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 ddpie/lark-mcp-on-agentcore --skill lark-drivegit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-drive)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-drive"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-drive/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/ddpie/lark-mcp-on-agentcore/lark-drive"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00192 | $0.07073 |
| Opus 5 | $0.00096 | $0.03537 |
| Sonnet 5 | $0.00038 | $0.01415 |
| Haiku 4.5 | $0.00019 | $0.00707 |
Grade A, and why
lark-drive 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 10d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drive (v1)
术语说明: 飞书云空间也常被称为"云盘"、"云存储"、"网盘"或"我的空间",这些说法通常指的是同一个产品,是飞书官方的云端文件存储与管理中心。
导入分流规则: 如果用户要把本地 Excel / CSV /
.base快照导入成 Base / 多维表格 / bitable,必须优先使用lark_drive_import(type="bitable")。不要先切到lark-base;lark-base只负责导入完成后的表内操作。
副本分流规则: 如果用户要复制在线文档、创建文档副本、把文档复制到另一个文件夹,必须使用
lark_invoke(tool_name="lark_drive_files_copy", ...)。不要用lark_drive_export下载后再lark_drive_import上传,也不要用lark_docs_fetch+lark_docs_create重建正文;导出/导入只用于本地文件转换或离线产物。
快速决策
- 用户要复制文档 / 创建副本 / 另存为副本时,使用
lark_invoke(tool_name="lark_drive_files_copy", ...)。先用lark_discover(query="drive.files.copy")确认参数;如果来源是 wiki URL/token,先用lark_drive_inspect()获取底层token和type,不要把 wiki token 直接当file_token。params.file_token传源文档 token,data.folder_token传目标文件夹 token,data.name传副本名称,data.type传源文件类型(如docx/sheet/bitable/slides)。示例:lark_invoke(tool_name="lark_drive_files_copy", args={params: {"file_token":"<DOC_TOKEN>"}, data: {"folder_token":"<FOLDER_TOKEN>","name":"<COPY_NAME>","type":"docx"}})。如返回需要确认,向用户确认后在调用里加_confirm=true重试。 - 用户要识别飞书 / doubao 云空间 URL 的类型和 token时,可以先按 URL 路径形态做轻量判断;当路径已明确指向 docx / sheet / bitable / slides / file / folder 等资源时,可直接提取对应 token/type。传入 wiki URL、需要识别标题或 canonical URL、URL/token 有歧义,或后续操作依赖底层真实资源时,再使用
lark_drive_inspect(url="<url>")进行识别;具体用法、失败处理和边界见lark_get_skill(domain="drive", section="inspect")。 - 高风险写操作(删除、公开权限修改、owner 转移、版本删除/回滚、批量移动/覆盖/同步)必须同时满足三个条件才执行:目标已解析为该操作可直接使用的执行对象,执行细节已明确到可直接调用命令(例如删除的 file-token/type、公开权限修改的共享范围、owner 转移的目标 owner、版本删除/回滚的 version id、移动/覆盖/同步的目标位置和冲突策略),且用户在本轮明确确认执行这些具体目标和执行细节。用户只说"删除没用的文件""开放/共享给大家""改成开放""覆盖/移动这些"只表示目标状态;先只读发现并列出候选、权限档位或执行方案,停止等待用户确认。
- 用户要检查 / 治理文档权限、公开范围、链接分享、外部访问、复制下载权限、密级标签、owner 转移,或要"权限风险报告、收紧权限、申请查看 / 编辑权限、转移 / 批量转移 owner",必须先调用
lark_get_skill(domain="drive", section="workflow"),再按其中Workflow Registry进入permission_governanceworkflow(lark_get_skill(domain="drive", section="workflow-permission-governance"))。 - 用户要整理云盘 / 文件夹 / 文档库 / 知识库 / 个人文档库,或要"盘点目录结构、找出未归档/临时/重复/空目录、生成整理方案",必须先调用
lark_get_skill(domain="drive", section="workflow"),再按其中Workflow Registry进入knowledge_organizeworkflow(lark_get_skill(domain="drive", section="workflow-knowledge-organize"))。默认只生成方案;创建目录、移动资源、申请权限都必须单独确认。 - 用户要搜文档 / Wiki / 电子表格 / 多维表格 / 云空间(云盘/云存储)对象,优先使用
lark_drive_search()。自然语言里"最近我编辑过的"、"我创建的"(→created_by_me=true,原始创建者语义)、"我负责/owner 的"(→mine=true,owner 语义)、"最近一周我打开过的 xxx"、"某人 owner 的 docx" 等直接映射到扁平参数,避免手写嵌套 JSON。 - 用户要获取文档评论列表时,优先使用
lark_drive_list_comments(url="<url>"),不要优先手写lark_invoke(tool_name="lark_drive_file_comments_list", ...);具体使用方式先调用lark_get_skill(domain="drive", section="list-comments")。 - 用户要根据文档评论定位正文位置,例如 根据评论 review 文档、根据评论内容回看文档、区分多处相同引用文本时,对于 docx 类型(
file_type=docx)的文档支持通过lark_drive_list_comments(need_relation=true)返回评论位置,其他类型会静默忽略该参数;具体用法需要先调用lark_get_skill(domain="drive", section="comment-location")了解。 - 用户给出 doubao.com 的云空间资源 URL/token,或明确提到豆包里的 file/folder/docx/sheet/bitable/wiki 资源时,仍按资源类型、URL 路径和 token 路由到本 skill;不要因为域名不是飞书而回退到 WebFetch。
- 用户要把本地
.xlsx/.csv/.base导入成 Base / 多维表格 / bitable,第一步必须使用lark_drive_import(type="bitable")。 - 用户要把本地
.md/.docx/.doc/.txt/.html导入成在线文档,使用lark_drive_import(type="docx")。 - 用户要把本地
.pptx导入成飞书幻灯片,使用lark_drive_import(type="slides");当前 PPTX 导入上限是 500MB。 - 批量执行
lark_drive_import且目标是同一个位置(同一folder_token、默认根目录,或同一target_token)时,必须串行执行;不要并发导入到同一位置,服务端可能返回并发冲突错误。 - 用户要在 Drive 里上传、创建、读取、局部 patch 或覆盖更新原生
.md文件(不是导入成 docx),切到lark_get_skill(domain="markdown")。 - 用户要比较原生
.md文件的历史版本差异,或比较远端 Markdown 与本地草稿,切到lark_get_skill(domain="markdown")的lark_markdown_diff;需要版本号时先用lark_drive_version_history()。 - 用户要查看、下载、回滚或删除文件的历史版本,使用
