The Agent Skills Directory

[SAFE]: The skill defines a procedural workflow for creating implementation plans from existing project artifacts (PRDs, SDDs, ADRs). It does not request any sensitive permissions or external network access.
[SAFE]: The instructions include robust safety and quality gates, such as requiring human confirmation for external mutations and explicitly stopping for approval via the /gadd:approve command before proceeding to further stages.
[SAFE]: Metadata in SKILL.md and policy definitions in agents/openai.yaml are consistent with the stated purpose of the skill. No obfuscation, persistence mechanisms, or privilege escalation attempts were detected.

gadd-plan