Cskwork Llm Review
- Updated January 17, 2026
- cskwork/llm-review
cskwork-llm-review is a Claude Code plugin that orchestrates Claude as planner-coder and Codex as a sequential code reviewer.
About
cskwork-llm-review is a Claude Code plugin from cskwork/llm-review that encodes a two-role AI pipeline: Claude handles planning and implementation while Codex focuses on review. For developers shipping fast with agents, the pain is often shallow self-review—same model approves its own diffs. This plugin targets that gap by making review an explicit downstream step in a sequential workflow, aligned with keywords like multiai, orchestration, pipeline, and code-review. It suits small SaaS, CLI, or agent projects where you already use Claude Code daily and can afford a second model pass before merge or release. It is not a replacement for human review, security scanners, or CI—you still own tests and policy. Complexity is intermediate because you must wire both Claude and Codex-capable tooling and understand when to invoke each phase. Register it when you want disciplined critique without building a custom orchestration script from scratch.
- Single-plugin bundle orchestrating Claude (planner + coder) with Codex as reviewer
- Keywords emphasize multi-ai pipeline, sequential workflow, and code-review
- Designed for Sonnet-era Claude workflows paired with Codex review passes
- Development-category listing focused on review orchestration, not deployment
- Fits indie builders who want model specialization instead of one model doing everything
Cskwork Llm Review by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin install cskwork-llm-review@cskwork/llm-reviewAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| Last updated | January 17, 2026 |
|---|---|
| Repository | cskwork/llm-review ↗ |
What it does
Run a sequential multi-model pipeline where Claude plans and implements code and Codex acts as a dedicated reviewer inside Claude Code.
Who is it for?
Best when you already use Claude Code for implementation and want a structured Codex review pass without custom glue code.
Skip if: Skip if you need enterprise PR tooling only, security-only audits, or a single-model workflow with no Codex access.
What you get
After install, you can run a defined multi-AI review pipeline so implementation and critique are separated before you ship or open a PR.
- Structured planner-plus-coder session followed by a Codex review pass
- Review-oriented workflow aligned with ship-phase quality checks
- Reduced same-model self-approval risk before merge
By the numbers
- Plugin bundle count: 1
- Source repository: cskwork/llm-review
- Catalog category: development
Recommended Plugins
0pg Cc MarketplacePersonal Claude Code plugins collection
1shot Labs Squadron Comms PluginVoice communication system with ElevenLabs TTS for multi-agent coordination in Claude Code3
23blocks Os Ai MaestroAI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging.733
3commas Io Commas ClaudeThis is a repo with shared agents and skills used company-wide4
884js Agent Plugins1 plugin
A5c Ai BabysitterBabysitter enforces obedience to agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration1.6kHow it compares
Multi-AI review orchestration plugin, not a standalone linter skill or MCP server.
FAQ
Who is Cskwork Llm Review for?
It is for developers and small teams using Claude Code who want Claude to plan and code while Codex provides a separate review step.
When should I use Cskwork Llm Review?
Use it in the ship phase after a feature branch is ready—invoke the workflow before merge, release tags, or handoff to production deploy.
How do I add Cskwork Llm Review to my agent?
Add the cskwork/llm-review plugin from the catalog in Claude Code, ensure Codex reviewer access is configured per your environment, then follow the plugin’s sequential planner-coder-reviewer flow.