The Agent Skills Directory

[SAFE]: The skill provides procedural instructions for incremental development cycles (implement, test, verify, commit). These guidelines are designed to improve code quality and maintainability without introducing security vulnerabilities.
[COMMAND_EXECUTION]: The skill mentions standard development commands such as npm test, npm run build, npx tsc --noEmit, and npm run lint. These are common developer tools used for local verification and do not constitute malicious command execution.
[PROMPT_INJECTION]: The instructions contain behavioral constraints (e.g., 'Touch only what the task requires', 'Do NOT clean up code adjacent to your change'). These are protective measures intended to limit the agent's impact on the codebase and do not attempt to bypass safety filters or override system instructions for malicious purposes.

incremental-implementation