The Agent Skills Directory

[SAFE]: No security issues detected. The skill uses standard agentic patterns for codebase research, plan generation, and file management.
[COMMAND_EXECUTION]: The skill uses Bash and Grep for legitimate codebase research (mapping files, scanning interfaces, and identifying test patterns) as part of its primary functionality.
[EXTERNAL_DOWNLOADS]: The skill refers to code-review-graph and other internal agents for research; no untrusted external downloads or remote code executions were identified.
[PROMPT_INJECTION]: Instructions include standard agentic role-play ('You are the plan orchestrator') and process guards, but no malicious bypass or override patterns were found.
[DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations were detected. File operations are restricted to project-local paths such as .fullstack-dev/config.json, docs/specs/, and docs/plans/.

plan