agent-plan-act-reflect
Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, checkpoint, stop, or human escalation.
SKILL.mdskills/agent-plan-act-reflect/SKILL.md
GitHubagent-plan-act-reflect (deprecated)
Deprecated in 0.6.0 and removed in 0.7.0.
- Iterating with the user present (edit, run the check, fix, repeat) needs no skill. Keep the acceptance check runnable and report its real result.
- An unattended multi-cycle loop under a configured
agent-collabpolicy follows harness-loop.md, the former body of this skill. It still runsagent-collab policy evaluateafter every cycle and before every spawn. - Comparing two consequential alternatives is agent-debate, not a loop.
See migration 0.6.