Loading...
Loading...
Review code with validated evidence. Use for normal, security, performance, or deep audits of diffs, architecture, data, tests, dependencies, docs, and code health.
npx skill4agent add time-attack/gstack reviewTarget: <concrete repository, product, URL, device, PR, or artifact>
Mode: <selected top-level mode>
Depth: <readiness, standard, or deep>
Mutation: <report-only or exact authorized mutation boundary>
Active modules: <comma-separated internal specialist modules>
Skipped modules: <comma-separated non-active mandatory modules with compact reasons>
Web context: <none, optional, local-browser, or production>references/EXECUTION-PROFILES.mdreferences/SHARED-JUDGMENT.mdreferences/AUTHORITY-POLICY.mdreferences/QUESTION-FORMAT.mdreferences/RUNTIME.mdreferences/WEB-CONTEXT.mdreferences/CODE-INTELLIGENCE.mdreferences/THIRD-PARTY-ACTIONS.mdreferences/ASSETS.mdreferences/COMPATIBILITY.md| Mode | Target | Infer when | Candidate internal specialists |
|---|---|---|---|
| A current branch diff | A standard pre-landing or broad code review is requested. | |
| The repository threat surface | The primary risk is auth, secrets, supply chain, abuse, infrastructure, or threat modeling. | |
| Changed performance behavior | The review should concentrate on latency, memory, resource use, hot paths, or regressions. | |
| A high-risk or cross-cutting change | The change warrants health evidence and every genuinely independent outside voice available. | |
| Legacy invocation | Legacy alias | Public mode | Role | Module |
|---|---|---|---|---|
| | | mandatory | |
| | | mandatory | |
| | | mandatory | |
| | | mandatory | |
| | | mandatory | |