Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/chentao326/vibe-code/codex-claude-handoffnpx skills add chentao326/vibe-code --skill codex-claude-handoffgit clone --depth 1 https://github.com/chentao326/vibe-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chentao326/vibe-code/codex-claude-handoff)<a href="https://agentmods.dev/skills/chentao326/vibe-code/codex-claude-handoff"><img src="https://agentmods.dev/badge/skills/chentao326/vibe-code/codex-claude-handoff.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00125 | $0.01032 |
| Opus 5 | $0.00063 | $0.00516 |
| Sonnet 5 | $0.00025 | $0.00206 |
| Haiku 4.5 | $0.00013 | $0.00103 |
Grade A, and why
codex-claude-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- codex-claude-handoff — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex + Claude Code Handoff
Overview
Enable Codex and Claude Code to collaborate on the same project through a 6-phase state machine. Signal files in handoff/ dictate which tool acts next. Codex handles Build and Polish phases; Claude Code handles Spec, Plan, and Review phases.
Workflow
Spec ──→ Plan ──→ Build ──→ Review ──→ Polish ──→ Commit
Claude Claude Codex Claude Codex 任一
Phase Detection
Always detect the current phase before acting. Run the detection script:
python3 <skill_dir>/scripts/check_phase.py
Or use --plain for phase name only. The script examines handoff/ signal files in order.
| Signal File | Phase | Actor |
|---|---|---|
| (none) | Init | Claude Code writes spec |
plan-ready.json |
Plan Ready | Codex builds |
build-done.json |
Build Done | Claude Code reviews |
review-fixes.json |
Fixes Needed | Codex fixes |
polish-done.json |
Polish Done | Claude Code re-reviews |
review-passed.json |
Ready | Either tool commits |
committed.json |
Done | Announce completion |
Full signal file schemas: references/protocol.md.
Role Rules
- You are Codex: Execute coding tasks, fix bugs, write tests. Do NOT design architecture or write specs.
- Claude Code: Design, plan, review. Do NOT write implementation code.
- If the current phase belongs to the other tool, stop and tell the user to switch.
Phase Instructions
Phase 1: Plan Ready (Codex acts)
- Read the spec from
specs/and task list fromhandoff/plan-ready.json - Execute tasks in dependency order
- After EACH task, update
plan-ready.json: set that task'sstatusto"completed" - After ALL tasks, write
handoff/build-done.json:
{
"stage": "build-done",
"timestamp": "<ISO 8601>",
"completed_tasks": [1, 2, ...],
"files_changed": ["file1.ts", "file2.ts"]
}
Phase 3: Fixes Needed (Codex acts)
- Read
handoff/review-notes.md - Fix all P0 issues first, then P1, optionally P2
- After each fix, append a
### Fix Appliedsection toreview-notes.md - Write
handoff/polish-done.json:
{
"stage": "polish-done",
"timestamp": "<ISO 8601>",
"fixes_applied": ["P0-xxx", "P1-xxx"]
}
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 103 lines · 125 tokens per session scan A f7cfe4f9644c
codex-claude-handoff is a skill published in the GitHub repository chentao326/vibe-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 1,032 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
test-repo
Use this skill to test strategy changes against a fresh test repository. Invoke when the user asks to "test against a test repo", "validate the changes", or wants to verify session hooks, commits, and checkpoint creation work correctly.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit
Commit current changes with a clear, descriptive message.