loop-implement
Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only…
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.
Claude Code
$ npx -y skills add lploc94/cross-review --skill review-plan --agent claude-code
Codex
$ npx skills add lploc94/cross-review --skill review-plan -a codex -y
Cursor
$ npx skills add lploc94/cross-review --skill review-plan -a cursor -y
Gemini CLI
$ npx skills add lploc94/cross-review --skill review-plan -a gemini-cli -y
GitHub Copilot
$ npx skills add lploc94/cross-review --skill review-plan -a github-copilot -y
OpenCode
$ npx skills add lploc94/cross-review --skill review-plan -a opencode -y
Windsurf
$ npx skills add lploc94/cross-review --skill review-plan -a windsurf -y
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.
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.
After creating a plan, before implementing code. Requires a Markdown plan file with headings.
{{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.
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.
Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.
Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only…
Create an execution-ready, code-grounded phased implementation plan before coding. Only for large work - several features, many…
Review uncommitted changes, unpushed or recent commits, or a branch diff against the plan/target with an external reviewer model…
Review someone else's pull request or branch with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on…
Peer debate with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request) on any technical…
Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to…
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review…
Build or update the code review knowledge graph. Run this first to initialise, or let hooks keep it updated automatically.
Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked…