domains / families / agent-tooling / agent-watchdog

agent-watchdog

separate

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same problem to form your own hypotheses and approach, inspect what the agent actually changed and verified, compare the two investigations, report gaps and add-on directions, and optionally make scoped fixes when the user authorizes repair.

When to use

• watch another agent's work
• babysit another agent's work
• audit another agent's work
• review another agent's work
• compare another agent's work
• fix another agent's work
• monitor session until done or blocked
• reconstruct user request

When not to use

• broad rewrites
• branch movement
• speculative changes

Skill page

Source