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 Amal-David/claude-to-codex --skill handoffgit clone --depth 1 https://github.com/Amal-David/claude-to-codexWrote 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/amal-david/claude-to-codex/handoff)<a href="https://agentmods.dev/skills/amal-david/claude-to-codex/handoff"><img src="https://agentmods.dev/badge/skills/amal-david/claude-to-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/amal-david/claude-to-codex/handoff"><img src="https://agentmods.dev/badge/skills/amal-david/claude-to-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 | $0.00059 | $0.00452 |
| Opus 5 | $0.00030 | $0.00226 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Handoff
Run the bundled launcher immediately. Do not manually summarize or paste the transcript into Codex.
For a Skills CLI installation, locate scripts/claude-to-codex.mjs beside this SKILL.md and run:
node <skill-directory>/scripts/claude-to-codex.mjs --session "${CLAUDE_SESSION_ID}"
Common skill directories are:
$HOME/.claude/skills/handoff<project>/.claude/skills/handoff$HOME/.agents/skills/handoff
Require a non-empty CLAUDE_SESSION_ID; do not silently choose the newest transcript. The launcher writes a
private package under ~/.claude/handoffs, resolves the target model from CLAUDE_TO_CODEX_MODEL or Codex
config, and dispatches Codex when a supported launcher is available. Relay the launcher result and manual
fallback command exactly.
The Claude Code plugin provides the deterministic namespaced command:
/claude-to-codex:handoff
Maintainers can use the direct Node CLI for recovery options such as --mode print, --codex-model,
--handoff-reason, --session, --latest, --transcript, --tail, --check, or
--codex-subagents:
node plugins/claude-to-codex/skills/handoff/scripts/claude-to-codex.mjs --mode print --latest --codex-model gpt-5.6-sol
Token rule: pass Codex a bounded pointer prompt plus hot context, handoff manifest, git snapshot, digest, and transcript paths, not a full pasted transcript. Source-model safety/refusal verdicts do not become continuation guidance; Codex assesses the original user request independently.
What ships with it
1 file 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.
- 8d ago First seen · 44 lines · 59 tokens per session scan A b5682fbc0329
handoff is a skill published in the GitHub repository Amal-David/claude-to-codex (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 452 once invoked, about $0.0003 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
cross-agent-handoff
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
typescript-react-nextjs-patterns
Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review.…
codex
Delegate coding tasks to OpenAI Codex CLI. Supports presets (turbo/balanced/quality/max) or custom model+effort selection. Use when user wants to leverage GPT-5.5/Codex models for code analysis, refactoring, security audits, or complex transformations. Also covers MCP server management and advanced CLI features.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…