Borrowing it
Nothing to install: this file belongs to hjl2004-10/Agent-Worlds. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hjl2004-10/Agent-Worlds/main/CLAUDE.mdgit clone --depth 1 https://github.com/hjl2004-10/Agent-WorldsWrote 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.
[](https://agentmods.dev/instructions/hjl2004-10/agent-worlds/claude-md)<a href="https://agentmods.dev/instructions/hjl2004-10/agent-worlds/claude-md"><img src="https://agentmods.dev/badge/instructions/hjl2004-10/agent-worlds/claude-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.
<a href="https://agentmods.dev/instructions/hjl2004-10/agent-worlds/claude-md"><img src="https://agentmods.dev/badge/instructions/hjl2004-10/agent-worlds/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.07125 | $0.07125 |
| Opus 5 | $0.03563 | $0.03563 |
| Sonnet 5 | $0.01425 | $0.01425 |
| Haiku 4.5 | $0.00713 | $0.00713 |
Grade A, and why
Agent-Worlds 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 9d 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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI_夸父 开发规范文档 (v2.0 - Skill化重构)
🌐 【语言要求】所有 Skill（/qa、/review、/plan-eng-review 等）的最终回答、报告、表格、总结必须使用中文。过程中的内部思考、代码注释、变量名等不限语言。
⚠️ 【重要提示】当前项目文件过大，查找时请尽量避免全量查找，避免读完整个上下文。优先使用精确路径或针对性搜索。
📝 【开发环境】不用构建了，现在只在开发环境下进行。前端使用
npm run dev，后端直接python main.py。🐍 【Python 路径】使用系统 Python 3.10+ 或虚拟环境，直接
python main.py启动。🗂️ 【素材库】像素素材统一放在
static/public/下使用。
架构总览：概念坐标系（先看这张图）
本系统是一个 agent 平台（AI_OS）。代码骨架与业界 agent 架构趋同：横向是多子系统、纵向是作用域分层，两者正交。先建立这张坐标系，再看下面的分层原则与目录职责，每块代码的"身份"就清楚了。
核心链：
Scaffolding（拼脚手架）→ 经 Harness（驾驭层）→ 跑出 Agentic Loop（循环）→ 实例化为 Agent（带运行时状态的个体）。 一个 NPC 的 hjl = 一份 scaffolding；core/运行时 = harness；跑起来带记忆/坐标/关系 = agent。
横向：子系统（业界术语 ↔ 本项目目录）
| 业界概念 | 本项目目录 | 职责 |
|---|---|---|
| Gateway 网关 | main.py + api/auth.py |
请求入口、路由挂载、token/CORS 守卫 |
| Channel 渠道·LLM 出站 | tools/llm/、tools/llm_l1.py、llm_l2.py |
选 LLM 供应商（zhipu/volcano/local/claude），代码内已用 channel 命名 |
| Channel 渠道·对话入站 | core/wechat/、tools/qq_bot*.py |
对话从哪个外部来源进来 |
| Scaffolding 脚手架 | tools/loader_l1.py、core/prompt/、data/*.hjl、config/ |
装配 agent：提示词变量槽 + 工具组 + 技能 + MCP + persona + 记忆/图谱策略。hjl 即脚手架载体 |
| Harness 驾驭层 | core/social/、drive/、mem/、graph/、tools/tool_l1.py |
运行时引擎：让脚手架跑起来（对话、移动、记忆、图谱、工具执行） |
| Agentic Loop | core/social/social_l1.py::_chat_with_tool_loop |
plan→act→observe 循环（寄生在 harness 内） |
| Context Engineering | core/prompt/prompt_l2.py::build_context |
运行时策展有限上下文：注入哪些变量、各多少限量 |
| State Bus 状态总线 | core/state_bus.py、api/_state.py |
子系统间事件推送/共享态（神经系统） |
| Frontend 前端 | static/ |
像素风 UI、地图、调试面板。构建部署：npm run build → static/dist/ → main.py 经 StaticFiles serve（非 dev 热部署） |
术语参考：HuggingFace·agent-glossary、Martin Fowler·Harness Engineering、Anthropic·Context Engineering。
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.
- 9d ago First seen · 532 lines · 7,125 tokens per session scan A 882f70e2093f
Agent-Worlds CLAUDE.md is an instructions file published in the GitHub repository hjl2004-10/Agent-Worlds (7 stars, last pushed yesterday), licensed MIT. It adds 7,125 tokens to every session, about $0.0356 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.