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/ethanqc/feishu-user-plugin/claude-mdgit clone --depth 1 https://github.com/EthanQC/feishu-user-pluginWrote 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/ethanqc/feishu-user-plugin/claude-md)<a href="https://agentmods.dev/instructions/ethanqc/feishu-user-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/ethanqc/feishu-user-plugin/claude-md.svg" alt="Measured on agentmods" 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 | $0.03356 | $0.03356 |
| Opus 5 | $0.01678 | $0.01678 |
| Sonnet 5 | $0.00671 | $0.00671 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade B, and why
feishu-user-plugin CLAUDE.md scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Codex**：TOML 配置在 `~/.codex/config.toml` mcp_servers This is a copy
98% identical to feishu-user-plugin AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
feishu-user-plugin — Claude Code 指令
本文件是 AI agent 与开发者在本仓内的核心指令。详细信息按需要查阅 docs/。
仓库是什么
All-in-one 飞书 plugin for Claude Code，覆盖三层鉴权：
- 用户身份（cookie 鉴权）：以你身份发送消息（text / image / file / post）
- 官方 API（应用凭证）：读群消息、操作 docs / tables / wiki / drive / contacts，上传文件
- 用户 OAuth UAT（user_access_token）：读 P2P 私聊历史，列用户所有 chat
85 个工具 + 9 个 MCP prompts。
MCP Prompts（v1.3.7+）
9 个 Claude Code skill 同时通过 prompts/list + prompts/get 暴露给 Codex / Cursor / OpenClaw / Windsurf。Prompt body 在 server 启动时从 skills/feishu-user-plugin/references/ 读。
| Prompt | 描述 |
|---|---|
/send |
以用户身份（非 bot）发消息 |
/reply |
读最近消息然后回复 |
/digest |
总结群或 P2P 最近消息 |
/search |
搜飞书联系人或群 |
/doc |
搜 / 读 / 创建飞书文档 |
/table |
操作飞书 Bitable（多维表格） |
/wiki |
搜 / 浏览飞书 Wiki 空间 |
/drive |
列文件 / 创建文件夹（飞书云空间） |
/status |
检查三层鉴权（cookie / app / UAT） |
每个 prompt 接受单一 arguments 自由文本（与 Claude Code skill 的 $ARGUMENTS 约定一致）。status 无参数。
工具大类（85 tools）
每个工具的具体参数说明在 MCP inputSchema.description（运行时可见）。工具列表 + 跨域 caveat + 用法 patterns 见 docs/TOOLS.md。
13 个工具大类的快速 sketch：
- 用户身份消息（cookie protobuf，8）：
send_to_user/send_to_group/send_as_user/send_image_as_user/send_file_as_user/send_post_as_user/send_card_as_user/batch_send - 用户身份联系人（cookie，5）：
search_contacts/create_p2p_chat/get_chat_info/get_user_info/get_login_status - UAT P2P 读取（2）：
read_p2p_messages/list_user_chats - 官方 API IM（16，含 v1.3.12
search_messages）、Docs（7）、Bitable（5）、Wiki（9）、Drive（4）、OKR（6）、Calendar（8）、Tasks v2（7） - 跨域 Uploads（3）：
upload_image/upload_file/upload_bitable_attachment - 插件层 多 profile（3）+ 实时事件（2）
必需环境变量
| 变量 | 用途 |
|---|---|
LARK_COOKIE |
用户身份发消息 |
LARK_APP_ID |
官方 API 访问 |
LARK_APP_SECRET |
官方 API 访问 |
LARK_USER_ACCESS_TOKEN |
P2P 读取 |
LARK_USER_REFRESH_TOKEN |
UAT 自动刷新 |
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.
- 5d ago First seen · 151 lines · 3,356 tokens per session scan B cff5a9f9342a
feishu-user-plugin CLAUDE.md is an instructions file published in the GitHub repository EthanQC/feishu-user-plugin (8 stars, last pushed 1mo ago), licensed MIT. It adds 3,356 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 98% identical to feishu-user-plugin AGENTS.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
botmux CLAUDE.md
Claude Code 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
AGENTS.md instructions for xvirobotics/metabot, covering metabot personal edition workspace, core cli, working principles, durable state and public boundary.
metabot CLAUDE.md
Claude Code 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.
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
larksnap CLAUDE.md
Claude Code 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.
nexu AGENTS.md
Instructions for nexu-io/nexu, covering agents.md, repo overview, project overview, commands and branch model.