Lark CLI is a command-line tool for using Lark/Feishu services such as messaging, documents, spreadsheets, calendars, mail, tasks, and meetings. It is intended for people and AI agents that need to work with these business tools through terminal commands.
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 skills/larksuite/cli/lark-meetingnpx skills add larksuite/cli --skill lark-meetinggit clone --depth 1 https://github.com/larksuite/cliWrote 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/cli/lark-meeting)<a href="https://agentmods.dev/skills/larksuite/cli/lark-meeting"><img src="https://agentmods.dev/badge/skills/larksuite/cli/lark-meeting.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 5.1 | $0.00118 | $0.03200 |
| Opus 5 | $0.00059 | $0.01600 |
| Sonnet 5 | $0.00024 | $0.00640 |
| Haiku 4.5 | $0.00012 | $0.00320 |
Grade A, and why
lark-meeting 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 6d 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
2 near-identical copies found in the catalogue:
- lark-meeting — 97% identical, 13 lines differ
- lark-meeting — 86% identical, 28 lines differ
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.
lark-meeting
飞书视频会议业务的统一入口，支持查询会议记录、实时会议互动、管理妙记、阅读智能纪要等操作。本技能负责领域关系、任务路由和跨命令编排。
无需预读 lark-shared 或预跑 auth status --verify，仅遇到未认证、token / 身份或 scope 错误时读取该 Skill，修复后重试。认证、身份或 scope 管理请求则直接使用该 Skill。
身份初始化与延续
把 source_identity 作为跨命令工作流的状态：
- 上下文已有来源身份：严格沿用。用户要求切换时先说明身份连续性和权限影响，不静默切换。
- 没有来源身份，用户明确指定身份：使用用户指定的
--as。 - 没有来源身份且用户未指定：操作语义明确要求应用机器人时使用
--as bot，否则显式使用--as user。
确定 source_identity 后，再检查目标命令是否支持该身份：
- 支持：显式传入并继续执行。
- 不支持：说明限制并停止；不要为了让命令成功而替换身份。
- 只有用户明确同意切换身份后，才以新身份重新开始一条工作流。
领域模型与概念
[会议来源]
Calendar 日程 (event_id) ──预约或关联──┐
即时会议（无 event_id）────────────────┴──► 会议 (meeting_id)
Calendar 日程 ──meeting_note────────────► Doc（用户纪要，独立于 AI 智能纪要）
[会议产物]
会议 (meeting_id)
├── AI 总结 ──► Note 智能纪要 (note_id)
│ ├── 智能纪要文档 ───────────► Doc (note_doc_token)
│ ├── 逐字稿
│ │ ├── normal ──────────► Doc (verbatim_doc_token)
│ │ └── unified ──────────► note +transcript（非独立 Doc）
│ └── 共享文档 ──────────────► Doc (shared_doc_tokens)
│
└── 录制 ──► Minutes 妙记 (minute_token)
├── AI 产物：Summary / Todo / Chapter / Keyword
├── Transcript（文字记录）
└── 原始音视频
本地音视频 ─────────────────────────────► Minutes 妙记 (minute_token)
| 对象 | 主标识 | 概念与关系 |
|---|---|---|
| Calendar 日程 | event_id |
日历上的日程，包含时间、参与人、会议室和 RSVP，可预约或关联 VC 会议；不是完整的会议记录。日程上的 meeting_note 是用户手工绑定的 Doc，与 AI 智能纪要无关。 |
| Meeting 会议 | meeting_id |
实际发生的视频会议，可以来自 Calendar，也可以是没有日程的即时会议。会议主题、时间、参会人快照和会中事件属于会议数据；Note 与 Minutes 是它可能关联的会后产物。 |
| Note 智能纪要 | note_id |
开启 AI 总结后形成的逻辑产物集合。note_display_type 决定获取逐字稿中文字记录的不同方式。 |
| Minutes 妙记 | minute_token |
由会议录制或本地音视频上传生成，包含总结、待办、章节、关键词、文字记录和原始音视频；可以关联 VC 会议，也可以独立存在。 |
| Doc 文档 | Doc token | 内容载体，不是会议标识。note_doc_token、shared_doc_tokens 和部分 verbatim_doc_token 指向 Doc；Doc token 不能当作 note_id 或 meeting_id。 |
核心标识
meeting_id：会议 ID。长数字字符串，不是 9 位会议号。meeting_no：会议号。9 位纯数字；CLI 参数名为--meeting-number。minute_token：妙记 Token。小写字母数字串，通常取自妙记 URL/minutes/<minute_token>。
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/lark-minutes-apply-permission.md 4.5 KB
- references/lark-minutes-detail.md 2.6 KB
- references/lark-minutes-download.md 5.8 KB
- references/lark-minutes-search.md 9.9 KB
- references/lark-minutes-speaker-replace.md 4.6 KB
- references/lark-minutes-summary.md 4.3 KB
- references/lark-minutes-todo.md 8.0 KB
- references/lark-minutes-update.md 980 B
- references/lark-minutes-upload.md 2.8 KB
- references/lark-note-detail.md 739 B
- references/lark-note-transcript.md 1.0 KB
- references/lark-vc-agent-meeting-end.md 959 B
- references/lark-vc-agent-meeting-invite.md 2.2 KB
- references/lark-vc-agent-meeting-join.md 6.2 KB
- references/lark-vc-agent-meeting-leave.md 3.3 KB
- references/lark-vc-detail.md 1.1 KB
- references/lark-vc-meeting-countdown.md 3.7 KB
- references/lark-vc-meeting-events.md 26 KB
- references/lark-vc-meeting-list-active.md 4.0 KB
- references/lark-vc-meeting-message-send.md 6.1 KB
- references/lark-vc-meeting-screenshot.md 1.7 KB
- references/lark-vc-recording.md 4.0 KB
- references/lark-vc-search.md 7.4 KB
- scenes/create-and-edit-minutes.md 10 KB
- scenes/live-meeting-attend.md 8.5 KB
- scenes/live-meeting-interact.md 6.5 KB
- scenes/query-meeting-and-artifacts.md 6.9 KB
- scenes/query-minutes-and-artifacts.md 4.1 KB
- scenes/query-note-and-artifacts.md 6.6 KB
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.
- 6d ago First seen · 151 lines · 118 tokens per session scan A 87664de707ed
lark-meeting is a skill published in the GitHub repository larksuite/cli (17,007 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 3,200 once invoked, about $0.0006 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 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…
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-drive
Google Drive operations through gog.
gog-save-attachments
Gmail attachment download and Google Drive archival with gog.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.