The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the Bash tool as part of its core logic. It instructs the agent to define "Concrete Steps" and "Validation and Acceptance" commands within its plan files and subsequently execute them to verify milestones.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to read and follow natural language instructions and milestones stored in external files.
Ingestion points: docs/exec-plans/active/*.md and docs/PLANS.md (via Read/Glob/Grep tools).
Boundary markers: Absent; the agent is directed to follow the narrative and steps within the plan without explicit delimiters to ignore embedded instructions.
Capability inventory: The skill has access to Bash, Write, Edit, Read, Glob, and Grep tools, allowing for file modification and command execution based on the plan content.
Sanitization: Absent; the skill does not specify any sanitization or validation of the content within the plan files before processing.

exec-plan