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/69gg/undefined/claude-mdgit clone --depth 1 https://github.com/69gg/UndefinedWhat 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 | $0.03571 | $0.03571 |
| Opus 5 | $0.01785 | $0.01785 |
| Sonnet 5 | $0.00714 | $0.00714 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade A, and why
Undefined CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
Undefined 是基于 Python asyncio 的高性能 QQ 机器人平台，通过 OneBot V11 协议（NapCat/Lagrange.Core）与 QQ 通信，搭载认知记忆架构、自研 Skills 系统、本地知识库、全局表情包库，以及 Management-first WebUI / Desktop / Android 管理端。
开发命令
# 依赖安装 / 初始化
uv sync
uv run playwright install # 页面截图等能力依赖的浏览器运行时
# 启动
uv run Undefined-webui # 启动 Management-first WebUI（推荐入口）
uv run Undefined # 直接启动 Bot
# WebUI 自动启动 Bot
# 配置 [webui].autostart_bot = true 后，运行 uv run Undefined-webui 会自动拉起 bot 进程
# 默认为 false，保持传统手动启动行为
# 注意：该配置仅在 WebUI 启动时生效，运行时修改需重启 WebUI
# 代码质量（提交前必须全部通过）
uv run ruff format .
uv run ruff check .
uv run mypy . # strict=true
uv run pytest tests/
uv run pytest tests/test_xxx.py
uv run pytest tests/test_xxx.py::test_func -v
uv build --wheel # 校验打包与资源包含
# 前端 / 桌面端（仅改动 apps/undefined-console/ 或 apps/undefined-chat/ 或 webui/static/js/ 时需要）
cd apps/undefined-console && npm ci && npm run check
cd apps/undefined-console && npm run dev
cd apps/undefined-console && npm run tauri:dev
cd apps/undefined-chat && npm ci && npm run check
cd apps/undefined-chat && npm run tauri:dev
# Git hooks 安装
bash scripts/install_git_hooks.sh
# pre-commit 自动执行：ruff format --check + ruff check + mypy
# 含 JS/Tauri 改动时额外执行：Biome + TypeScript + cargo fmt/check
代码规范
- 类型注释：所有 Python 代码必须有完整类型注释，mypy strict 模式
- 异步 IO：磁盘读写必须走
utils/io.py（asyncio.to_thread+ 跨平台文件锁 + 原子写入），禁止在事件循环中直接阻塞 IO - Python 版本：
>=3.11, <3.14（推荐 3.12） - 测试：pytest + pytest-asyncio，
asyncio_mode = "auto" - 前端格式化：
src/Undefined/webui/static/js/由根目录biome.json管理；apps/undefined-console/和apps/undefined-chat/走 Biome + TypeScript + Cargo 检查 - 版本号同步：发布版本时优先使用
uv run python scripts/bump_version.py <version>，统一同步 Python 包、console、chat 与 Tauri 版本号 - Git hooks：优先通过
scripts/install_git_hooks.sh安装，不要手动维护core.hooksPath
架构分层
核心源码位于 src/Undefined/，主要模块如下：
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.
- 2d ago First seen · 172 lines · 3,571 tokens per session scan A 323997fd5c3c
Undefined CLAUDE.md is an instructions file published in the GitHub repository 69gg/Undefined (259 stars, last pushed 6d ago), licensed MIT. It adds 3,571 tokens to every session, about $0.0179 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
ouro CLAUDE.md
Instructions for ouro-ai-labs/ouro, covering ouro — agent instructions, command discovery (no guessing), core workflow (verify → explore → plan → implement → ship), quickstart (local dev) and three-layer architecture (read first).
AgentX AGENTS.md
Instructions for DezXBT/AgentX, covering agentx — agent integration guide, contract, decision guide, multi-account and pagination.
ouro AGENTS.md
Instructions for ouro-ai-labs/ouro, a project described as: Ouro is an open-source AI agent — run it as a Coding agent CLI or deploy it as a bot just like JARVIS.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.