The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local codebase to generate implementation plans, creating a surface for indirect instructions to influence the agent.
Ingestion points: Reads existing code and documentation using Explore Agent, Glob, and Grep tools as described in Step 1 of SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the codebase files it analyzes.
Capability inventory: The skill can write files to _/local-plans/, move files to configuration directories like .claude/ using mv, and remove directories using rmdir (SKILL.md).
Sanitization: No explicit validation or filtering of the content read from the codebase is specified before it is used to generate the plan files.
[COMMAND_EXECUTION]: The skill explicitly instructs the agent to use shell commands for file operations and environment management.
Evidence: Uses mv for relocating completed plans and rmdir for directory cleanup. It also specifies the use of ls to verify file creation in the Verification section of SKILL.md.

create-plan