The Agent Skills Directory

[SAFE]: The skill operates as a passive scanner, identifying project configuration files and documentation signals to help agents assess repository structure. All included shell scripts ('scan_agent_instructions.sh', 'scan_build_env.sh', 'scan_feedback_loops.sh', 'scan_policy.sh', 'scan_workflows.sh') follow a safe pattern of locating files without modifying system state or exfiltrating data.- [COMMAND_EXECUTION]: The skill utilizes standard shell commands ('bash', 'find', 'grep', 'wc', 'ls') to inspect the filesystem. These operations are scoped to the target repository directory and do not involve privilege escalation or dangerous execution of external content.- [EXTERNAL_DOWNLOADS]: The skill does not download external scripts or packages. It references standard configuration files for well-known services (e.g., Vercel, Netlify, GitHub Actions) but does not fetch remote payloads.- [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were detected. The scripts only report the presence of files or counts of specific patterns (like build commands or secret references in CI configuration) within the user-provided repository path.

agent-readiness-report