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.
npx agentmods add instructions/lee-w/maigo/agents-mdgit clone --depth 1 https://github.com/Lee-W/maigoWhat 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 | $0.01468 | $0.01468 |
| Opus 5 | $0.00734 | $0.00734 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
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 3d 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.
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 underhooks/and blocks the turn automatically. Example: 🩵 Tomori 沒寫 plan path →teammate_quality_check.pyblock；任務宣告完成沒跑 test →verify_completion.pyblock. 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。
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.
- 3d ago First seen · 90 lines · 1,468 tokens per session scan A f5fa93333231
maigo AGENTS.md is an instructions file published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 1,468 tokens to every session, about $0.0073 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.