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 skills add DropFan/claude-code-plugins --skill lark-docgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWrote 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/dropfan/claude-code-plugins/lark-doc)<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-doc"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-doc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-doc"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-doc.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00124 | $0.01351 |
| Opus 5.5 | $0.00050 | $0.00540 |
| Sonnet 5.5 | $0.00025 | $0.00270 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
lark-doc 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 25d 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.
This is a copy
95% identical to lark-doc — 98 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 61 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。）
docs
场景与 Shortcut 路由
CRITICAL：先判断场景，再读取该场景的参考文件；不要在任务开始时一次性读取全部参考文件。每个文件只在首次进入对应阶段时读取一次。
身份：文档操作推荐显式指定 --as user。
本地文件引用统一遵循文件访问权限：CWD 内优先使用 @./相对路径，其他目录使用 @绝对路径。XML 内的相对资源路径先查 CWD；仅文件不存在时再查源 XML 文件所在目录，同名文件以 CWD 为准。内联内容、stdin、在线文档没有源文件目录，不执行回退。
文档内容
- 读取 / 摘要 —
+fetch：先读参考再获取文档。 - 从零创作 —
创建工作流：先完整执行创建工作流，简单任务不是跳过的理由； - 导入 / 空文档 —
+create：仅创建空文档或原样导入用户提供的完整内容时，跳过创建工作流。 - 编辑 / block 直达链接 —
+update：语义改写、润色、重组、补写或排版均按 update 参考完成。
辅助能力
- 草稿初始化、解析与统计 —
+script：支持解析文档 URL / token 与本地 XML，统计字数并返回字符诊断；不支持 Markdown 输入。 - 历史版本 —
+history-list/+history-revert/+history-revert-status：查询、回滚文档历史版本或检查回滚任务状态。
资源、画板与思维笔记
- 插入本地素材 —
+media-insert：在文末插入本地图片或文件。 - 预览素材 —
+media-preview：预览文档或评论中的图片、附件或素材。 - 下载素材 —
+media-download：下载文档中的图片、附件、素材或画板缩略图。 - Docx 封面 —
+resource-download/+resource-update/+resource-delete：下载、更新或删除 Docx 封面。 - 画板 —
画板工作流：创建或更新画板时先读取工作流；更新已有画板必须复用现有 token，禁止新建空白画板；使用whiteboard +update写入。 - 思维笔记 —
mindnotes：已有思维笔记走思维笔记链路；新建思维笔记走lark-doc-whiteboard。
What ships with it
43 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.
- references/genres/business-analysis.md 3.1 KB
- references/genres/data-report.md 2.9 KB
- references/genres/email.md 4.0 KB
- references/genres/execution-plan.md 2.9 KB
- references/genres/formal-doc.md 4.4 KB
- references/genres/meeting-minutes.md 2.3 KB
- references/genres/memo-brief.md 2.0 KB
- references/genres/official-redhead.md 6.1 KB
- references/genres/prd.md 2.5 KB
- references/genres/proposal.md 2.1 KB
- references/genres/research-report.md 3.2 KB
- references/genres/retrospective.md 2.4 KB
- references/genres/route-consumer.md 3.8 KB
- references/genres/route-creative.md 3.6 KB
- references/genres/route-knowledge.md 4.7 KB
- references/genres/route-marketing.md 4.2 KB
- references/genres/route-media.md 3.7 KB
- references/genres/route-opinion.md 3.6 KB
- references/genres/route-personal-brand.md 3.4 KB
- references/genres/route-platform.md 639 B
- references/genres/route-report.md 1.2 KB
- references/genres/route-workplace.md 2.8 KB
- references/genres/sop-tutorial.md 4.0 KB
- references/genres/technical-doc.md 3.5 KB
- references/genres/wechat.md 3.9 KB
- references/genres/weekly-report.md 2.0 KB
- references/genres/white-paper.md 3.1 KB
- references/genres/xiaohongshu.md 3.2 KB
- references/lark-doc-create-workflow.md 9.3 KB
- references/lark-doc-create.md 3.2 KB
- references/lark-doc-fetch.md 7.8 KB
- references/lark-doc-history.md 5.4 KB
- references/lark-doc-md.md 5.8 KB
- references/lark-doc-media-download.md 2.2 KB
- references/lark-doc-media-insert.md 6.8 KB
- references/lark-doc-media-preview.md 1.6 KB
- references/lark-doc-mindnote.md 5.4 KB
- references/lark-doc-resource-cover.md 4.1 KB
- references/lark-doc-script.md 5.1 KB
- references/lark-doc-update.md 7.3 KB
- references/lark-doc-whiteboard.md 8.7 KB
- references/lark-doc-xml-extended-blocks.md 4.3 KB
- references/lark-doc-xml.md 5.3 KB
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.
- 25d ago Changed · -36 lines · -38 tokens per session 697893168dfb
- 1mo ago First seen · 97 lines · 162 tokens per session scan A 166f8adbfdc7
lark-doc is a skill published in the GitHub repository DropFan/claude-code-plugins (8 stars, last pushed 26d ago), licensed MIT. It adds 124 tokens to every session and 1,351 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to lark-doc, differing in 98 lines, and is treated as a copy.
Other skills, from other repositories
sheet-music-publisher
Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.
fly
Fly one thought to its destination across concurrent agents, on whatever the project and harness already have. Lands only when the user has accounted for every detail, never on an agent's say-so.
deepen
Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is clear but nothing yet names the sources, methods, target, or outside check the work will meet.
consult
Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.
setup
Use when installing or refreshing sound taste rules in a project — an explicit "sound setup", starting work in a repo with no .claude/sound/, or a taste-not-defined nudge. Also use to re-run after a stack change (new framework, new package in a monorepo).
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.