What is maigo AGENTS.md?

Contributor instructions for the maigo repository, covering coding-agent behavior, project conventions, tone, and the relationship between hooks and skills. It also defines emoji markers used for agents and narrators in project-related writing.

Use it when contributing to maigo, especially when changing shared instructions, discussing its agents or skills, or writing contributor-facing documentation.

It gives agents the repository-specific rules they need to make compatible changes and communicate in the expected style. It also warns that shared rules must stay synchronized between AGENTS.md and CLAUDE.md.

How Lee-W/maigo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Lee-W/maigo. 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/Lee-W/maigo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Lee-W/maigo

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lee-w/maigo/agents-md/github.svg)](https://agentmods.dev/instructions/lee-w/maigo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lee-w/maigo/agents-md"><img src="https://agentmods.dev/badge/instructions/lee-w/maigo/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lee-w/maigo/agents-md"><img src="https://agentmods.dev/badge/instructions/lee-w/maigo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,468 This file is loaded in full into every session.

When invoked 1,468 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.

Model	Per session	Once invoked
Fable 5.1	$0.01468	$0.01468
Opus 5.5	$0.00587	$0.00587
Sonnet 5.5	$0.00294	$0.00294
Haiku 4.5	$0.00147	$0.00147

Measured 2mo ago against content hash f5fa93333231, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maigo 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 2mo 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maigo contributor instructions for Codex agents

鏡射檔同步：CLAUDE.md 與 AGENTS.md 共用下列 contributor conventions。修改共同規則時必須同步另一份；平台特定措辭、連結格式與 hook runtime 說明可保留差異，否則另一端會照舊快照做事。

Tone

This project is emoji-friendly. When working in this repository (including meta-discussion about maigo's own design — skills, commands, agents, docs), default to allowing emoji use where it aids clarity or matches the project's voice:

Agent identity markers — 🐱 樂奈 / 🩵 燈 / 🎀 愛音 / 🟡 爽世 / 🟣 立希
Narrator markers — 🌙 Doloris / 🌑 Mortis (per skills/narration)
Section / status markers in chat output where they aid scanning

Default assistant behavior that avoids emoji unless asked does not apply here — the emoji markers below are project convention, not decoration, and should be used where they aid clarity.

This applies to prose, chat output, and contributor-facing docs in this repo. Source code (Python, YAML config, etc.) follows its own conventions — do not sprinkle emojis into code where they don't already belong.

Agent & narrator emoji — quick-ref (always in context)

Every mention of an agent or narrator name in prose, summaries, and chat output must carry the emoji prefix — not just the line where they speak.

Role	Emoji	Names
樂奈	🐱	Raana
燈	🩵	Tomori
愛音	🎀	Anon
爽世	🟡	Soyo
立希	🟣	Taki
Doloris	🌙	—
Mortis	🌑	—

Not applicable: content inside code blocks, file paths (agents/Soyo.md), commit messages, and direct quotes from the user.

Full narration rules (when to use Doloris vs Mortis, voice tone, etc.) live in skills/narration.

Hooks vs Skills boundary

hooks/ = machine-enforced checks inside a Claude Code session — Claude Code's harness runs the scripts under hooks/ and blocks the turn automatically. Example: 🩵 Tomori 沒寫 plan path → teammate_quality_check.py block；任務宣告完成沒跑 test → verify_completion.py block. Codex 也有 lifecycle hook runtime，但 Maigo 的 Codex manifest 會用空的 inline hooks 覆蓋這組 Claude Code 專用 hooks：兩端支援的事件與 I/O schema 不完全相同，直接共用會讓 Codex 把 Claude Code 的合法輸出判成錯誤。Codex command 會顯式執行 review / verification；其餘 hook 邏輯仍視為必要的手動步驟（閱讀，或在適用時直接執行 python3 hooks/<script>.py），不依賴環境自動攔截。
skills/ = 知識共享。Prompt-driven 共用 narrative / convention / workflow，靠 command / agent 定義檔用 markdown link 引用進 context 才生效 ——這點在 Claude Code 與 Codex 都一樣，都是「讀了才知道」，不是機器強制。例： skills/strict-review、 skills/commit-message、 skills/narration。

Read the full file on GitHub · 90 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.

2mo ago First seen · 90 lines · 1,468 tokens per session scan A f5fa93333231

Subscribe to this mod's changes

maigo AGENTS.md is an instructions file published in the GitHub repository Lee-W/maigo (14 stars, last pushed 6d ago), licensed MIT. It adds 1,468 tokens to every session, about $0.0059 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 2026-08-30.

maigo AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
maigo AGENTS.mdLee-W/maigo	Instructions file	14	6d ago	MIT	A	1,468	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

maigo: Instructions file for Codex