The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from project files and codebase research, creating a potential surface for instructions embedded in data to influence the agent.
Ingestion points: The skill reads and processes data from AGENTS.md, LEARNINGS.md, and various files discovered during targeted codebase research.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its core logic and the data ingested from external files.
Capability inventory: The skill possesses the ability to read from the codebase and write to specific documentation paths such as docs/task/ and TASKS.md.
Sanitization: No specific sanitization or validation of the content retrieved from external files is described before it is incorporated into documentation.
[NO_CODE]: The skill consists entirely of markdown-based instructions and does not include any external scripts, binaries, or code files for analysis.

task