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-vcnpx skills add DropFan/claude-code-plugins --skill lark-vcgit 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 | $0.00095 | $0.04668 |
| Opus 5 | $0.00048 | $0.02334 |
| Sonnet 5 | $0.00019 | $0.00934 |
| Haiku 4.5 | $0.00010 | $0.00467 |
Grade A, and why
lark-vc 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 — 217 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 (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
CRITICAL — 开始前 MUST 先用 Read 工具读取 references/vc-domain-boundaries.md，不读将导致命令使用、会议产物决策、领域边界职责判断错误：
- 了解日历 & VC、会议产物 & 文档的关联关系和职责划分
- 了解会议产物（妙记和纪要）之间的关联关系，例如：妙记和纪要产生条件相互独立
- 了解不同会议产物的组成部分，以便根据需求决策使用哪种产物的数据
- 了解会议总结、分析和信息提取的标准流程
身份
所有 vc 命令默认使用 --as user。+search 和 meeting get 也支持 --as bot。
# BAD — 查昨天的会议用 calendar，会漏掉即时会议
lark-cli calendar +search-event --query "站会" --start <start_time> --end <end_time>
# GOOD — 查已结束的会议用 vc +search
lark-cli vc +search --query "站会" --start <start_time> --end <end_time>
Shortcuts （推荐优先使用）
| Shortcut | 说明 |
|---|---|
+search |
搜索历史会议记录（需至关键词、时间范围、组织者、参与者、会议室少一个筛选条件） |
+detail |
通过 meeting-ids 获取会议详情，包括 note_id 和 minute_token |
+recording |
通过 meeting-ids 或 calendar-event-ids 查询 minute_token |
- 使用任何 Shortcut 前，必须先读其对应 reference 文档。
意图路由
| 用户意图 | 路由到 |
|---|---|
| 查"昨天的会议""上周的会""已结束的会议" | 本 skill（+search，含即时会议） |
| 查日历/日程或未来时间的会议 | lark-calendar |
| 查"今天有哪些会议" | vc +search（已结束）+ lark-calendar（未开始），合并展示 |
| 只按自然语言标题查"xx 纪要的逐字稿 / 原始记录 / 谁说了什么" | 先到 lark-drive / lark-doc；仅在已拿到 note_id / vc-node-id 后再到 lark-note |
| Agent 真实入会/离会、会中实时事件 | lark-vc-agent |
| 妙记信息/时长/封面/链接 | 先走 vc +detail 或 vc +recording 获取 minute_token，再用 lark-minutes 的 minutes get |
| 本地音视频文件转纪要/逐字稿 | 先走 lark-minutes 上传，再用 minutes +detail --minute-tokens |
What ships with it
4 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 · 217 lines · 95 tokens per session scan A a0c3113e271d
lark-vc is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 95 tokens to every session and 4,668 once invoked, about $0.0005 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.