Agent skill

Claude Codex Fallback

by bam-bam-2 in bam-bam-2/solo-skills

CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용

MITAuto-check passed

Install Claude Codex Fallback

skills CLI
$ npx skills add bam-bam-2/solo-skills --skill claude-codex-fallback -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bam-bam-2/solo-skills claude-codex-fallback --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bam-bam-2/solo-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-codex-fallback .claude/skills/claude-codex-fallback && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-codex-fallback
GitHub stars
367
Token cost
~275 tokens
SKILL.md length
192 words
Files
2 (incl. scripts)
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용

  • Works in 8 steps: 같은 프롬프트를 안전한 임시파일에 저장한다. → Claude Code를 먼저 실행한다. 자동화에 필요한 모델, 권한, 턴… → Claude가 실패했을 때 stdout과 stderr에서 실제 사용량… → …
  • Runs Shell scripts from its folder

What it does

Claude Codex Fallback is an agent skill from bam-bam-2/solo-skills. CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용

Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/llm-with-fallback.sh`).

The repository describes itself as: 1인 사업가 생산성 키트 — 직원 없이 58개를 자동화했고, 그중 바로 쓸 수 있는 AI 에이전트 스킬 38개(+실행 스크립트 19개)를 공개합니다. The licence is MIT.

Example prompts

  • “/claude-codex-fallback”

Requirements

  • A Bash shell

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. 같은 프롬프트를 안전한 임시파일에 저장한다.
  2. Claude Code를 먼저 실행한다. 자동화에 필요한 모델, 권한, 턴 상한을 기존 작업과 동일하게 유지한다.
  3. Claude가 실패했을 때 stdout과 stderr에서 실제 사용량 한도 문구만 판별한다.
  4. 사용량 한도가 확정된 경우에만 같은 프롬프트를 Codex CLI로 한 번 재실행한다.
  5. Codex도 실패하면 원래 오류와 폴백 오류를 함께 기록하고 정상 산출물처럼 발송하지 않는다.
  6. 인증 토큰 값은 로그나 응답에 출력하지 않는다. Claude OAuth와 Codex ChatGPT 인증은 각 CLI의 기존 저장소를 사용한다.
  7. 배포 전에 세 경로를 각각 검증한다.
  8. 실제 운영 환경에서 무발송 또는 읽기 전용 프롬프트로 한도 감지와 폴백 성공 로그를 확인한다.

What it can do on your machine

Read from SKILL.md and the folder at commit 0712439. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Codex Fallback loads about 275 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 192 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~275

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from bam-bam-2/solo-skills at commit 0712439, republished under its MIT licence (© bam-bam-2). 192 words, ~275 tokens.

Download SKILL.mdSave it as .claude/skills/claude-codex-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
claude-codex-fallback
description
CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용

이 스킬이 시스템에 하는 일 (설치 전 확인)

  • claude와 codex CLI를 로컬에서 실행합니다. 둘 다 설치돼 있어야 합니다.
  • OAuth 토큰을 ~/.config/llm/claude-oauth-token에서 읽기만 합니다. 출력하거나 전송하지 않습니다.
  • 프롬프트는 임시파일(mktemp, mode 600)에 두고 종료 시 삭제합니다.
  • 네트워크 호출은 각 CLI가 하는 것뿐이고, 이 스크립트가 따로 하는 외부 통신은 없습니다.

Claude 우선, Codex 조건부 폴백

  1. 같은 프롬프트를 안전한 임시파일에 저장한다.
  2. Claude Code를 먼저 실행한다. 자동화에 필요한 모델, 권한, 턴 상한을 기존 작업과 동일하게 유지한다.
  3. Claude가 실패했을 때 stdout과 stderr에서 실제 사용량 한도 문구만 판별한다.
    • 예: weekly limit, usage limit, hit your limit, limit ... resets
    • 일반 네트워크 오류, 인증 오류, 파싱 오류, 단순 rate limit은 자동 모델 전환 근거로 쓰지 않는다.
  4. 사용량 한도가 확정된 경우에만 같은 프롬프트를 Codex CLI로 한 번 재실행한다.
  5. Codex도 실패하면 원래 오류와 폴백 오류를 함께 기록하고 정상 산출물처럼 발송하지 않는다.
  6. 인증 토큰 값은 로그나 응답에 출력하지 않는다. Claude OAuth와 Codex ChatGPT 인증은 각 CLI의 기존 저장소를 사용한다.
  7. 배포 전에 세 경로를 각각 검증한다.
    • Claude 정상 성공: Codex 미호출
    • Claude 사용량 한도: Codex 호출 및 성공
    • Claude 일반 오류: Codex 미호출
  8. 실제 운영 환경에서 무발송 또는 읽기 전용 프롬프트로 한도 감지와 폴백 성공 로그를 확인한다.

© bam-bam-2, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/claude-codex-fallback of bam-bam-2/solo-skills.

