, wave-decision reconciliation, graceful degradation, and document back-propagation.
nw-review-output-format
YAML output format and approval criteria for platform design reviews. Load when generating review feedback.
nw-ddd-tactical
Tactical DDD — aggregate design rules, entities, value objects, domain events, repositories, domain services, and anti-pattern detection
nw-infrastructure-and-observability
Infrastructure as Code patterns (Terraform, Kubernetes), observability design (SLOs, metrics, alerting, dashboards), and pipeline security stages. Load when designing infrastructure, observability, or security scanning.
nw-par-critique-dimensions
Platform design review critique dimensions and severity levels. Load when reviewing CI/CD pipelines, infrastructure, deployment strategies, observability, or security designs.
Didn't find tool you were looking for?