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/yideng966/lightagent/agents-mdgit clone --depth 1 https://github.com/yideng966/LightAgentWhat 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 | $0.19455 | $0.19455 |
| Opus 5 | $0.09728 | $0.09728 |
| Sonnet 5 | $0.03891 | $0.03891 |
| Haiku 4.5 | $0.01946 | $0.01946 |
Grade A, and why
LightAgent 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 — 678 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LightAgent 项目协作指南
本文件面向在本仓库内工作的 AI Agent 与开发者。目标是先理解项目边界，再用最小改动完成需求，并保留可验证、可回退的交付路径。
项目概览
LightAgent 是一个以 Python 为主的多渠道 Agent Harness 项目，包含：
- 后端运行入口：
app.py - 配置中心：
config.py、config-template.json - 消息渠道层：
channel/ - 模型、语音、翻译路由：
bridge/、models/、voice/、translate/ - Agent 核心协议、工具、技能、记忆、知识库：
agent/ - 插件系统：
plugins/ - CLI：
cli/ - 历史桌面端归档：
desktop/（停止维护，不参与构建发布） - 文档站内容：
docs/ - 回归测试：
tests/
项目核心数据流：
app.py加载配置并启动ChannelManager。channel/channel_factory.py根据channel_type创建 Web、IM 或终端渠道。- 渠道把消息包装为
bridge.context.Context。 bridge/bridge.py根据配置选择聊天模型、语音、翻译或 Agent 模式。- Agent 模式通过
bridge/agent_bridge.py进入agent/，按工具、技能、记忆与知识库上下文执行任务。 - 回复通过原渠道发送回用户。
主要目录职责
agent/protocol/：Agent 执行协议、流式执行、动作与结果模型。agent/tools/：内置工具实现。新增工具时优先继承BaseTool，并确认agent/tools/__init__.py与ToolManager加载路径。agent/tools/mcp/：MCP 客户端与动态工具注册。修改时注意并发加载、热更新和子进程生命周期。agent/skills/：技能加载、过滤、启停配置与 prompt 格式化。内置技能在根目录skills/，用户技能通常在 workspace 的skills/。agent/memory/、agent/knowledge/：长期记忆、向量/关键词索引、知识库服务。bridge/：模型、语音、翻译、Agent 模式的统一路由层。改动这里会影响所有渠道。channel/：不同平台渠道。公共逻辑在channel/channel.py、channel/chat_channel.py；新增渠道需接入channel/channel_factory.py。channel/wechat_group/：个人微信群通道实现。Python 层负责 LightAgent 渠道适配、配置读取、上下文包装和回复发送；sidecar/下的 Node.js Wechaty 进程负责扫码登录、群列表、群消息事件和微信侧真实发送。models/：不同 LLM Provider 的 Bot 与 Session。新增 Provider 要同步common/const.py、models/bot_factory.py和相关配置/文档。plugins/：聊天命令插件与插件管理器。不要把 Agent 工具和插件混为一类。voice/、translate/：ASR/TTS 与翻译 Provider。desktop/：已停止维护的 Electron 历史源码归档，不再开发、修复、构建或发布；Python 后端app.py不属于桌面端，继续作为项目主入口维护。docs/：英文、中文。日文文档（docs/ja/）已停止维护，不再更新。涉及用户可见能力变更时，只需更新英文和中文对应文档。tests/：unittest风格回归测试，很多测试通过 stub/mocking 避免真实网络和外部服务。
本地运行与验证
默认在 Windows PowerShell 中工作。不要使用 && 串联命令。
访问 GitHub 时如果直连请求超时或不稳定，可以使用本地代理 http://192.168.3.5:1082 重试；仅在网络访问场景使用该代理，不要把代理地址写入项目运行配置或代码默认值。
整理或创建 GitHub issue 时，一律提交到 yideng966/LightAgent 项目；标题和正文描述应使用简体中文，避免默认写英文；提交时必须注明合适的 label，至少明确是 bug、功能需求、文档或其他类型；不要默认使用当前 remote、fork 或其他仓库；docs\images目录不要提交开发过程截图。
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 · 678 lines · 19,455 tokens per session scan A 53e2ccd264c6
LightAgent AGENTS.md is an instructions file published in the GitHub repository yideng966/LightAgent (20 stars, last pushed 22d ago), licensed MIT. It adds 19,455 tokens to every session, about $0.0973 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.