The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) commands to analyze the repository state. These are standard operations for a development utility and are limited to local repository inspection (e.g., git log, git blame, git diff).- [INDIRECT_PROMPT_INJECTION]: The skill processes data that could be controlled by an external actor, such as commit messages, file contents, and diff outputs, which could contain malicious instructions designed to influence the agent.
Ingestion points: The skill reads output from git diff, git log, git blame, and gh pr view.
Boundary markers: The instructions do not specify the use of delimiters or markers to isolate ingested git data from the agent's core instructions.
Capability inventory: The skill identifies changes and plans git commands, including staging and fixup commits.
Sanitization: The skill mitigates risks by explicitly forbidding the agent from executing commits, tags, or rebases itself, ensuring all planned commands must be reviewed and run manually by the user.

fixup-plan