The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Node.js script located at ~/.claude/get-shit-done/bin/gsd-tools.cjs to initialize and track workflow progress. This is the core functionality of the orchestrator.
[PROMPT_INJECTION]: Surface for indirect prompt injection via untrusted user data. 1. Ingestion points: User-provided task descriptions, PRD documents (via --auto @doc.md), and architecture opinions processed in SKILL.md. 2. Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or ignore instructions within the ingested data. 3. Capability inventory: The skill utilizes node for command execution and performs extensive file system operations (read/write) for project management. 4. Sanitization: No explicit sanitization or validation of the user-provided content is performed before it is passed to subagents or tool arguments.

gsd-orchestrator