The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to conduct filesystem operations required for planning and project structure discovery. These include using find to identify deployment infrastructure (e.g., Dockerfiles, deploy scripts), mkdir to establish plan directories, and ls to audit existing planning documents to avoid duplication.
[INDIRECT_PROMPT_INJECTION]: The skill researches the local project environment, which involves ingesting data from files that could theoretically contain instructions intended to influence the agent's logic during the planning phase.
Ingestion points: Reads project-specific files such as package.json, pyproject.toml, Cargo.toml, CLAUDE.md, and docs/prd.md, as well as user-supplied task descriptions via $ARGUMENTS.
Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instructions" guards when reading external file content.
Capability inventory: The skill has access to tools for file modification (Write, Edit), shell command execution (Bash), and advanced code searching via MCP extensions (mcp__solograph__*).
Sanitization: There is no documented logic for sanitizing or escaping content retrieved from project files before it is processed by the agent to generate specifications.

solo-plan