Skip to content
Code Review
Skill

/review-plan

Review/debate plans before implementation with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request). Can run in plan mode — debates the plan and edits the plan file to fix accepted issues.

From plugin
cross-review
1686 skills

Claude Code

$ npx -y skills add lploc94/cross-review --skill review-plan --agent claude-code

SKILL.md

review-plan.SKILL.md
name: review-plan
description: Review/debate plans before implementation with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request). Can run in plan mode — debates the plan and edits the plan file to fix accepted issues.

Plan Review

Purpose

Adversarially review a plan before implementation to **maximize its chance of achieving the stated target**: achievability, technology or capability claims that do not hold, logic and design flaws, missing steps, and places where the plan patches around a problem that an established standard solves better. Additions are proposed only when the target needs them.

When to Use

After creating a plan, before implementing code. Requires a Markdown plan file with headings.

Inputs

  • **Plan path**: the user's (it may be outside the repository, such as a client's plan-mode file), else a single `*-plan.md` in the repo (`ls *plan*.md`, `find ./docs -maxdepth 3 -name "*plan*.md"`). Ask if several or none.
  • Round 1 placeholders: `PLAN_PATH` (absolute), `USER_REQUEST` (original request plus the user's latest decisions), `SESSION_CONTEXT` (only what the reviewer cannot read in the plan or the repository: decisions and constraints from the conversation; where real samples live when the work parses, limits or guards input).
  • Reply placeholders: `PLAN_PATH`, `SESSION_CONTEXT`, `FIXED_ITEMS`, `DISPUTED_ITEMS`.
  • Skill `review-plan`, no mode.

{{PROTOCOL_CORE}}

{{PROTOCOL_VARIANT}}

For this skill, ACCEPT means editing the plan file so it reaches the user's existing target. A change of target, scope, acceptance criteria or architecture direction is a USER DECISION. A standards-based restructuring the plan proposes is not over-engineering when it has evidence (source, spike, breaking scope, migration cost); judge the evidence, and treat "too big a redesign" alone as no reason to reject it.

Completion

APPROVE: if the plan has a `Plan Review` section (loop-plan), set it to `APPROVE (review-plan <session id>, <date>)`; do not add one to other plans. Stalemate: present the deadlocked issues and ask the user. Report rounds, verdict, issues found/fixed/disputed, user decisions, plan edits, and remaining risks.

Rules

  • In plan mode, stay in plan mode; the debate takes priority.
  • Do not implement code. Never claim approval without `VERDICT: APPROVE` from the reviewer or an explicit user approval.
  • Never hide a review-originated expansion inside a fix, test step, assumption, or rebuttal.
Read more
@lploc94
Ships withcross-review

Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.

Stars on GitHub

Momentum

stars in total
168
Star history of lploc94/cross-review on GitHub, a chart by star-history.com

Other skills on cross-review.

loop-implement

loop-implement

Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only…

loop-plan

loop-plan

Create an execution-ready, code-grounded phased implementation plan before coding. Only for large work - several features, many…

review-impl

review-impl

Review uncommitted changes, unpushed or recent commits, or a branch diff against the plan/target with an external reviewer model…

review-pr

review-pr

Review someone else's pull request or branch with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on…

review-think

review-think

Peer debate with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request) on any technical…

More skills from other plugins.

open-code-review

open-code-review

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to…

@alibaba@alibabaInstall Skill
build-graph

build-graph

Build or update the code review knowledge graph. Run this first to initialise, or let hooks keep it updated automatically.

@tirth8205@tirth8205Install Skill
hunk-extensions

hunk-extensions

Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked…

hunk6d9.8k
@modem-dev@modem-devInstall Skill

Questions about review-plan.

Which coding agents can use review-plan?
review-plan installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.