Review an agent-generated plan
Purpose: Review agent-generated plans for intent, evidence, risk, and decision completeness.
Use it when: Use before execution when a plan was generated by an agent and needs critique.
Install
Section titled “Install”Check out the published v0.6.2 tag of the Commentary Skills repository, then copy the complete skills/review-agentic-plans/ folder into the skills directory for your compatible SKILL.md agent. Preserve references and metadata. Restart or refresh the harness if it loads skills at startup.
Invoke
Section titled “Invoke”Copy this request into a compatible agent:
Use `review-agentic-plans` to critique this migration plan for intent, evidence, rollback risk, and missing human decisions. Return prioritized findings and do not execute it.Expected result: The agent returns a grounded plan review with evidence gaps and decision points, without inventing facts or taking action.
Workflow
Section titled “Workflow”Restate intended outcome, inspect evidence and assumptions, identify failure modes and irreversible actions, and return prioritized questions or decision points grounded in the supplied plan.
Environment and limits
Section titled “Environment and limits”Read the published v0.6.2 SKILL.md and its referenced files for the exact transport, scopes, target, and environment settings; those instructions are authoritative for this skill. For transport setup, see CLI, MCP, and Developer access. Never store credentials in the skill folder or send them to a renderer. Do not invent evidence or silently execute the plan. Preserve human decision points.