The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill invokes npx vigiles during its verification step. This command downloads and executes the 'vigiles' package from the npm registry. This behavior is consistent with the skill's stated purpose of validating rule formats and follows common development practices for linting.
[COMMAND_EXECUTION]: The skill executes shell commands using npx to perform file validation. This execution is limited to a specific validator tool and is used to confirm that the documentation rules are properly formatted.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of untrusted markdown files (CLAUDE.md, .cursorrules, etc.) found in the repository.
Ingestion points: Reads content from CLAUDE.md, AGENTS.md, .cursorrules, and other user-configured markdown files across the repository.
Boundary markers: None. The skill parses raw markdown headers and text without explicit delimiters to isolate untrusted content from the agent's instructions.
Capability inventory: The skill has the ability to execute shell commands (npx) and write changes to files in the repository.
Sanitization: No content sanitization or validation of the input markdown text is performed beyond checking for header patterns.

enforce-rules-format