failover-crossover

failover-crossover is a skill for Codex from rodrigorpassos/claude-codex-failover. It costs 278 tokens per session (1,896 once invoked), scanned A, original, MIT.

A manually triggered handoff procedure between Codex and Claude, two AI coding assistants, when one becomes unavailable or returns. It transfers session state and supports reconciliation after the handoff.

In plain words
What is it for?
Use it when Codex is down and Claude must continue the session, or when Codex returns and needs to realign with the state created during the interruption.
Why use it?
It provides a defined way to continue interrupted work across the two assistants. It also separates project changes from changes to the assistant setup and governance.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it when Codex is down and Claude must continue the session, or when Codex returns and needs to realign with the state created during the interruption.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rodrigorpassos/claude-codex-failover/failover-crossover
Install

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.

Any agent
npx skills add rodrigorpassos/claude-codex-failover --skill failover-crossover
Clone the repo
git clone --depth 1 https://github.com/rodrigorpassos/claude-codex-failover

Made for: Codex.

Wrote 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.

agentmods badge for failover-crossover

README.md
[![agentmods](https://agentmods.dev/badge/skills/rodrigorpassos/claude-codex-failover/failover-crossover.svg)](https://agentmods.dev/skills/rodrigorpassos/claude-codex-failover/failover-crossover)
Your own site
<a href="https://agentmods.dev/skills/rodrigorpassos/claude-codex-failover/failover-crossover"><img src="https://agentmods.dev/badge/skills/rodrigorpassos/claude-codex-failover/failover-crossover.svg" alt="Measured on agentmods" height="20"></a>
Per session 278 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00278 $0.01896
Opus 5 $0.00139 $0.00948
Sonnet 5 $0.00056 $0.00379
Haiku 4.5 $0.00028 $0.00190

Measured 7d ago against content hash bb77d0a7840e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

failover-crossover 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 7d 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.

claude/skills/failover-crossover/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

failover-crossover — lado CLAUDE (Opus)

Skill crossover de failover manual, espelho inverso de codex/skills/failover-crossover (lado Codex). Quem aciona é o lado UP: esta skill roda no Claude, quando o GPT/Codex caiu e o Opus está vivo. O modelo de resiliência não precisa de processo externo porque a skill que executa é a do lado que sobreviveu.

Fontes (ler de 1ª mão ao acionar): docs/contract.md (§4 failover, §5 isolamento) · docs/runbook.md (prompts P3/P4) · docs/adr/0001 (dois orquestradores) e docs/adr/0002 (sem degradar modelo). Gate de reconciliação (contexto separado): para scope=harness-meta (governança), um subagente revisor adversarial em contexto separado; para scope=project (código), revisão em instância/sessão distinta apropriada ao código.

Convenção de instalação: ao instalar no seu harness, copie este SKILL.md para ~/.claude/skills/failover-crossover/ e os docs citados para onde preferir (ex.: ~/.claude/docs/). Os paths ~/.claude (casa do Claude Code), ~/.codex (casa do Codex CLI) e ~/.agents/skills (skills do Codex) são as localizações padrão dos harnesses. As branches failover/harness são nomes de exemplo — ajuste aos da sua topologia.

Parâmetros canônicos (mudança de estado)

Invocação: failover-crossover <event> [scope=<project|harness-meta>] [context="<...>"]

  • event — OBRIGATÓRIO, canônico; a transição de estado observada. Vocabulário crossover compartilhado = {opus-down, opus-up, gpt-down, gpt-up}. Esta skill (Claude) trata apenas:
    • gpt-down — GPT/Codex indisponível, Opus UP → Claude ASSUME a sessão do Codex e continua (runbook P3).
    • gpt-up — GPT/Codex voltou → o Claude disponibiliza o estado (versionado/handoff) e o Codex realinha a própria casa em sessão nativa (runbook P4); o Claude não executa P4 (ponte read-only em ~/.codex).
    • (opus-down/opus-up pertencem ao lado Codex — recusar com ponteiro à skill espelho.)
  • scope — canônico; fixa a invariante §5 (destino do trabalho):
    • project → trabalho vai ao repo/branch do projeto.
    • harness-meta → meta-trabalho no harness → branch failover (e o Claude primário reconcilia a harness a partir dela).
  • context — texto livre; o que a sessão interrompida fazia / objetivo / onde parou (insumo da recuperação).

Read the full file on GitHub · 88 lines

Changes

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.

  1. 7d ago First seen · 88 lines · 278 tokens per session scan A bb77d0a7840e

Subscribe to this mod's changes

failover-crossover is a skill published in the GitHub repository rodrigorpassos/claude-codex-failover (1 stars, last pushed 2mo ago), licensed MIT. It adds 278 tokens to every session and 1,896 once invoked, about $0.0014 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.