The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands including 'rm -rf' for deleting tracks, 'mv' for archiving and renaming, and 'git' for committing changes. These operations are constrained to the 'conductor/' directory.
[PROMPT_INJECTION]: The skill processes local project files which creates a surface for indirect prompt injection. * Ingestion points: The agent reads 'conductor/tracks.md', 'metadata.json', and 'plan.md' from the project directory. * Boundary markers: No explicit markers are used to distinguish data from instructions within these files. * Capability inventory: The skill can perform file deletions ('rm -rf'), move directories ('mv'), and execute git commands. * Sanitization: The instructions do not mention validating or sanitizing the content of the ingested files.

conductor-manage