subagent-driven-development
Executes a plan by spawning a fresh implementer subagent per task plus per-task and final reviews.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for subagent-driven-development, 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 runs an implementation plan by dispatching a new isolated-context implementer subagent for each task, a spec+quality review after each, and a broad whole-branch review at the end. Carries agent-spawning and code-mutation surface across many delegated tasks.
Key features and capabilities
- Fresh subagent per task
- Per-task spec + quality review
- Whole-branch final review
Use cases
- Executing a multi-task plan in one session
- High-quality fast iteration on independent tasks