The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python's subprocess.run to interact with the local Git repository (e.g., git status, git diff, git rev-parse). The implementation follows security best practices by passing arguments as a list rather than a shell string, effectively mitigating command injection risks.
[EXTERNAL_DOWNLOADS]: The skill includes a serve command that launches a local HTTP server using the built-in http.server module. This server is bound to the loopback address (127.0.0.1) and is used solely to render the provided dashboard.html using local plan data. It does not perform external network requests.
[SAFE]: Systematic analysis of all script files, including the core runtime and the dashboard asset, revealed no evidence of obfuscation, hardcoded credentials, or unauthorized data exfiltration. The skill's behavior is consistent with its stated purpose of tracking development plans in Git.

track-ai-plans