The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes system tools to manage processes and network connections.
Executes lsof (Unix) and Get-NetTCPConnection (Windows) to scan for active port listeners.
Executes kill and Stop-Process to terminate existing development server processes.
Spawns development servers using framework-specific CLI commands (e.g., npm run dev, flask run, dotnet run).
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from project configuration files which can influence the parameters of executed shell commands.
Ingestion points: Reads local files including package.json, pnpm-workspace.yaml, vite.config.js, next.config.js, and other framework-specific manifests found in SKILL.md Step 3.
Boundary markers: Instructions do not define specific delimiters or "ignore" instructions for the content read from these files.
Capability inventory: The skill has access to the Bash tool, allowing it to execute arbitrary shell commands.
Sanitization: There is no explicit requirement to sanitize or validate strings (such as script names or port numbers) parsed from configuration files before they are interpolated into shell commands.

managing-ports