Updated today
by lploc94
cross-review
Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.
153 GitHub stars (153)
- 7 skills (7 skills found in its SKILL.md files)
- 23 forks (23 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add lploc94/cross-review
Asks which skills and agents to install. Just one: npx skills add lploc94/cross-review --skill loop-implement — add -g for every project.
Claude Code
git clone https://github.com/lploc94/cross-reviewcp -r "cross-review/skill-packs/cross-review/skills/loop-implement" ~/.claude/skills/
Copies the loop-implement skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add lploc94/cross-review
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
loop-implement
Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only when an approved plan exists.
skill-packs/cross-review/skills/loop-implement/SKILL.md on GitHub (opens in a new tab) -
loop-plan
Create an execution-ready, code-grounded phased implementation plan before coding. Only for large work - several features, many files or components, or work spanning sessions that needs resumable phase boundaries. Not for small fixes or single-feature changes; do those directly.
skill-packs/cross-review/skills/loop-plan/SKILL.md on GitHub (opens in a new tab) -
review-commit
Peer debate with an external reviewer model (Codex CLI by default) on committed code quality. Report + suggest only, no modifications.
skill-packs/cross-review/skills/review-commit/SKILL.md on GitHub (opens in a new tab) -
review-impl
Review uncommitted code changes or branch diff against the plan/target with an external reviewer model (Codex CLI by default) — verify correctness, catch unacceptable deviations and bugs (logic/security/memory/runtime). No new features or over-engineering beyond the plan. You apply valid fixes, rebut invalid points, and iterate until consensus or stalemate.
skill-packs/cross-review/skills/review-impl/SKILL.md on GitHub (opens in a new tab) -
review-plan
Review/debate plans before implementation with an external reviewer model (Codex CLI by default). Can run in plan mode — debates the plan and edits the plan file to fix accepted issues.
skill-packs/cross-review/skills/review-plan/SKILL.md on GitHub (opens in a new tab) -
review-pr
Peer debate with an external reviewer model (Codex CLI by default) on PR quality and merge readiness. No code modifications.
skill-packs/cross-review/skills/review-pr/SKILL.md on GitHub (opens in a new tab) -
review-think
Peer debate with an external reviewer model (Codex CLI by default) on any technical question. Both think independently, challenge each other, converge to consensus or explicit disagreement.
skill-packs/cross-review/skills/review-think/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.