The Agent Skills Directory

[SAFE]: The skill's primary function is to replace the standard plan mode with a narrative-driven task management system. All operations involve local project files and standard development tools.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute bon list and bon work. These commands are specific to the task management utility intended for use with this skill.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external, untrusted data to generate plans:
Ingestion points: The skill reads CLAUDE.md, .bon/understanding.md, and project source files (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard malicious instructions that might be embedded in the files it reads.
Capability inventory: The skill allows for shell command execution (Bash), file modification (Edit, Write), and the creation of sub-agents (Agent).
Sanitization: There is no mention of sanitizing or validating the contents of the project files before they are used to influence the agent's planning output.

plan