lark-cli — security grade SAFE, quality 76/100

Security audit verdict: SAFE · quality 76/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by yjwong · Agent Tool · ★ 53

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is lark-cli safe to install? View the security audit →

About lark-cli

lark A CLI tool for interacting with Lark/Feishu APIs, designed for use with Claude Code and other AI assistants. Why This Tool? The official Lark MCP server exists, but its tools are not token-efficient. Each tool call returns verbose responses that consume significant context window space when used with AI assistants. This CLI addresses that by: Returning compact JSON - Structured output optimized for programmatic consumption Providing markdown conversion - Documents are converted to markdown (2-3x smaller than raw block structures) Supporting selective queries - Fetch only what you need (e.g., just event IDs, just document titles) The result: AI assistants can interact with Lark using fewer tokens, leaving more context for actual work.

ai-toolsclaudeclaude-codeclifeishulark

Quick Facts

Stars53
Forks18
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score75.6759184996073/100
Open Issues8
Last Updated2026-04-06
Created2026-01-14
Platformsclaude-code, cli, go
Est. Tokens~12k

Compatible Skills

These tools work well together with lark-cli for enhanced workflows:

  • feishu-claude-code — semantic(0.56)+complementary+rare_topics+similar_pop+shared_platform (64%)
  • skills — semantic(0.33)+complementary+rare_topics+similar_pop+shared_platform (56%)
  • hotplex — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (55%)

lark-cli alternative? Top 6 similar tools

Looking for a lark-cli alternative? If you're comparing lark-cli with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • feishu-claude-code by joewongjc · ⭐ 163

    Bridge Claude Code CLI with Feishu/Lark via WebSocket. 飞书 × Claude Code 实时对话。

  • cc-telegram-bridge by cloveric · ⭐ 121

    Run real local Codex, Claude Code, and Antigravity sessions from Telegram or Feishu/Lark; resume your work any

  • claude-feishu-channel by Blackman99 · ⭐ 50

    Bridge Claude Code sessions to a Feishu (Lark) bot

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • openmozi by oujingzhou · ⭐ 186

    轻量级的clawdbot/openclaw,支持飞书,钉钉,QQ和企业微信

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 An MCP server for conversation history search and retrieval in Claude Code

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is lark-cli?

lark-cli is A token-efficient CLI for Lark/Feishu APIs, designed for AI assistants like Claude Code. Supports calendar, contacts, documents, and messages.. It is categorized as a Agent Tool with 53 GitHub stars.

What programming language is lark-cli written in?

lark-cli is primarily written in Go. It covers topics such as ai-tools, claude, claude-code.

How do I install or use lark-cli?

You can find installation instructions and usage details in the lark-cli GitHub repository at github.com/yjwong/lark-cli. The project has 53 stars and 18 forks, indicating an active community.

What license does lark-cli use?

lark-cli is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to lark-cli?

The top alternatives to lark-cli on Agent Skills Hub include feishu-claude-code, cc-telegram-bridge, claude-feishu-channel. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools