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 skills add ParaGenie/claude-codex-handoff --skill codex-handoffgit clone --depth 1 https://github.com/ParaGenie/claude-codex-handoffWrote 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/paragenie/claude-codex-handoff/codex-handoff)<a href="https://agentmods.dev/skills/paragenie/claude-codex-handoff/codex-handoff"><img src="https://agentmods.dev/badge/skills/paragenie/claude-codex-handoff/codex-handoff/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paragenie/claude-codex-handoff/codex-handoff"><img src="https://agentmods.dev/badge/skills/paragenie/claude-codex-handoff/codex-handoff.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00119 | $0.02872 |
| Opus 5 | $0.00060 | $0.01436 |
| Sonnet 5 | $0.00024 | $0.00574 |
| Haiku 4.5 | $0.00012 | $0.00287 |
Grade A, and why
codex-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 2d 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-handoff — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Handoff Workflow
Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session reviews the diff through the codex-plugin-cc plugin. Everything happens inside one Claude Code session.
Roles
| Role | Who | Does |
|---|---|---|
| Orchestrator | Claude main agent (you) | Probe code, write the spec, spawn subagents, record results, drive git, triage the review |
| Implementer | Claude subagent (general-purpose, host) |
Edit only the files in spec §2, write acceptance command lines into §9, no commit |
| Verifier | A second, fresh Claude subagent (host) | Run the §9 commands, report output tails |
| Reviewer | Codex via /codex:adversarial-review |
Judge diff + §9 evidence against the spec, write the report |
Two rules that hold everywhere
- The orchestrator never touches the codebase. No implementation edits, no build/test runs — not even a one-line fix. Edits go to the implementer subagent; verify runs go to a separate host subagent. The main agent keeps planning, judgment, the spec/review markdown, and git (branch + commit).
- Implementation and review are never the same model. Claude implements, Codex reviews. Two Claude subagents are one model. If Codex is unavailable (stall, usage limit), the task waits — there is no Claude-reviewer fallback, not "just this once".
/codex:rescueis not part of this loop; the only/codex:*commands used arereview,adversarial-review,status,result,cancel.
Why this split: the Codex sandbox cannot write to .git/ and does not mount .venv / node_modules, so it cannot run the project's build/test tools. That makes it a poor implementer but a fine cold reader of a diff. Its only source of acceptance truth is the §9 evidence recorded in Phase 2c — and keeping implementer and verifier separate means that evidence was not produced by the hands that wrote the code.
When to use
What ships with it
4 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.
- 2d ago Changed · -197 lines · -56 tokens per session f15657bf9b1b
- 8d ago First seen · 361 lines · 175 tokens per session scan A fa4884685bd3
codex-handoff is a skill published in the GitHub repository ParaGenie/claude-codex-handoff (1 stars, last pushed 2d ago), licensed MIT. It adds 119 tokens to every session and 2,872 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
codex-adversarial-review-lite
Codex Adversarial Review - Lite: user-invoked audit workflow for Claude Code users who want Codex CLI to independently review AI-generated code, plans, test expectations, and scope before fixes are applied. Cross-platform (Windows, macOS, Linux, WSL). Use only when the user explicitly invokes audit or selftest.
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
self-assessment
Interactive skill assessment with personalized learning path generation.