Agent skill
policy-runner
Run policy-as-code checks (e.g., OPA/Conftest) based on the policy_plan. Use in Flow 2 and Flow 4.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/policy-runner-effortlessmetrics-demo-swarm
SKILL.md
Policy Runner Skill
You are a helper for running policy-as-code checks. If no policies are configured, report that no policy checks are wired for this change.
Behavior
-
If
policy_plan.mdexists, read it to discover which policies and paths to evaluate. -
For each configured policy entry:
- If an explicit command is listed (e.g.,
conftest test <path>oropa eval ...), run it. - Otherwise, if a policy file/rego path is provided, return a message that this policy is planned but not auto-executed.
- If an explicit command is listed (e.g.,
-
Output artifacts:
- Save raw runner output to
policy_runner_output.log. - Write
policy_runner_summary.mdsummarizing checks run, passed, failed, and planned-only policies.
- Save raw runner output to
-
Do not modify policy files or code.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?