lark_drive_version_history()、lark_drive_version_get()、lark_drive_version_revert()、lark_drive_version_delete();这组工具同时支持 user identity 和 bot identity。 - 用户要把本地
.xlsx/.xls/.csv导入成电子表格,使用lark_drive_import(type="sheet")。 - 用户要在云空间(云盘/云存储)里新建文件夹,优先使用
lark_drive_create_folder()。 - 用户要查看某个文件有哪些可下载预览格式,或想下载 PDF / HTML / 文本 / 图片等预览产物,使用
lark_drive_preview()。 - 用户要获取某个文件的封面图,优先使用
lark_drive_cover();先list_only=true看规格,再选spec下载。 - 用户要导出云文档时,优先使用
lark_drive_export(url="<文档 URL>", file_extension="<格式>");详细参数、Wiki token 和错误码处理见lark_get_skill(domain="drive", section="export")。 - 用户要把本地文件上传到知识库 / 文档库里的某个 wiki 节点下时,仍然使用
lark_drive_upload(wiki_token="<wiki_token>");不要误切到wiki域命令。 lark-base只负责导入完成后的 Base 内部操作(表、字段、记录、视图),不要在"本地文件 -> Base"这一步提前切到lark-base。- 用户给的是 wiki URL / token,且后续还没明确底层资源类型时,先用
lark_drive_inspect()解包;lark_drive_inspect()失败后不要自动切到别的写接口继续尝试,先按错误提示处理权限、scope 或链接问题。 lark_drive_inspect()/lark_drive_upload()遇到not found、permission denied、missing scope时,默认停止重试;只有rate limit或临时网络错误才适合有限重试。
What ships with it
41 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-drive-add-comment.md 11 KB
- references/lark-drive-apply-permission.md 3.3 KB
- references/lark-drive-comment-location.md 11 KB
- references/lark-drive-comments-guide.md 6.3 KB
- references/lark-drive-cover.md 2.1 KB
- references/lark-drive-create-folder.md 1.9 KB
- references/lark-drive-create-shortcut.md 3.6 KB
- references/lark-drive-delete.md 3.4 KB
- references/lark-drive-download.md 584 B
- references/lark-drive-export-download.md 1.3 KB
- references/lark-drive-export.md 6.5 KB
- references/lark-drive-files-list.md 10 KB
- references/lark-drive-import.md 8.3 KB
- references/lark-drive-inspect.md 1.9 KB
- references/lark-drive-list-comments.md 5.2 KB
- references/lark-drive-member-add.md 4.7 KB
- references/lark-drive-move.md 4.3 KB
- references/lark-drive-permission-guide.md 3.9 KB
- references/lark-drive-preview.md 2.1 KB
- references/lark-drive-pull.md 9.2 KB
- references/lark-drive-push.md 16 KB
- references/lark-drive-reactions.md 6.4 KB
- references/lark-drive-search.md 19 KB
- references/lark-drive-secure-label.md 1.9 KB
- references/lark-drive-status.md 7.0 KB
- references/lark-drive-task-result.md 8.2 KB
- references/lark-drive-upload.md 2.5 KB
- references/lark-drive-version-delete.md 603 B
- references/lark-drive-version-get.md 1.5 KB
- references/lark-drive-version-history.md 1.4 KB
- references/lark-drive-version-revert.md 540 B
- references/lark-drive-workflow-knowledge-organize-analysis.md 12 KB
- references/lark-drive-workflow-knowledge-organize-discovery.md 19 KB
- references/lark-drive-workflow-knowledge-organize-execution.md 9.4 KB
- references/lark-drive-workflow-knowledge-organize-planning.md 14 KB
- references/lark-drive-workflow-knowledge-organize-rollback.md 11 KB
- references/lark-drive-workflow-knowledge-organize.md 19 KB
- references/lark-drive-workflow-permission-governance-commands.md 4.5 KB
- references/lark-drive-workflow-permission-governance-outputs.md 28 KB
- references/lark-drive-workflow-permission-governance.md 25 KB
- references/lark-drive-workflow.md 7.8 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.
- 10d ago First seen · 222 lines · 192 tokens per session scan A 89f9d55646ef
lark-drive is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 12d ago), licensed MIT. It adds 192 tokens to every session and 7,073 once invoked, about $0.0010 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
lark-cli
A command-line tool for working with Lark, also called Feishu, a workplace collaboration platform. It covers services such as calendars, meetings, documents, spreadsheets, messaging, tasks, approvals, and shared files.
minutes
Access Lark Minutes recordings - get metadata, export transcripts, download audio/video. Use when user asks about meeting recordings, transcripts, or minutes.
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
notion
Use the Notion API to create/read/update pages, data sources (databases), and blocks.
google-workspace
Use the native Google Workspace tools for Gmail, Calendar, Drive, Docs, and Sheets.
claude-to-im
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge"…