The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/lint_runner.py uses the Python subprocess module to run linter commands. While it uses shell=True on Windows systems to handle command resolution (a common practice for developer tools), the commands themselves are restricted to hardcoded, expected values like npm, npx, ruff, and mypy based on project metadata.
[COMMAND_EXECUTION]: The script scripts/type_coverage.py performs a search for a project-local TypeScript compiler binary (node_modules/.bin/tsc) and executes it to generate type-safety reports. This follows standard behavior for JavaScript development environments.
[SAFE]: The skill promotes secure coding practices by including instructions for running security-focused tools such as npm audit and bandit during the development loop.
[SAFE]: No evidence of data exfiltration, obfuscation, persistence, or prompt injection was found during the analysis of the instructions or the supporting Python scripts.

lint-and-validate