triflux: Instructions file for Codex

AGENTS.md

triflux AGENTS.md is an instructions file for Codex, OpenCode from tellang/triflux. It costs 748 tokens per session, scanned A, original, MIT.

Project instructions for Triflux that define how Codex should run tasks, use its agent-routing tools, handle non-interactive results, and follow project-specific safety rules.

In plain words
What is it for?
Use them when Codex works in Triflux, especially for routed or multi-agent jobs, headless execution, reasoning profiles, and reviewing another agent’s code.
Why use it?
They prevent unsupported direct agent calls and make automated runs, cross-checking, profiles, and result collection follow the project’s expected process.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; runs codex exec.

This is tellang/triflux's own configuration. It tells Codex and OpenCode how to work on triflux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything triflux configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tellang/triflux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tellang/triflux/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tellang/triflux

Made for: Codex, OpenCode.

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 triflux AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tellang/triflux/agents-md"><img src="https://agentmods.dev/badge/instructions/tellang/triflux/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 748 This file is loaded in full into every session.
When invoked 748 The same file — it is already loaded in full.
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 $0.00748 $0.00748
Opus 5.5 $0.00299 $0.00299
Sonnet 5.5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 15d ago against content hash 98ee548ef180, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triflux AGENTS.md 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 15d 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.

AGENTS.md · 40 lines

What it actually says

triflux Codex 가이드

상세 운영 지시는 CLAUDE.md에 있다. Codex는 @import를 지원하지 않으므로 필요할 때 직접 읽는다.

핵심 규칙 (triflux 환경 특화)

  • Codex 직접 호출 금지. tfx-auto --cli codex를 거친다. 코드 변경 병렬 작업은 작업별 worktree와 세션을 분리하고 각 세션에서 tfx-auto를 사용한다.
  • 프롬프트는 -- 뒤의 인자로 넘기고 표준 입력은 닫는다(… -- "$prompt" < /dev/null). codex < prompt.md는 비대화식 실행이라 실패한다.
  • config.toml에 approval_policy, sandbox_mode 기본값을 두고 CLI는 --profile만 지정한다. 중복 플래그를 쓰지 않는다.
  • Claude가 작성한 코드는 Codex로 교차 검증한다. 스스로 승인하지 않는다.
  • 비대화식 결과는 작업 알림이 완료된 뒤에만 읽는다.

비대화식 실행 경로

  • codex exec / agy --dangerously-skip-permissions --print= 를 직접 호출하지 않는다. 자동 차단 훅(headless-guard)은 2026-09-07 에 제거되었으므로 호출자가 지킨다.

추론 수준 예외 경로

  • 기본 역할 라우팅은 low/medium/high/xhigh 프로필을 유지한다.
  • 최난도 단일 작업만 TFX_CODEX_PROFILE=max (astra_max).
  • ultra는 최상위 단독 deep-executor/scientist-deep에서만 허용하고, 팀·비대화식·워커 내부의 ultra 요청은 중첩 분산 실행을 막기 위해 astra_max로 낮춘다.
  • --retry auto-escalate의 Codex 단계도 astra_max다.

비대화식 결과 회수

  • 완료 마커: === HEADLESS_COMPLETE succeeded=N failed=N total=N ===
  • 결과 색인: $TMPDIR/triflux-<uid>/tfx-headless/{sessionName}.results.json. 워커별 상태, exit 코드, 출력 경로는 이 파일을 읽는다(ADR-0034).
  • 워커 상세: $TMPDIR/triflux-<uid>/tfx-headless/{sessionName}-worker-N.txt

SSH 방식

  • hosts.json의 os 필드로 셸을 판단한다 (windows=PowerShell, darwin=zsh, linux=bash).
  • SSH 너머로 Codex를 직접 실행하지 않는다(config.toml 충돌과 TTY 문제). 원격에서 Codex가 필요하면 tfx-remote → Claude Code → Claude가 내부에서 codex 호출.

작업 합의

  • 한국어 우선, 기술 용어는 원어 유지.
  • 커밋: type(scope): 한국어 설명. type은 소문자이며 Co-Authored-By와 AI 꼬리표를 넣지 않는다.
  • 비밀 정보(API 키, 토큰, 세션)를 하드코딩하지 않는다.

코드 작성 원칙

  • 주석은 한국어로 쓴다.
  • 제거 여부는 해당 파일을 끝까지 직접 읽고 판단한다.
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. 15d ago Changed · -12 tokens per session 98ee548ef180
  2. 16d ago Changed · -2 lines · -92 tokens per session 69b258a1fa21
  3. 19d ago Changed · -5 lines · -82 tokens per session d6390e215f14
  4. 20d ago Changed · +5 lines · +67 tokens per session 38cd6d99db6d
  5. 23d ago Changed · +26 tokens per session 87345dc6aa36
  6. 1mo ago Changed · +3 tokens per session b3dcf3f09a9f
  7. 1mo ago Changed · +11 tokens per session 81670f1a7ef1
  8. 1mo ago First seen · 42 lines · 827 tokens per session scan A 13f06d9874aa

Subscribe to this mod's changes

triflux AGENTS.md is an instructions file published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 748 tokens to every session, about $0.0030 per session on Opus 5.5. 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens