A tool for using Feishu instant messaging and group chats. It works with messages, replies, threads, files, reactions, bookmarks, members, and interactive message cards.

Use it to send or search messages, reply in threads, download files, manage group members and chats, add reactions or bookmarks, and process interactive card actions.

It brings chat operations into the coding agent while keeping messages, files, group management, and card interactions in one workflow. It can handle both one-to-one and group conversations.

lark-im — Skill by DropFan

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/dropfan/claude-code-plugins/lark-im

Any agent

npx skills add DropFan/claude-code-plugins --skill lark-im

Clone the repo

git clone --depth 1 https://github.com/DropFan/claude-code-plugins

Made for: Claude Code, Codex.

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,713 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 88% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00147	$0.05713
Opus 5	$0.00073	$0.02857
Sonnet 5	$0.00029	$0.01143
Haiku 4.5	$0.00015	$0.00571

Measured 2d ago against content hash 66d872929fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lark-im 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.

Origin

This is a copy

88% identical to lark-im — 52 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/lark/skills/lark-im/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ Cowork / Claude Desktop 执行环境说明（自动注入）

本技能依赖本地 lark-cli（@larksuite/cli，可用 command -v lark-cli 定位）及其 ~/.lark-cli 登录态（应用密钥存于 macOS keychain）。

在 Cowork 中运行任何 lark-cli 命令时，必须在本地 macOS 上执行（使用 Desktop Commander 的 start_process / interact_with_process，或其它本地 shell 工具），不要用隔离的 Linux 沙箱 mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。执行前确保 npm 全局 bin 目录（npm prefix -g 输出目录下的 bin）在 PATH 中。

（在 Claude Code 中可忽略本说明，lark-cli 在本机 shell 直接可用。）

im (v1)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md，其中包含认证、权限处理

Core Concepts

Message: A single message in a chat, identified by message_id (om_xxx). Supports types: text, post, image, file, audio, video, sticker, interactive (card), share_chat, share_user, merge_forward, etc.
Chat: A group chat or P2P conversation, identified by chat_id (oc_xxx).
Thread: A reply thread under a message, identified by thread_id (om_xxx or omt_xxx).
Reaction: An emoji reaction on a message.
Flag: A bookmark on a message or thread.
Feed Shortcut: A chat pinned to the current user's feed sidebar, identified by feed_card_id (an oc_xxx open_chat_id for CHAT type).
Feed Group: A tag that groups feed cards in the feed list, identified by feed_group_id (ofg_xxx). Members are feed cards, each identified by feed_id + feed_type. Two types: normal (members managed explicitly) and rule (members auto-derived from rules).

Resource Relationships

Chat (oc_xxx)
├── Message (om_xxx)
│   ├── Thread (reply thread)
│   ├── Reaction (emoji)
│   └── Resource (image / file / video / audio)
└── Member (user / bot)

Important Notes

Identity and Token Mapping

--as user means user identity and uses user_access_token. Calls run as the authorized end user, so permissions depend on both the app scopes and that user's own access to the target chat/message/resource.
--as bot means bot identity and uses tenant_access_token. Calls run as the app bot, so behavior depends on the bot's membership, app visibility, availability range, and bot-specific scopes.
If an IM API says it supports both user and bot, the token type changes who the operator is. The same API can succeed with one identity and fail with the other because owner/admin status, chat membership, tenant boundary, or app availability are checked against the current caller.

Read the full file on GitHub · 261 lines

Files

What ships with it

58 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.

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.

2d ago First seen · 261 lines · 147 tokens per session scan A 66d872929fff

Subscribe to this mod's changes

lark-im is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 147 tokens to every session and 5,713 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to lark-im, differing in 52 lines, and is treated as a copy.

Code review Research ai-coding ai-coding-assistant claude-code claude-code-plugins claude-code-plugins-marketplace claude-code-skills

auto-loop

TDD-based autonomous development loop with checkpoint recovery and observability changelog.

claude-world/director-mode-lite · 17 tokens

hook-template

Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.

claude-world/director-mode-lite · 39 tokens

agent-check

Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.

claude-world/director-mode-lite · 32 tokens

session-relay

Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…

claude-world/director-mode-lite · 82 tokens

skill-check

Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.

claude-world/director-mode-lite · 35 tokens

skill-template

Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.

claude-world/director-mode-lite · 34 tokens