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.
AIVSS 8.7 · High
View MAESTRO 7-layer threat model →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
- 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