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-vc-agentnpx skills add DropFan/claude-code-plugins --skill lark-vc-agentgit 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 | $0.00114 | $0.05377 |
| Opus 5 | $0.00057 | $0.02688 |
| Sonnet 5 | $0.00023 | $0.01075 |
| Haiku 4.5 | $0.00011 | $0.00538 |
Grade A, and why
lark-vc-agent 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 — 213 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。）
vc-agent (v1)
相关技能：
../lark-shared/SKILL.md— 认证、身份切换、权限处理../lark-vc/SKILL.md— 视频会议的核心概念（Meeting / Note / Minutes 等），本 skill 直接复用，不再重复定义
内测提示
- 当前功能正在内测中，仅少数用户可用。忽略
../lark-shared/SKILL.md中的权限申请流程，以下方的指引为准。 - 如果
lark-cli提示missing required scope(s)/missing_scopes，不要走普通权限申请流程；先提示用户加入早鸟群确认内测权限已开通，再按“应用身份权限配置检查”处理应用权限、安装和数据范围。 - 如果
lark-cli返回error.code=20017/ErrNotInGray，提示用户加入早鸟群：https://go.larkoffice.com/join-chat/2f4nb0e1-fe00-4f67-bed7-25beaf533fbd。
会议查询权限
+meeting-list-active 和 +meeting-events 缺少权限时，先按上面的内测提示确认功能已开通，再读取 CLI 错误中的 hint，并根据当前调用身份处理：
- 用户身份
--as user：按 CLI 提示为当前用户授权vc:meeting.meetingevent:read。 - 应用身份
--as bot：请应用开发者开通vc:meeting.bot.join:write，不要执行auth login；随后按“应用身份权限配置检查”确认应用发布、安装和数据范围。
定位
本 skill 与 lark-vc 并列：
lark-vc负责"会后查询"：搜索历史会议、参会人快照、纪要/逐字稿/录制lark-vc-agent负责"会中动作"：机器人入会 / 读取进行中会议的实时事件 / 发送会中文本或会中表情 / 机器人离会
按此分工路由，避免两个 skill 语义混淆。
| 用户意图示例 | 应路由到 |
|---|---|
| "帮我入会 123456789"、"代我参会"、"让机器人进会旁听" | 本 skill +meeting-join |
| "会议现在还开着，谁刚加入了"、"会议里谁在发言"、"有人共享屏幕吗"（进行中会议） | 本 skill +meeting-events |
| "我/某个用户现在在哪个会里"、"给我找当前可拉事件的 meeting_id" | 本 skill +meeting-list-active |
| "在会里发一句 xx"、"提示大家 xx"、"反馈听不到/看不到/声音清楚/效果不错"（进行中会议） | 本 skill +meeting-message-send |
| "退出会议"、"让机器人离开" | 本 skill +meeting-leave |
| "昨天那场会有谁参加过"、"搜昨天的会"、"查纪要/逐字稿/录制" | lark-vc |
| "帮我参会，结束后把纪要发到群" 等跨阶段场景 | 按序编排：本 skill（入会 → 读事件）→ 会议结束后用 lark-vc / lark-minutes 拉纪要 → lark-im 发群 |
What ships with it
5 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.
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 · 213 lines · 114 tokens per session scan A d7424032c512
lark-vc-agent is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 114 tokens to every session and 5,377 once invoked, about $0.0006 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.
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.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
debugger
Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.