requesting-code-review
Dispatches a code-reviewer subagent with crafted context to catch issues before they cascade.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for requesting-code-review, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A superpowers skill that spins up a reviewer subagent given precisely constructed context (never the session's full history) to evaluate the work product before merge. Security-relevant because it programmatically spawns a reviewing agent and controls exactly what code/context that agent sees.
Key features and capabilities
- Reviewer-subagent dispatch
- Curated review context
- Review-early-review-often cadence
Use cases
- Reviewing a major feature before merge
- Catching defects before they cascade