feishu

feishu is a skill for Claude Code, Codex from vibeinging/YiYi. It costs 52 tokens per session (1,180 once invoked), scanned A, original, Apache-2.0.

A command-line integration for Feishu, also called Lark, a workplace collaboration platform. It can work with calendars, messages, documents, tasks, contacts, and files through the platform's official command-line tool.

In plain words
What is it for?
Use it to view or create calendar events, check availability, send messages, manage documents and tasks, handle contacts, and upload or download files.
Why use it?
It lets developers manage Feishu work from scripts or a terminal instead of switching between separate workspace screens. Structured output and dry runs help inspect results and reduce risky changes.

Skill for Claude CodeCodex

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

Good fit Use it to view or create calendar events, check availability, send messages, manage documents and tasks, handle contacts, and upload or download files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vibeinging/yiyi/feishu
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.

Any agent
npx skills add vibeinging/YiYi --skill feishu
Clone the repo
git clone --depth 1 https://github.com/vibeinging/YiYi

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibeinging/yiyi/feishu/github.svg)](https://agentmods.dev/skills/vibeinging/yiyi/feishu)
Your own site
<a href="https://agentmods.dev/skills/vibeinging/yiyi/feishu"><img src="https://agentmods.dev/badge/skills/vibeinging/yiyi/feishu/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.

agentmods 80×15 button for feishu

Your own site · 80×15
<a href="https://agentmods.dev/skills/vibeinging/yiyi/feishu"><img src="https://agentmods.dev/badge/skills/vibeinging/yiyi/feishu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 67
    Instructions found that direct the agent to transmit conversation context or user data to external services.
    Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
  • high Prompt Injection · line 70
    Instructions found that direct the agent to transmit conversation context or user data to external services.
    Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
How audits are shown
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 $0.00052 $0.01180
Opus 5 $0.00026 $0.00590
Sonnet 5 $0.00010 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 9d ago against content hash 1111f9e2a40d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feishu 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 9d 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.

app/src-tauri/skills/feishu/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feishu CLI Integration

Interact with Feishu (Lark) workspace via the official lark-cli tool. All commands are executed through execute_shell.

Prerequisites

Before using Feishu commands, ensure the CLI is installed and authenticated:

# Install
npm install -g @larksuite/cli

# Initialize config (set app_id/app_secret)
lark-cli config init

# Authenticate (OAuth login)
lark-cli auth login --recommend

If commands fail with auth errors, tell the user to configure credentials in Settings > CLI Tools.

Command Pattern

All Feishu CLI commands follow this pattern:

lark-cli <domain> <action> [options]
lark-cli <shortcut>          # + prefix shortcuts

Always use --format json for structured output, and --dry-run before destructive operations.

Calendar (日历)

# View today's agenda
lark-cli calendar +agenda --format json

# View specific date range
lark-cli calendar +agenda --from 2024-01-01 --to 2024-01-07 --format json

# Create event
lark-cli calendar +create-event --summary "Meeting" --start "2024-01-15T10:00:00" --end "2024-01-15T11:00:00"

# Check free/busy
lark-cli calendar +free-busy --from "2024-01-15T09:00:00" --to "2024-01-15T18:00:00" --format json

# List calendars
lark-cli calendar list --format json

Messenger (消息)

# Send message to a user
lark-cli message send --receive-id "user_id" --msg-type text --content '{"text":"Hello"}'

# Send message to a group
lark-cli message send --receive-id "chat_id" --receive-id-type chat --msg-type text --content '{"text":"Hello"}'

# List recent messages in a chat
lark-cli message list --chat-id "chat_id" --format json

Docs (文档)

# Create a new document
lark-cli doc create --title "My Document" --format json

# Get document content
lark-cli doc get --document-id "doc_id" --format json

# Update document
lark-cli doc update --document-id "doc_id" --content '{"body":{"content":[]}}'

Drive (云盘)

# Upload file
lark-cli drive upload --local-path "/path/to/file.pdf" --parent-node "folder_id"

# Download file
lark-cli drive download --file-token "file_token" --local-path "/path/to/save/"

# List folder contents
lark-cli drive list --folder-token "folder_token" --format json

Read the full file on GitHub · 172 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. 9d ago First seen · 172 lines · 52 tokens per session scan A 1111f9e2a40d

Subscribe to this mod's changes

feishu is a skill published in the GitHub repository vibeinging/YiYi (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,180 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.