The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content (source code, documentation, agent notes) which acts as an attack surface for indirect prompt injection.
Ingestion points: The agent is instructed to read AGENTS.md, architecture documentation, and various production and non-production files across the repository.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the processed content.
Capability inventory: The skill utilizes tools like rg and knip, executes pnpm scripts, and writes new documentation files to the .agents/notes/ directory.
Sanitization: There is no requirement to sanitize or escape data before it is included in the generated notes.
[COMMAND_EXECUTION]: The skill guides the agent to execute several shell commands, including rg (ripgrep), knip (dead code analysis), git diff, and repository-specific scripts such as pnpm run lint and pnpm run doc-sync.

find-simplifications