The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute filesystem operations such as find and grep to identify files that lack spec loader implementation.
[COMMAND_EXECUTION]: In the verification phase (prompts/04-verify.md), the skill executes npm run typecheck and npm test. These commands run project-specific scripts which involve the execution of local code defined in the repository's configuration.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and processes source code from the local environment. Maliciously crafted code or comments within the scanned files could attempt to influence the agent's behavior during the refactoring process.
Ingestion points: Source files in app/routes/ and tests/ are read and analyzed via Grep and Read tools.
Boundary markers: The skill instructions do not define specific delimiters or instructions to ignore or isolate content within the ingested files.
Capability inventory: The agent has access to powerful tools including Bash, Write, and Edit for filesystem and command execution.
Sanitization: There is no explicit logic to sanitize or validate strings extracted from the source code before they are processed in refactoring templates.

ssot-refactor