# Review an agent-generated plan

Review agent-generated plans for intent, evidence, risk, and decision completeness.

Canonical: https://commentary.dev/docs/build/skills/review-agentic-plans


**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

Check out the published `v0.6.2` tag of the [Commentary Skills repository](https://github.com/commentary-dev/commentary-skills/tree/v0.6.2), 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

Copy this request into a compatible agent:

```text
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

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

Read the published v0.6.2 [SKILL.md](https://github.com/commentary-dev/commentary-skills/blob/v0.6.2/skills/review-agentic-plans/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](/docs/build/cli), [MCP](/docs/build/mcp), and [Developer access](/docs/build/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.