The Agent Skills Directory

[SAFE]: The skill follows a well-defined orchestration pattern with explicit safety checkpoints and mandatory user approval steps before finalizing any work plan.
[SAFE]: Sub-agent interactions are hardened by the fork_turns="none" rule, which limits the context provided to spawned agents to only the immediate task, reducing the risk of unintended instruction propagation.
[SAFE]: No suspicious patterns were detected regarding network access, credential handling, or arbitrary command execution.
[SAFE]: The skill's primary function involves processing documents within the docs/design/ and docs/plans/ directories, which is consistent with its stated purpose of project planning.

recipe-plan