The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as its primary function involves reading external, potentially untrusted documentation to generate new instructions for AI agents.
Ingestion points: The skill reads proposal.md, design.md, and all files matching specs/**/*.md as described in Step 1.
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded prompts within the ingested artifact files.
Capability inventory: The skill has the capability to write multiple markdown files to the tasks/ directory and update the tasks.md index. It also directs the agent to research the codebase, which involves filesystem read capabilities.
Sanitization: The skill does not provide mechanisms for sanitizing or escaping content from source files before interpolating it into the generated task files.
[NO_CODE]: The skill consists entirely of instructional markdown and does not include any executable scripts, binaries, or configuration files.

plan-tasks