quick-critique

Critique final_plan.md files with Codex CLI and write critique reports.

1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Honigbart/honeyflow --skill quick-critique
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quick-critique
Source: https://github.com/Honigbart/honeyflow/tree/main/quick-critique
Command: npx skills add https://github.com/Honigbart/honeyflow --skill quick-critique

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a skeptical external critique of an active plan's final_plan.md using Codex CLI to verify readiness for execution and surface gaps before shipping.

Core Features & Use Cases

  • Generates codex_critique.md by running Codex CLI against the plan's final_plan.md.
  • Creates an optional ollama_critique.md when a local Ollama reviewer is available.
  • Supports --apply to critique and immediately re-plan, updating the final_plan.md for the same slug.
  • Operates on namespaced plan directories under .ai/plans/<slug>/ and leaves execution state untouched.

Quick Start

Run quick-critique on a target plan slug to generate a Codex critique and optionally apply it to update the final plan.

Frequently Asked Questions about quick-critique

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a critique of my final_plan.md before execution?▼

You can automate a plan critique by running Codex CLI against your active plan's final_plan.md. This generates a codex_critique.md file to validate execution readiness and surface any gaps before you ship.

Can I use a local Ollama reviewer for plan validation?▼

Yes, when a local Ollama reviewer is available, the critique workflow generates an additional ollama_critique.md file alongside the Codex critique to provide a second perspective on your plan.

How do I apply critique feedback to update an existing plan?▼

You can apply critique feedback by using the --apply option. This re-runs the planning workflow and updates the final_plan.md for the same slug while preserving the existing execution state.

Does the critique process modify the execution state of my active plan?▼

No, the critique process operates on namespaced plan directories under .ai/plans/<slug>/ and leaves the execution state completely untouched while documenting feedback for decision making.

What is the best way to validate execution readiness for a planning workflow?▼

The best way to validate readiness is through skeptical external critique using Codex CLI. This approach reviews your final_plan.md to identify gaps and writes structured critique files for decision making.

Do I need a specific directory structure to run an automated plan review?▼

Yes, automated plan review requires an active plan with a final_plan.md located under the .ai/plans/<slug>/ directory structure to generate and store the resulting critique files.