The Agent Skills Directory

[SAFE]: The skill implements a structured technical planning workflow. It processes local project documentation and source code to generate task lists, which is its primary intended function.
[DATA_EXPOSURE]: While the skill reads project files (code and specifications), it does so within the local context to create plans. There are no instructions or capabilities for transmitting this data to external or untrusted domains.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from docs/<feature-slug>/spec.md and project source code.
Ingestion points: Files located at docs/<feature-slug>/spec.md and general project code.
Boundary markers: None specified in the instructions.
Capability inventory: File system write access to docs/<feature-slug>/plan.md.
Sanitization: No explicit sanitization or filtering of input content is defined. However, the risk is negligible as the output is restricted to planning documentation and the skill operates on local project resources.

plan