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.
npx agentmods add skills/yjwong/lark-cli/messagesnpx skills add yjwong/lark-cli --skill messagesgit clone --depth 1 https://github.com/yjwong/lark-cliWrote 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.
[](https://agentmods.dev/skills/yjwong/lark-cli/messages)<a href="https://agentmods.dev/skills/yjwong/lark-cli/messages"><img src="https://agentmods.dev/badge/skills/yjwong/lark-cli/messages.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00068 | $0.02523 |
| Opus 5 | $0.00034 | $0.01262 |
| Sonnet 5 | $0.00014 | $0.00505 |
| Haiku 4.5 | $0.00007 | $0.00252 |
Grade A, and why
messages 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Messages Skill
Retrieve chat message history, send messages, manage reactions, and search for chats/groups via the lark CLI.
🤖 Capabilities and Use Cases
- Send markdown-lite messages with links and mentions
- Send images with
--imageand{{image}}placement - Reply to messages and threads with
--parent-id/--root-id - Message recall/delete for cleanup
- Add/list/remove emoji reactions
- Browse emoji catalog reference
- Read chat history (chat or thread)
- Download message resources (images/files/audio/video)
- Find chats by name or member
- Use clear, flag-based CLI with consistent JSON output
🚀 Quick Reference
Send message:
lark msg send --to [email protected] --text "Hello!"
Reply in thread:
lark msg send --to oc_12345 --parent-id om_abcdef --msg-type text --text "Replying here"
Read messages:
lark msg history --chat-id oc_12345 --limit 10
Find chats:
lark chat search "project team"
React / list / remove reaction:
lark msg react --message-id om_123456789abcdef --reaction SMILE
lark msg react list --message-id om_123456789abcdef
lark msg react remove --message-id om_123456789abcdef --reaction-id ZCaCIjUBVVWSrm5L-3ZTw...
Download resource:
lark msg resource --message-id om_xxx --file-key img_v3_xxx --type image --output ./image.png
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 msg <command>
lark chat <command>
# Or with explicit config:
LARK_CONFIG_DIR=/path/to/.lark lark msg <command>
Commands Reference
Search for Chats/Groups
lark chat search "project" --limit 10
Available flags:
--limit: Maximum number of chats to retrieve (0 = no limit)
Output fields include:
chats[]withchat_id,name,description,owner_id,external,chat_statuscount,query
Send Messages
Send messages to users or group chats as the bot.
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.
- 4d ago First seen · 330 lines · 68 tokens per session scan A a6c21c70e9d8
messages is a skill published in the GitHub repository yjwong/lark-cli (53 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 2,523 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.
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。.
openlark-api
OpenLark 项目 API 接口实现规范（速查）。用于添加/重构飞书开放平台 API：确定落盘路径、实现 Body/Response + Builder(Request)、对齐 endpoints 常量/enum、补齐 mod.rs 导出，并明确"调用服务端 API"的方法签名/RequestOption 传递约定。触发关键词：API 接口、API 文件、飞书 API、添加 API、调用服务端 API.
openlark-api-field-verify
OpenLark API 字段核对技能。用于新增/重构飞书 API 后，核对 Rust 实现的请求体/响应体字段是否与飞书官方文档一致。通过 playwright 渲染飞书 SPA 文档页面，提取真实的请求/响应字段定义，对比代码实现找出不符项。触发关键词：字段核对、字段验证、字段不符、文档核对、核对请求字段、核对响应字段、飞书文档字段、推断字段、user 级接口、用户级接口字段.
openlark-design-review
OpenLark Rust SDK 的代码设计/公共 API 规范审查技能（面向 crate/模块）。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制，并输出按优先级排序的整改清单与可落地改造方案。触发关键词：设计审查、crate 设计、API 设计、public API、feature flag、端点、Builder/Service、架构一致性.
openlark-naming
OpenLark Rust SDK 命名与对外 API 表达规范（Client/Service/Resource/Request/Builder）。用于新增/重构公开类型、设计 meta 调用链、调整模块导出与 prelude、或排查 Service 同名/语义错配/V{N}Service 版本层错位、Resource 与 Service 同类型两名、以及 Client/Service/Resource 调用风格不一致的问题。触发关键词：命名规范、Client vs Service、Resource、重命名、V1Service 版本层、meta 调用链、公开 API.
openlark-api-validation
OpenLark API 覆盖率验证技能。用于验证各 crate 的 API 实现数量与覆盖率，基于 tools/validateapis.py 脚本和 apilistexport.csv 对比实际代码实现。触发关键词：API 验证、API 覆盖率、验证 API 数量、检查 API 实现、API 统计.