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-notenpx skills add DropFan/claude-code-plugins --skill lark-notegit 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 | $0.00086 | $0.01926 |
| Opus 5 | $0.00043 | $0.00963 |
| Sonnet 5 | $0.00017 | $0.00385 |
| Haiku 4.5 | $0.00009 | $0.00193 |
Grade A, and why
lark-note 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 yesterday.
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 — 106 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。）
note (v1)
身份：仅使用 --as user。使用前阅读 ../lark-shared/SKILL.md。
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-vc/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
Note 域只接受显式 note_id：用户直接提供，或 docs +fetch 返回的 <vc-transcribe-tab vc-node-id="..."> 中的 vc-node-id。不要从 doc_token、标题、正文或 backlink 反推 note_id。
命令路由
| 用户表达 / 上下文 | 路由 |
|---|---|
已知 note_id，查纪要类型 / 文档 token |
note +detail --note-id NOTE_ID |
docs +fetch 返回 <vc-transcribe-tab vc-node-id="..."> |
取 vc-node-id 作为 NOTE_ID，先 note +detail --note-id NOTE_ID |
只持有 meeting_id |
先 vc +detail --meeting-ids <id> 拿 note_id，再 note +detail --note-id NOTE_ID |
只持有 minute_token（妙记 URL） |
先 minutes +detail --minute-tokens <token> 顶层取 note_id，再 note +detail --note-id NOTE_ID（不要把 minute_token 当 note_id） |
只持有日程 event_id |
先 calendar +meeting --event-ids <id> 拿 meeting_id，再按上一行继续 |
已知 note_id，读纪要正文 |
note +detail → docs +fetch --doc <note_doc_token> |
已知 note_id，查 unified 原始记录 / 逐字稿 |
note +transcript --note-id NOTE_ID |
| 只有自然语言纪要标题，用户要逐字稿 / 原始记录 / 谁说了什么 | 不进本 skill；先走文档搜索与 docs +fetch，拿到 vc-node-id 后再回来 |
note_display_type 路由
note +detail 结果 |
用户要逐字稿 / 原始记录时 |
|---|---|
normal + verbatim_doc_token 非空 |
docs +fetch --doc <verbatim_doc_token> |
unknown + verbatim_doc_token 非空 |
先按独立文档处理；不要猜成 unified |
unknown + 无逐字稿 token |
停止重试并说明无法确定逐字稿入口 |
unified |
note +transcript --note-id <note_id> |
What ships with it
2 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.
- yesterday First seen · 106 lines · 86 tokens per session scan A f10a8db78a0c
lark-note is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 86 tokens to every session and 1,926 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.
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.
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.
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.
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…