  • SKILL.md
  • scripts/llm-with-fallback.sh

Open the folder on GitHubat commit 0712439

Compare with similar skills

Claude Codex Fallback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Codex Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Codex Fallback this skillbam-bam-2/solo-skills367—~275Automated safety check: PassMIT
Offline Fallbackthedaviddias/Front-End-Checklist74k—~488Automated safety check: PassMIT
PDF Extraction FallbacksHKUDS/OpenSpace7.7k—~1.8kAutomated safety check: PassMIT
Execute Code FallbackHKUDS/OpenSpace7.7k—~1kAutomated safety check: PassMIT
Sandbox Fallback ExecutionHKUDS/OpenSpace7.7k—~740Automated safety check: PassMIT
Excel Creation FallbackHKUDS/OpenSpace7.7k—~921Automated safety check: PassMIT

Similar skills

  • Offline Fallback

    thedaviddias/Front-End-Checklist

    A skill your agent uses when adding PWA capabilities, implementing a service worker, or improving the experience for users on unreliable network connections.

    74k GitHub stars~488 tokensUpdated 2 days ago
    Auto-check passed
  • Multi-fallback PDF/text extraction with early failure detection and sequential tool fallbacks

    7.7k GitHub stars~1.8k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Execute Code Fallback

    HKUDS/OpenSpace

    Fallback from executecodesandbox to runshell when e2b sandbox is unavailable

    7.7k GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails

    7.7k GitHub stars~740 tokensUpdated 1 mo ago
    Auto-check passed
  • Use shellagent as fallback when executecodesandbox fails for Excel file operations

    7.7k GitHub stars~921 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Fallback File Ops

    HKUDS/OpenSpace

    Use runshell as fallback when executecodesandbox or shellagent fail on filesystem operations

    7.7k GitHub stars~718 tokensUpdated 1 mo ago
    Auto-check passed

More from bam-bam-2/solo-skills

All 38 skills in this repo
  • Computer Use

    bam-bam-2/solo-skills

    Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions.

    367 GitHub starsUsed in 1 repo~915 tokens
    Auto-check passed
  • Orchestration

    bam-bam-2/solo-skills

    Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, workerdone/escalation waits, task DAGs, decision gates, coordinator loops…

    367 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Book PDF Pagedjs

    bam-bam-2/solo-skills

    마크다운 원고를 실제 책처럼 보이는 PDF/EPUB 전자책으로 만들 때 사용. An agent skill from bam-bam-2/solo-skills.

    367 GitHub stars~2.5k tokensUpdated 24 days ago
    Auto-check passed
  • Lecture Recording Captions

    bam-bam-2/solo-skills

    밤밤의 강연·라이브·기수 세션 녹화본(줌 클라우드·디스코드·맥 화면기록)을 자막판 영상으로 만들고 배포할 때 읽을 것.

    367 GitHub stars~1.4k tokensUpdated 24 days ago
    Auto-check passed
  • Naver Mail Imap

    bam-bam-2/solo-skills

    밤밤의 네이버 메일(you@example.com)을 브라우저 없이 읽어야 할 때 사용. An agent skill from bam-bam-2/solo-skills.

    367 GitHub stars~964 tokensUpdated 24 days ago
    Auto-check: notes
  • Style Skill Creator

    bam-bam-2/solo-skills

    Creative writing skill for creating style skills that teach Claude to write in specific styles.

    367 GitHub stars~935 tokensUpdated 24 days ago
    Auto-check passed

Questions about Claude Codex Fallback

What does Claude Codex Fallback do?

CLI 기반 자동화에서 Claude를 우선 사용하고 계정 사용량 한도 초과 때만 Codex로 재실행하는 폴백을 구현하거나 점검할 때 사용. Claude Codex Fallback is an agent skill from bam-bam-2/solo-skills.

How do I install Claude Codex Fallback in Claude Code?

Run `npx skills add bam-bam-2/solo-skills --skill claude-codex-fallback -a claude-code`. Or copy the skill folder (skills/claude-codex-fallback in bam-bam-2/solo-skills) into .claude/skills/claude-codex-fallback in your project. Claude Code loads it when a task matches its description.

How do I install Claude Codex Fallback in Codex?

Run `npx skills add bam-bam-2/solo-skills --skill claude-codex-fallback -a codex`. Or copy the skill folder (skills/claude-codex-fallback in bam-bam-2/solo-skills) into .agents/skills/claude-codex-fallback in your project. Codex loads it when a task matches its description.

Can I use Claude Codex Fallback in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bam-bam-2/solo-skills --skill claude-codex-fallback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-codex-fallback, .gemini/skills/claude-codex-fallback, .github/skills/claude-codex-fallback and .opencode/skills/claude-codex-fallback in your project.

What does Claude Codex Fallback need to run?

Going by SKILL.md and its folder, Claude Codex Fallback needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Claude Codex Fallback access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claude Codex Fallback safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Claude Codex Fallback use?

Claude Codex Fallback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claude Codex Fallback use?

About 275 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Codex Fallback?

Skills that share tags, products or a category with Claude Codex Fallback: Offline Fallback (thedaviddias/Front-End-Checklist, 74k stars), PDF Extraction Fallbacks (HKUDS/OpenSpace, 7.7k stars), Execute Code Fallback (HKUDS/OpenSpace, 7.7k stars) and Sandbox Fallback Execution (HKUDS/OpenSpace, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Codex Fallback?

bam-bam-2 (a GitHub user) maintains it in bam-bam-2/solo-skills, which has 367 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 14, 2026.

Source: bam-bam-2/solo-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.