WAY AGENTS.md

A repository instruction file that points coding agents to the main CLAUDE.md file for their rules and working procedures. AGENTS.md is an open standard pointer used so different tools can find the same instructions.

In plain words
What is it for?
Use it to direct Codex, Cursor, Gemini CLI, and similar tools to the project's setup steps, approval process, and guidance on skills and agents.
Why use it?
It avoids maintaining separate instructions for each coding tool. Agents can find the repository's single source of truth before making changes.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/global-mindee/way/agents-md
Clone the repo
git clone --depth 1 https://github.com/Global-mindee/WAY

Made for: Codex, OpenCode.

Per session 135 This file is loaded in full into every session.
When invoked 135 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00135 $0.00135
Opus 5 $0.00068 $0.00068
Sonnet 5 $0.00027 $0.00027
Haiku 4.5 $0.00014 $0.00014

Measured 2d ago against content hash b40a00ea05a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

WAY 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 2d 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 · 7 lines

What it actually says

AGENTS.md

이 레포의 AI 에이전트 지침 정본은 CLAUDE.md 입니다 (이중 정본 금지). 비-Claude 도구(Codex·Cursor·Gemini CLI 등)도 CLAUDE.md를 읽으세요 — 작업 시작 절차·SVOP·결재 흐름·skills/agents 결정 트리가 모두 거기 있습니다.

(AGENTS.md = Linux Foundation 관리 개방 표준 포인터. 거버넌스 결정 — P4 이식성: 환경 무관 동일 하네스가 읽히도록 표준 포인터 채택.)

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. 2d ago First seen · 7 lines · 135 tokens per session scan A b40a00ea05a5

Subscribe to this mod's changes

WAY AGENTS.md is an instructions file published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session, about $0.0007 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 2026-08-30.