The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local maintenance scripts (scripts/setup-worktree.sh, scripts/merge-worktrees.sh) and standard git operations. These commands are necessary for the skill's stated purpose of parallelizing implementation tasks.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it ingests untrusted data from the repository and local files like issues.md. Ingestion points: Reads issues.md, progress.md, and codebase files. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided markdown. Capability inventory: Uses Bash, Write, Edit, and SendMessage to manipulate the workspace. Sanitization: There is no evidence of sanitization or filtering for the data read from the files. However, this is considered a low risk inherent to implementation-focused agent skills.

agent-implement