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-docnpx skills add DropFan/claude-code-plugins --skill lark-docgit 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 | $0.00162 | $0.02837 |
| Opus 5 | $0.00081 | $0.01418 |
| Sonnet 5 | $0.00032 | $0.00567 |
| Haiku 4.5 | $0.00016 | $0.00284 |
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 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 — 97 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
身份：文档操作默认使用 --as user。首次使用前执行 lark-cli auth login。
# 常用示例
lark-cli docs +fetch --doc "文档URL或token；若 URL 存在 #share-... 锚点，优先使用锚点方式读取，不要全文拉取"
lark-cli docs +create --content '<title>标题</title><p>内容</p>'
lark-cli docs +update --doc "文档URL或token" --command append --content '<p>内容</p>'
前置条件 — 执行操作前必读
CRITICAL — 执行对应操作前，MUST 先用 Read 工具读取以下文件，缺一不可：
../lark-shared/SKILL.md— 认证、权限处理、全局参数（所有操作通用）- 读取文档（
docs +fetch） → 必读lark-doc-fetch.md（--scope/--detail选择、局部读取策略、<fragment>/<excerpt>输出结构） - 创建或编辑文档内容 → 必读
lark-doc-xml.md（XML 语法规则，仅当用户明确要求 Markdown 时改读lark-doc-md.md）和必读lark-doc-style.md（写作原则：默认段落、按体裁、组件克制）；从零创建时加读lark-doc-create-workflow.md；编辑已有文档时加读lark-doc-update.md和lark-doc-update-workflow.md
未读完以上文件就执行相应操作会导致参数选择错误或格式错误。
格式选择规则（全局）：
- 创建 / 导入场景（
docs +create，或docs +update --command append/overwrite的整段写入）：XML 和 Markdown 都可以。用户提供.md本地文件、或明确说"导入 Markdown"时，直接用 Markdown；否则默认 XML。- 精准编辑场景（
docs +update的str_replace/block_insert_after/block_replace/block_delete/block_move_after等局部精修指令）：优先使用 XML（--doc-format xml，即默认值）。XML 能稳定表达 block 结构和样式，局部精修更可控；不要因为 Markdown 更简单就自行切换。
What ships with it
18 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/lark-doc-create.md 5.1 KB
- references/lark-doc-fetch.md 9.2 KB
- references/lark-doc-history.md 5.2 KB
- references/lark-doc-md.md 5.3 KB
- references/lark-doc-media-download.md 2.1 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-update.md 13 KB
- references/lark-doc-whiteboard.md 8.9 KB
- references/lark-doc-word-stat.md 4.1 KB
- references/lark-doc-xml-extended-blocks.md 3.8 KB
- references/lark-doc-xml.md 9.9 KB
- references/style/lark-doc-create-workflow.md 4.7 KB
- references/style/lark-doc-style.md 6.0 KB
- references/style/lark-doc-update-workflow.md 4.3 KB
- scripts/doc_word_stat.py 39 KB runs code
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 · 97 lines · 162 tokens per session scan A 166f8adbfdc7
lark-doc is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 162 tokens to every session and 2,837 once invoked, about $0.0008 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.