documents

A tool for reading and writing Lark documents, including text documents, spreadsheets, slides, and other Drive items. Lark is a workplace collaboration platform.

In plain words
What is it for?
Use it to search documents, list folder contents, read document content, create documents, or append text, headings, lists, and code.
Why use it?
It removes the need to open Lark manually when you need to find or update shared documents.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yjwong/lark-cli/documents
Any agent
npx skills add yjwong/lark-cli --skill documents
Clone the repo
git clone --depth 1 https://github.com/yjwong/lark-cli

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.04575
Opus 5 $0.00030 $0.02287
Sonnet 5 $0.00012 $0.00915
Haiku 4.5 $0.00006 $0.00458

Measured 2d ago against content hash 6beb3c9d12ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documents 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.

skills/documents/SKILL.md · 596 lines

How it starts

The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lark Documents Skill

Query and retrieve Lark document content via the lark CLI.

Running Commands

Ensure lark is in your PATH, or use the full path to the binary. Set the config directory if not using the default:

lark doc <command>
# Or with explicit config:
LARK_CONFIG_DIR=/Users/yingcong/Code/lark-cli/.lark lark doc <command>

Commands Reference

Search Documents

lark doc search <query> [--owner <user-id>] [--chat <chat-id>] [--type <doc-type>]

Searches for documents by keyword. Returns documents from Drive that match the query.

Options:

  • --owner: Filter by owner user ID (can be repeated)
  • --chat: Filter by chat ID where document is located (can be repeated)
  • --type: Filter by document type (can be repeated). Valid types: doc, sheet, slide, bitable, mindnote, file

Output:

{
  "query": "project plan",
  "results": [
    {
      "token": "doxcntan34DX4QoKJu7jJyabcef",
      "type": "docx",
      "title": "Q4 Project Plan",
      "owner_id": "ou_xxxx"
    }
  ],
  "total": 15,
  "count": 15
}

Note: Maximum 200 results can be returned per search.

List Folder Items

lark doc list [folder-token]

Lists items in a Lark Drive folder. If no folder token is provided, lists items in the root cloud space.

Output:

{
  "folder_token": "fldbcRho46N6MQ3mJkOAuPabcef",
  "items": [
    {
      "token": "doxcntan34DX4QoKJu7jJyabcef",
      "name": "My Document",
      "type": "docx",
      "parent_token": "fldbcRho46N6MQ3mJkOAuPabcef",
      "url": "https://larksuite.com/docx/doxcntan34DX4QoKJu7jJyabcef"
    }
  ],
  "count": 1
}

Item types: doc, docx, sheet, bitable, mindnote, file, folder, shortcut

For shortcuts, includes shortcut_info with target_type and target_token.

Download File from Drive

lark doc download <file_token> -o <output_path>

Downloads a file from Lark Drive. The file token is obtained from doc list or doc search output. Only files with type "file" can be downloaded (not docs, sheets, etc - those are Lark native formats).

Read the full file on GitHub · 596 lines

Changes

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.

  1. 2d ago First seen · 596 lines · 60 tokens per session scan A 6beb3c9d12ba

Subscribe to this mod's changes

documents is a skill published in the GitHub repository yjwong/lark-cli (53 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 4,575 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

larksnap-fetch

把飞书/Lark 文档或普通网页抓取并保存到本地,也能编辑用户有权限的飞书文档,并用已登录浏览器执行一次网页搜索。用户要求下载、导出、抓取、写入飞书文档,或联网搜索资料/参考链接时使用本技能,即使没有提到 larksnap。底层通过技能自带 daemon 桥接已登录的 larksnap 浏览器扩展;arXiv 使用独立脚本。.

AmbroseX/larksnap · 111 tokens

lark-sheets

飞书电子表格:创建和操作电子表格。支持创建表格、管理工作表与行列结构(增删/合并/调整尺寸/隐藏/冻结)、读写单元格(值/公式/样式/批注/单元格图片)、查找替换、多操作原子批量更新,以及图表、透视表、条件格式、筛选器、迷你图、浮动图片等对象的创建与维护。当用户需要创建电子表格、管理工作表、批量读写或编辑数据、统计汇总与可视化、表格美化、公式计算(含 Excel 公式迁移)、金融/财务建模(DCF、三张表、预算、Sensitivity 等)等任务时使用。若用户是想按名称或关键词搜索云空间(云盘/云存储)里的表格文件,请改用 lark-drive 的 larkdrivesearch 先定位资源。当用户给出 doubao.com 的…

ddpie/lark-mcp-on-agentcore · 260 tokens

lark-drive

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走…

ddpie/lark-mcp-on-agentcore · 192 tokens

lark-vc

飞书视频会议:搜索历史会议记录、查询会议纪要(总结/待办/章节/逐字稿)、查询参会人快照。当用户查询已结束的会议、获取会议产物(纪要/妙记)、查看参会人时使用;查询未来日程走 lark-calendar。不负责:Agent 真实入会/离会、会中实时事件(走 lark-vc-agent)。.

ddpie/lark-mcp-on-agentcore · 95 tokens

lark-minutes

飞书妙记:搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词。当给出minutetoken、本地音视频文件,要查/改/转妙记产物时使用;本地音视频转纪要/逐字稿优先走本 skill,不要用 ffmpeg/whisper 本地转写。不负责:获取会议关联妙记,或仅按自然语言标题定位纪要.

ddpie/lark-mcp-on-agentcore · 115 tokens

lark-slides

飞书幻灯片:创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面(创建、删除、读取、局部替换)。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时,也应直接使用本 skill,不要因为域名不是飞书而回退到 WebFetch;路由依据是 URL 路径模式和 token,而不是域名。不负责:云文档内容编辑(走 lark-doc)、云文档里的独立画板对象(走 lark-whiteboard,注意 slide 内嵌的流程图/架构图仍属本 skill)、上传或下载普通文件(走 lark-drive)。.

ddpie/lark-mcp-on-agentcore · 174 tokens