OpenClaw Lark/Feishu Plugin connects an OpenClaw agent to Lark or Feishu workspaces, allowing it to work with messages, documents, databases, spreadsheets, calendars, and tasks. It is for OpenClaw users who want their agent to read and update Lark/Feishu workspace data. The catalogue skills provide the agent workflows for operating those connected workspace features.
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 skills add larksuite/openclaw-lark --skill feishu-im-readgit clone --depth 1 https://github.com/larksuite/openclaw-larkWrote 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/skills/larksuite/openclaw-lark/feishu-im-read)<a href="https://agentmods.dev/skills/larksuite/openclaw-lark/feishu-im-read"><img src="https://agentmods.dev/badge/skills/larksuite/openclaw-lark/feishu-im-read/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/skills/larksuite/openclaw-lark/feishu-im-read"><img src="https://agentmods.dev/badge/skills/larksuite/openclaw-lark/feishu-im-read.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 | $0.00176 | $0.02190 |
| Opus 5 | $0.00088 | $0.01095 |
| Sonnet 5 | $0.00035 | $0.00438 |
| Haiku 4.5 | $0.00018 | $0.00219 |
Grade A, and why
feishu-im-read 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 10d 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.
This is a copy
95% identical to feishu-im-read — 11 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书 IM 消息读取
执行前必读
- 该 Skill 中的所有消息读取工具均以用户身份调用，只能读取用户有权限的会话
feishu_im_user_get_messages中open_id和chat_id必须二选一- 消息中出现
thread_id时，根据用户意图判断是否用feishu_im_user_get_thread_messages读取话题内回复 - 以用户身份读取后，如果消息内容中出现资源标记时，用
feishu_im_user_fetch_resource下载，需要message_id+file_key+type
快速索引：意图 → 工具
| 用户意图 | 工具 | 必填参数 | 常用可选 |
|---|---|---|---|
| 获取群聊/单聊历史消息 | feishu_im_user_get_messages | chat_id 或 open_id（二选一） | relative_time, start_time/end_time, page_size, sort_rule |
| 获取话题内回复消息 | feishu_im_user_get_thread_messages | thread_id（omt_xxx） | page_size, sort_rule |
| 跨会话搜索消息 | feishu_im_user_search_messages | 至少一个过滤条件 | query, sender_ids, chat_id, relative_time, start_time/end_time, page_size |
| 下载消息中的图片 | feishu_im_user_fetch_resource | message_id, file_key（img_xxx）, type="image" | - |
| 下载消息中的文件/音频/视频 | feishu_im_user_fetch_resource | message_id, file_key（file_xxx）, type="file" | - |
核心约束
1. 时间范围：确保消息覆盖完整
当用户没有明确指定时间范围时，根据用户意图推断合适的 relative_time，确保返回的消息能完整覆盖用户关心的内容。用户明确指定时间时直接使用用户的值。
2. 分页：根据需要翻页获取更多结果
page_size范围 1-50，默认 50- 返回结果中
has_more=true时，可使用page_token继续获取下一页 - 根据用户需求判断是否需要翻页：需要完整结果时继续翻页，浏览概览时第一页通常够用
3. 话题回复：主动展开话题获取上下文
获取历史消息时，返回的消息中如果包含 thread_id 字段，推荐主动获取话题的最新 10 条回复（page_size: 10, sort_rule: "create_time_desc"）以提供更完整的上下文。
| 场景 | 行为 |
|---|---|
| 获取历史消息并需要理解上下文（默认） | 对发现的 thread_id 调用 feishu_im_user_get_thread_messages 获取最新 10 条回复 |
| 用户要求"完整对话"、"详细讨论"、"看看回复" | 获取话题全部回复（page_size: 50, sort_rule: "create_time_asc"），需要时翻页 |
| 用户只浏览消息概览 / 用户明确说不看回复 | 跳过话题展开 |
注意：话题消息不支持时间过滤（飞书 API 限制），只能通过分页获取。
4. 跨会话消息搜索
feishu_im_user_search_messages 支持跨所有会话搜索消息：
| 参数 | 说明 |
|---|---|
query |
搜索关键词，匹配消息内容 |
sender_ids |
发送者 open_id 列表 |
chat_id |
限定搜索范围的会话 ID |
mention_ids |
被@用户的 open_id 列表 |
message_type |
消息类型：file / image / media |
sender_type |
发送者类型：user / bot / all（默认 user） |
chat_type |
会话类型：group / p2p |
搜索结果每条消息额外包含 chat_id、chat_type（p2p/group）、chat_name。单聊消息还有 chat_partner（对方 open_id 和名字）。
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.
- 10d ago First seen · 164 lines · 176 tokens per session scan A 8dba4d9fc35b
feishu-im-read is a skill published in the GitHub repository larksuite/openclaw-lark (2,374 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 2,190 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to feishu-im-read, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.