The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script recall.py via uv run to retrieve contextual information. This is a standard part of the skill's logic for knowledge retrieval.
[COMMAND_EXECUTION]: The agent is guided to run standard development commands like npm test and npm run build for plan verification.
[PROMPT_INJECTION]: The skill processes external files such as requirements and research docs, creating a surface for indirect prompt injection.
Ingestion points: Files in research/, plans/, .planning/, and general codebase files.
Boundary markers: The skill does not employ explicit delimiters or instructions to ignore embedded commands in ingested files.
Capability inventory: The agent can read files, write plans, and execute shell commands (uv run, npm).
Sanitization: No validation or sanitization of the ingested data is performed.

plan