The Agent Skills Directory

[SAFE]: The skill defines a planning framework using standard Markdown and does not contain any malicious code, obfuscation, or unauthorized access patterns.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation and reading of task planning files, which introduces a surface where the agent might ingest instructions from untrusted project files. However, this risk is mitigated by the skill's restricted toolset.
Ingestion points: Plan files located in the project root.
Boundary markers: None.
Capability inventory: Limited to Read, Glob, and Grep tools.
Sanitization: None.

plan-writing