The Agent Skills Directory

[SAFE]: The skill performs static analysis of public-facing project configuration files such as package.json, Cargo.toml, and go.mod. It does not attempt to access sensitive files like credentials, environment variables, or SSH keys.
[SAFE]: The primary function is to write a summary file (.agents/stack-context.md) to the local project directory. It does not perform unauthorized network requests or exfiltrate data.
[SAFE]: No remote code execution patterns, obfuscation, or privilege escalation attempts were detected. The use of MCP tools and web search is restricted to fetching library documentation based on the detected stack.

detect-stack