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/dropfan/claude-code-plugins/lark-openapi-explorernpx skills add DropFan/claude-code-plugins --skill lark-openapi-explorergit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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 | $0.00076 | $0.01712 |
| Opus 5 | $0.00038 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
lark-openapi-explorer 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.
How it starts
The opening of the file, as written. The whole thing — 165 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。)
OpenAPI Explorer
前置条件: 先阅读
../lark-shared/SKILL.md了解认证、身份切换和安全规则。
当用户的需求无法被现有 skill 或 CLI 已注册 API 覆盖时,使用本技能从飞书官方 markdown 文档库中逐层挖掘原生 OpenAPI 接口,然后通过 lark-cli api 裸调完成任务。
文档库结构
飞书 OpenAPI 文档以 markdown 层级组织:
llms.txt ← 顶层索引,列出所有模块文档链接
└─ llms-<module>.txt ← 模块文档,包含功能概述 + 底层 API 文档链接
└─ <api-doc>.md ← 单个 API 的完整说明(方法/路径/参数/响应/错误码)
文档入口:
| 品牌 | 入口 URL |
|---|---|
| 飞书 (Feishu) | https://open.feishu.cn/llms.txt |
| Lark | https://open.larksuite.com/llms.txt |
所有文档以中文编写。如果用户使用英文交流,需将文档内容翻译为英文后输出。
挖掘流程
严格按以下步骤逐层检索,不要跳步或猜测 API:
Step 1:确认现有能力不足
# 先检查是否已有对应的 skill 或已注册 API
lark-cli <可能的service> --help
如果已有对应命令或 shortcut,直接使用,不需要继续挖掘。
Step 2:从顶层索引定位模块
用 WebFetch 获取顶层索引,找到与需求相关的模块文档链接:
WebFetch https://open.feishu.cn/llms.txt
→ 提取问题:"列出所有模块文档链接,找出与 <用户需求关键词> 相关的链接"
- 飞书品牌使用
open.feishu.cn - Lark 品牌使用
open.larksuite.com - 如不确定用户品牌,默认使用飞书
Step 3:从模块文档定位具体 API
用 WebFetch 获取模块文档,找到具体 API 的文档链接:
WebFetch https://open.feishu.cn/llms-docs/zh-CN/llms-<module>.txt
→ 提取问题:"找出与 <用户需求> 相关的 API 说明和文档链接"
Step 4:获取 API 完整规范
用 WebFetch 获取具体 API 文档,提取完整的调用规范:
WebFetch https://open.feishu.cn/document/server-docs/.../<api>.md
→ 提取问题:"返回完整 API 规范:HTTP 方法、URL 路径、路径参数、查询参数、请求体字段(名称/类型/必填/说明)、响应字段、所需权限、错误码"
Step 5:通过 CLI 调用 API
使用 lark-cli api 裸调:
# GET 请求
lark-cli api GET /open-apis/<path> --params '{"key":"value"}'
# POST 请求
lark-cli api POST /open-apis/<path> --data '{"key":"value"}'
# PUT 请求
lark-cli api PUT /open-apis/<path> --data '{"key":"value"}'
# DELETE 请求
lark-cli api DELETE /open-apis/<path>
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 · 165 lines · 76 tokens per session scan A ad33cc2a3966
lark-openapi-explorer is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 76 tokens to every session and 1,712 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
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.
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.
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…
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.
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.