Is the Claude-Codex Collaboration skill free?

Yes. The skill itself is free from trietdeptrai/Byterover-Claude-Codex-Collaboration-. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude-Codex Collaboration SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Claude-Codex Collaboration?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Claude-Codex Collaboration with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Claude-Codex Collaboration

Auto-loops Codex to review Claude's plans and code via Byterover shared memory

by trietdeptrai · trietdeptrai/Byterover-Claude-Codex-Collaboration-

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 1d49fff

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

The whole loop hinges on the Byterover MCP being configured in both Claude and Codex, and that is an account-gated external service that was not available on the test machine, so the actual review-quality delta over a single agent could not be measured. Codex CLI was present but without the shared-memory layer the plan store and retrieve steps cannot run end to end. Install copies cleanly, though SKILL.md points to 'scripts/collaborate.sh' while the helper actually sits at the repo root. Honest fit is a capable multi-agent harness that needs real setup before it does anything.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Claude-Codex Collaboration does

Orchestrates an automated code-review handoff where Claude Code drafts an architectural plan, stores it in Byterover, then invokes the Codex CLI via Bash to critique it before implementation. Triggers when a user wants a second AI to review or validate a design or implementation. Both agents share context through the Byterover MCP memory layer.

How to install Claude-Codex Collaboration

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Claude-Codex Collaboration

/claude-codex-collaboration Auto-loops Codex to review Claude's plans and code via Byterover shared memory

It also activates on plain-language prompts like these:

Have Codex review my architecture plan before I build it
Get a second AI to validate this implementation design
Peer-review this feature design with Codex before coding

Frequently asked questions

Is the Claude-Codex Collaboration skill free?: Yes. The skill itself is free from trietdeptrai/Byterover-Claude-Codex-Collaboration-. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude-Codex Collaboration work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Works with setup. The whole loop hinges on the Byterover MCP being configured in both Claude and Codex, and that is an account-gated external service that was not available on the test machine, so the actual review-quality delta over a single agent could not be measured. Codex CLI was present but without the shared-memory layer the plan store and retrieve steps cannot run end to end. Install copies cleanly, though SKILL.md points to 'scripts/collaborate.sh' while the helper actually sits at the repo root. Honest fit is a capable multi-agent harness that needs real setup before it does anything.
What is the Claude-Codex Collaboration SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Claude-Codex Collaboration?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Claude-Codex Collaboration with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.