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/finch04/lightbot/agents-mdgit clone --depth 1 https://github.com/finch04/LightBotWhat 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 | $0.07716 | $0.07716 |
| Opus 5 | $0.03858 | $0.03858 |
| Sonnet 5 | $0.01543 | $0.01543 |
| Haiku 4.5 | $0.00772 | $0.00772 |
Grade A, and why
LightBot 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- LightBot CLAUDE.md — 92% identical, 36 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,022 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LightBot - AI Coding Guide
轻量级 Java AI Agent 平台
Tech Stack: SpringBoot + SpringAI + Vue3
项目原则
| 原则 | 说明 |
|---|---|
| 模块化 | 每个功能域独立模块，边界清晰，可独立演进 |
| AI Native | 架构围绕 AI 能力设计，而非传统 CRUD 套壳 |
| Java First | 后端统一 Java，不混入 Python / Node |
| 渐进式演进 | 先单体后拆分，先简单后复杂，不提前设计 |
| 低耦合 | 模块间通过接口通信，禁止直接依赖实现类 |
架构原则
禁止事项
❌ 禁止跨模块直接调用 Service
❌ 禁止 Controller 写业务逻辑
❌ 禁止循环依赖
❌ 禁止硬编码 Prompt
❌ 禁止直接依赖 OpenAI SDK / DashScope SDK
❌ 禁止在业务代码中直接 new RestTemplate 调用模型
❌ 禁止使用拼接SQL语句操作数据库（必须使用 MyBatis-Plus）
❌ 禁止在 Service 中直接操作中间件客户端（必须通过 Util 类）
❌ 禁止 lightbot-server 新增业务 Service、DTO/VO、tool/builtin、service/chat、workflow/*Executor*
必须遵守
✅ 所有模型调用必须通过统一 AI Framework（SpringAI）
✅ 跨模块调用通过 Service 接口；跨域聚合使用 Port 模式（如 Dashboard）；禁止 import ...service.impl.*
✅ 所有 Prompt 必须模板化，存储于配置或数据库
✅ 所有外部依赖通过依赖注入，禁止静态方法调用
✅ 所有数据库操作必须使用 MyBatis-Plus（LambdaQueryWrapper / ServiceImpl）
✅ 所有中间件操作（MinIO/Redis/MQ等）必须封装为 Util 类
✅ 业务核心逻辑必须有注释说明意图
模块结构
架构边界详见
docs/architecture/module-boundaries.md
lightbot/
├── lightbot-common/ # Result、枚举、公共类型
├── lightbot-framework/ # Spring 配置、Redis/MinIO 等中间件 Util
├── lightbot-platform/ # 用户、任务、系统配置、API Key、Dashboard、日志
├── lightbot-ai/ # 模型工厂、Prompt、LLM Trace
├── lightbot-knowledge/ # RAG、文档、图谱、评测
├── lightbot-tool/ # Tool / MCP / Skill / SubAgent 定义与注册
├── lightbot-workflow/ # Workflow DSL、节点处理器、图校验
├── lightbot-agent/ # Agent 运行时（Chat、Workflow 执行、SubAgent）
├── lightbot-server/ # HTTP 入口（Controller、Config、拦截器）
└── lightbot-ui/ # Vue3 前端（独立目录，非 Maven 模块）
依赖规则
common ← framework ← platform ← ai ← knowledge ← tool ← workflow ← agent ← server
lightbot-server → platform, ai, knowledge, tool, workflow, agent
lightbot-agent → platform, workflow, knowledge
lightbot-workflow → tool
lightbot-tool → knowledge
lightbot-knowledge → ai
lightbot-ai → framework, platform
lightbot-platform → framework
lightbot-framework → common
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 · 1,022 lines · 7,716 tokens per session scan A a4ff334937ea
LightBot AGENTS.md is an instructions file published in the GitHub repository finch04/LightBot (93 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 7,716 tokens to every session, about $0.0386 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
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.
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).
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.