feishu-tools

feishu-tools is a skill for Claude Code, Codex from ThinkInAIXYZ/deepchat. It costs 29 tokens per session (562 once invoked), scanned A, original, Apache-2.0.

A tool guide for working with Feishu, also called Lark, a workplace platform with documents, spreadsheets, and knowledge content. It tells an agent when and how to use the available Feishu workspace tools.

In plain words
What is it for?
Use it to read, search, summarize, create, update, append to, or organize Feishu documents and spreadsheets.
Why use it?
It helps an agent handle Feishu content through the connected workspace instead of treating it like ordinary local files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

DeepChat is an open-source desktop client for AI agents that keeps user data local first and connects agents with services such as MCP, Skills, ACP, and messaging apps. It is for people who want to use and control AI assistants from a desktop application. The catalogue add-ons extend DeepChat’s agent workflows.

ThinkInAIXYZ/deepchat · 6,309 stars · on GitHub · deepchat.thinkinai.xyz

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/thinkinaixyz/deepchat/feishu-tools
Any agent
npx skills add ThinkInAIXYZ/deepchat --skill feishu-tools
Clone the repo
git clone --depth 1 https://github.com/ThinkInAIXYZ/deepchat

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for feishu-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/feishu-tools.svg)](https://agentmods.dev/skills/thinkinaixyz/deepchat/feishu-tools)
Your own site
<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/feishu-tools"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/feishu-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 562 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 5.1 $0.00029 $0.00562
Opus 5 $0.00015 $0.00281
Sonnet 5 $0.00006 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 6d ago against content hash 6b3a59bcb6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feishu-tools 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.

plugins/feishu/skills/feishu-tools/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

feishu-tools

This plugin is an MCP server tool surface exposed by DeepChat's Feishu plugin. Do not ask the user to classify the plugin as an MCP server, a CLI tool, or another plugin type. When a request is about Feishu/Lark content and matching tools are available, invoke the relevant tool directly.

Runtime Context

  • Plugin id: ${OWNER_PLUGIN_ID}.
  • Plugin root: ${PLUGIN_ROOT}.
  • Server id: feishu-tools.

When To Use

  • The user asks to read, summarize, search, create, update, append to, or organize Feishu/Lark documents.
  • The user asks to inspect or edit Feishu/Lark spreadsheets, sheets, tables, or similar structured workspace data.
  • The user asks to operate on another Feishu/Lark artifact and the current tool list exposes a matching tool by name or description.

Required Behavior

  1. Treat the currently exposed feishu-tools MCP tools as the primary action surface for Feishu/Lark requests.
  2. Use the live tool names and descriptions in the current session as the source of truth for what the server supports.
  3. Prefer the matching tool directly instead of asking the user how to call the plugin or what kind of plugin it is.
  4. When the user provides a Feishu/Lark URL, extract the relevant document, sheet, spreadsheet, or workspace identifier when the target tool expects an id or token.
  5. For write operations that could overwrite or append content, confirm intent only when the target artifact or requested mutation is ambiguous or destructive.
  6. If the requested operation has no matching currently exposed tool, explain that the active Feishu preset may not include it and describe the gap.
  7. If a tool call returns an authentication or configuration error, tell the user to open the Feishu plugin settings and verify App ID, App Secret, brand, and preset.

Routing Hints

  • For documents, prefer tools whose names or descriptions reference docs, docx, wiki, or knowledge.
  • For spreadsheets or tables, prefer tools whose names or descriptions reference sheets, spreadsheets, tables, or bitable-like structures.
  • For task, calendar, or IM requests, prefer the matching domain-specific Feishu/Lark tools when they are exposed by the current preset.

Read the full file on GitHub · 55 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. 6d ago First seen · 55 lines · 29 tokens per session scan A 6b3a59bcb6d6

Subscribe to this mod's changes

feishu-tools is a skill published in the GitHub repository ThinkInAIXYZ/deepchat (6,309 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 562 once invoked, about $0.0001 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

aetox-audit-xls

ตรวจเวิร์กบุ๊กที่คนอื่นทำมา ก่อนเชื่อตัวเลขในนั้นหรือส่งต่อให้ใครใช้ หา error, ค่าคงที่ฝังในสูตร, สูตรที่หลุดแพตเทิร์น, ช่วง SUM ที่ขาดแถว, สูตรที่ถูกวางทับด้วยค่า และงบที่ไม่บาลานซ์.

Mikedev115/Aetox · 83 tokens

aetox-clean-data-xls

ล้างข้อมูลที่เละก่อนเอาไปคำนวณ รวมยอด หรือ pivot ช่องว่างหัวท้าย ตัวพิมพ์ไม่ตรงกัน ตัวเลขที่ถูกเก็บเป็นข้อความ วันที่คนละฟอร์แมตในคอลัมน์เดียว แถวซ้ำ และตัวอักษรเพี้ยน.

Mikedev115/Aetox · 72 tokens

dcf-model

Build discounted cash flow valuation workbooks in Excel.

NousResearch/hermes-agent · 14 tokens

comps-analysis

Build comparable-company valuation workbooks in Excel.

NousResearch/hermes-agent · 13 tokens

lbo-model

Build leveraged buyout workbooks with IRR/MOIC in Excel.

NousResearch/hermes-agent · 19 tokens

google-workspace

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

NousResearch/hermes-agent · 21 tokens