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/foxzool/openlark/agents-mdgit clone --depth 1 https://github.com/foxzool/openlarkWhat 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 | $0.02416 | $0.02416 |
| Opus 5 | $0.01208 | $0.01208 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
openlark 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLark Knowledge Base
Project: OpenLark - 飞书开放平台 Rust SDK
Stack: Rust, Tokio, Reqwest, WebSocket
Version: 0.20.0
Repository: https://github.com/foxzool/openlark
OVERVIEW
OpenLark 是为飞书(Feishu/Lark)开放平台构建的企业级 Rust SDK,提供 1,560+ 个 API 的类型安全访问。采用模块化架构设计,支持按需编译和功能组合。
STRUCTURE
.
├── crates/ # 18 个业务模块 crates
│ ├── openlark-core/ # 核心基础设施(HTTP、错误处理)
│ ├── openlark-client/ # 高级客户端(meta 链式入口)
│ ├── lark-websocket-protobuf/ # WebSocket protobuf 协议(预生成源码)
│ ├── openlark-auth/ # 认证服务
│ ├── openlark-communication/ # IM 消息和联系人
│ ├── openlark-docs/ # 云文档和表格(158 APIs)
│ ├── openlark-hr/ # HR 和招聘(562 APIs)
│ ├── openlark-workflow/ # 任务和审批
│ ├── openlark-meeting/ # 视频会议
│ └── ... (其他业务模块)
├── src/ # 根 crate 导出
├── examples/ # 使用示例
├── tests/ # 集成测试
└── tools/ # 开发和维护脚本
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| 添加新 API | crates/openlark-*/src/**/v*/ |
按业务模块和版本组织 |
| 错误处理 | crates/openlark-core/src/error/ |
CoreError 企业级错误系统 |
| HTTP 客户端 | crates/openlark-core/src/http.rs |
共享 reqwest 配置 |
| 模型定义 | */models.rs 或 */models/ |
Serde 序列化结构体 |
| Feature flags | Cargo.toml [features] |
50+ 功能标志 |
CONVENTIONS
模块组织
- 业务领域驱动: 按功能(HR/Docs/IM)而非技术层次组织
- 版本化 API:
v1/,v2/子目录管理不同 API 版本 - 模型分离: 请求/响应模型放在
models/或models.rs
代码风格
- 中文优先: 文档和注释使用中文,面向中国开发者
- Builder 模式: API 请求使用流畅的构建器模式
- Feature 条件编译:
#[cfg(feature = "...")]控制模块编译 - 错误处理: 统一使用
CoreError,支持链式错误上下文
API 实现模式
// 1. 定义请求结构体(Builder 模式)
pub struct CreateXxxRequest { config: Config, ... }
impl CreateXxxRequest {
pub fn new(config: Config) -> Self { ... }
pub fn field(mut self, value: T) -> Self { ... }
pub async fn execute(self) -> Result<XxxResponse> { ... }
}
// 2. 模型使用 Serde
#[derive(Debug, Serialize, Deserialize)]
pub struct XxxResponse { ... }
// 3. 验证使用宏
validate_required!(self.field, "字段不能为空");
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 · 162 lines · 2,416 tokens per session scan A e48241638649
openlark AGENTS.md is an instructions file published in the GitHub repository foxzool/openlark (105 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,416 tokens to every session, about $0.0121 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
botmux CLAUDE.md
Instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules:共享还是独立(改前必读) and 编译态(单文件二进制)注意.
metabot AGENTS.md
Instructions for xvirobotics/metabot, covering metabot personal edition workspace, core cli, working principles, durable state and public boundary.
metabot CLAUDE.md
Instructions for xvirobotics/metabot: The canonical project instructions are in AGENTS.md. Follow that file for this repository. This compatibility file exists for Claude Code; MetaBot install/update does not deploy or replace workspace instruction files.
larksnap CLAUDE.md
Instructions for AmbroseX/larksnap, covering 基本约定, plan 文件管理, 开发规范, 根据场景动态调整顺序 and 文档写入.
Claude-to-IM-skill CLAUDE.md
Instructions for op7418/Claude-to-IM-skill, covering claude.md — project guidelines for claude-to-im-skill and replying to github issues.
lark-mcp-on-agentcore AGENTS.md
AGENTS.md instructions for ddpie/lark-mcp-on-agentcore, covering agents.md, project overview, setup & commands, project structure and code style.