tfx-auto-codex

tfx-auto-codex is a skill for Claude Code from tellang/triflux. It costs 35 tokens per session (774 once invoked), scanned A, original, MIT.

An automation workflow that coordinates coding tasks between Codex and Gemini. It sends coding, analysis, review, debugging, testing, and verification work to Codex while keeping design and writing work on Gemini.

In plain words
What is it for?
Use it for combined engineering tasks, such as authentication refactoring, interface improvements, test coverage, code reviews, or onboarding copy and accessibility work.
Why use it?
Projects that mix code, design, and writing can otherwise require manual routing between agents. This workflow separates those types of work and runs the resulting tasks as a dependency-aware plan.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Codex.

Part of the triflux plugin — 29 skills, 1 agent, 12 hooks shipped together

Good fit Use it for combined engineering tasks, such as authentication refactoring, interface improvements, test coverage, code reviews, or onboarding copy and accessibility work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tellang/triflux/tfx-auto-codex
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 tellang/triflux --skill tfx-auto-codex
Clone the repo
git clone --depth 1 https://github.com/tellang/triflux

Made for: Claude Code.

Or install triflux, the plugin that ships this one along with the rest of its 29 skills, 1 agent, 12 hooks.

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 tfx-auto-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/tellang/triflux/tfx-auto-codex/github.svg)](https://agentmods.dev/skills/tellang/triflux/tfx-auto-codex)
Your own site
<a href="https://agentmods.dev/skills/tellang/triflux/tfx-auto-codex"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-auto-codex/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.

agentmods 80×15 button for tfx-auto-codex

Your own site · 80×15
<a href="https://agentmods.dev/skills/tellang/triflux/tfx-auto-codex"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-auto-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 774 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 $0.00035 $0.00774
Opus 5 $0.00017 $0.00387
Sonnet 5 $0.00007 $0.00155
Haiku 4.5 $0.00003 $0.00077

Measured 8d ago against content hash 5475913e00da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tfx-auto-codex 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.

packages/triflux/skills/tfx-workspace/skill-snapshot/tfx-auto-codex/SKILL.md · 78 lines

What it actually says

tfx-auto-codex — Codex 리드형 tfx-auto

목적: 기존 tfx-auto의 오케스트레이션 패턴을 유지하면서 Claude 네이티브 역할(explore, verifier, test-engineer, qa-tester)을 Codex로 치환해 Codex/Antigravity만으로 실행한다.

핵심 원칙

  1. Codex 라우팅 유지
    • 구현/분석/리뷰/디버깅/검증은 Codex 우선.
  2. Gemini 유지
    • designer, writer는 Gemini 경로를 그대로 사용.
  3. Claude 네이티브 제거
    • 실행 시 TFX_NO_CLAUDE_NATIVE=1로 강제.
  4. 고난도 설계는 xhigh
    • 설계/분해/비판 검토 성격의 작업은 codex --profile xhigh 기준으로 운용.

사용법

/tfx-auto-codex "인증 리팩터링 + UI 개선 + 테스트 보강"
/tfx-auto-codex 3:codex "src/api, src/auth, src/payment 병렬 리뷰"
/tfx-auto-codex 2:gemini "온보딩 UI 카피 + 접근성 개선"

실행 규칙

tfx-auto 워크플로우(입력 파싱 → 트리아지 → 분해 → DAG 실행 → 수집/보고)를 그대로 사용한다.

단, 실행 명령은 아래 환경변수를 반드시 포함한다:

TFX_NO_CLAUDE_NATIVE=1 bash ~/.claude/scripts/tfx-route.sh {agent} '{prompt}' {mcp_profile}

역할 치환 (자동)

TFX_NO_CLAUDE_NATIVE=1일 때:

  • explore -> Codex fast
  • verifier -> Codex thorough review
  • test-engineer -> Codex high
  • qa-tester -> Codex thorough review

트리아지 기준

  • codex: 코드 구현/수정/분석/리뷰/디버깅/테스트/검증/리서치
  • gemini: 문서/UI/디자인/멀티모달

Claude 타입 반환은 기본적으로 허용하지 않는다. 분류 결과에 claude가 포함되면 codex로 치환 후 분해를 진행한다. 단, Codex CLI 미설치 환경에서는 실행 안전성을 위해 claude-native fallback이 유지될 수 있다.

권장 프로필

  • 설계/계획/비판적 검토: xhigh
  • 일반 구현/수정: high
  • 리뷰: thorough
  • 빠른 탐색: fast

의존성

  • ~/.claude/scripts/tfx-route.sh 최신 동기화 상태
  • Codex CLI 설치
  • Antigravity CLI 설치 (UI/문서 경로 사용 시)

Troubleshooting

문제 발생 시 /tfx-doctor 실행. (--fix 자동 수정, --reset 캐시 초기화)

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. 8d ago First seen · 78 lines · 35 tokens per session scan A 5475913e00da

Subscribe to this mod's changes

tfx-auto-codex is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 774 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

ready

Make an unfamiliar repository agent-ready with a verify command, smoke tests, guardrails, and project notes. Use for repository setup, agentic engineering, verify commands, hooks, or allowlists; skip when verification and scope are already clear.

ohm41321/luciazero · 50 tokens

handoff

Write a state capsule so the next session — or a different agent/harness — can resume unfinished work without re-deriving context. Use when a session is ending with work incomplete, when the user says "handoff", "pack up", "ส่งต่อ", "continue tomorrow", when switching between Claude Code and Codex mid-task, or when…

ohm41321/luciazero · 86 tokens

lucia-chat

Set two agent sessions talking through the Luciazero Agent Bus and watch it live in a terminal: pick the pair, open the panes, read the transcript. Use for "ให้ codex กับ claude คุยกัน" or "watch the bus".

ohm41321/luciazero · 55 tokens

done

Run the closeout ritual before handing back non-trivial work; full verification, revert-probe honesty, independent review, and scope reporting. Use before declaring completion, opening a PR, wrapping up a change, or "ปิดงาน".

ohm41321/luciazero · 50 tokens

retro

Record durable lessons, null results, and footguns after hard work or debugging. Use when the user asks for a retro, dead ends need preserving, a task disproves an approach, or "จดบทเรียน". Keep repo knowledge separate from machine-local memory.

ohm41321/luciazero · 55 tokens

show

Visualize code structure, changes, and verification evidence in the smallest useful view. Use for connections, flows, diffs, file maps, Mermaid diagrams, evidence maps, or focused HTML; show facts and label unknowns.

ohm41321/luciazero · 47 tokens