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/larksuite/cli/lark-drivenpx skills add larksuite/cli --skill lark-drivegit clone --depth 1 https://github.com/larksuite/cliWrote 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/larksuite/cli/lark-drive)<a href="https://agentmods.dev/skills/larksuite/cli/lark-drive"><img src="https://agentmods.dev/badge/skills/larksuite/cli/lark-drive.svg" alt="Measured on agentmods" 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 | $0.00208 | $0.06721 |
| Opus 5 | $0.00104 | $0.03361 |
| Sonnet 5 | $0.00042 | $0.01344 |
| Haiku 4.5 | $0.00021 | $0.00672 |
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 4d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- lark-drive — 97% identical, 22 lines differ
- lark-drive — 94% identical, 29 lines differ
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.
drive (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
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-cli 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-cli drive +copy。不要用drive +export下载后再drive +import上传,也不要用docs +fetch+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
- 用户要把已有 Wiki 节点移出知识库,放到 Drive 文件夹或“我的空间”根目录:切到
lark-wiki,使用lark-cli wiki +move-to-drive;不要把 Wiki token 直接交给drive +move。这是会改变文档归属和权限继承的写操作,执行前确认源节点与目标位置。 - 用户要复制文档 / 创建副本 到云盘或者文件夹时:已提供可直接使用的 URL 或 token,按
references/lark-drive-copy.md使用lark-cli drive +copy;仅提供标题时,先按references/lark-drive-search.md使用drive +search唯一定位源资源,再按 copy reference 复制。如果是要复制文档 / 创建副本到知识库,使用wiki +node-copy(见lark-wiki-node-copy.md)。 - 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-cli drive +inspect --url '<url>'进行识别;具体用法、失败处理和边界见references/lark-drive-inspect.md。 - 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”,必须先阅读
references/lark-drive-workflow.md,再按其中Workflow Registry进入permission_governanceworkflow。 - 用户明确要移除单个云文档协作者权限时,使用
lark-cli drive +member-remove;先阅读references/lark-drive-member-remove.md。这是高风险写操作,真实执行必须确认准确的资源、成员 ID/type 和 wiki 权限范围,并显式传--yes。 - 用户要为指定飞书文档设置 / 修改密级标签(secure label),或查询当前用户可用的密级标签,直接读取
references/lark-drive-secure-label.md;这是 Drive 文件治理能力。 - 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”,必须先阅读
references/lark-drive-workflow.md,再按其中Workflow Registry进入permission_governanceworkflow。 - 用户要查询文件、文件夹或云文档自身的公开访问、分享、协作者管理、安全与评论权限设置,优先使用
lark-cli drive +permission-get-setting;它只读取目标自身设置,不递归审计文件夹子文档权限。裸 token 必须显式传--type。 - 用户要按特定主题、关键词或内容线索跨容器查找资料,并统一收集到 Drive 文件夹或 Wiki 节点,必须先阅读
references/lark-drive-workflow.md,再按其中Workflow Registry进入topic_move_collectorworkflow。该 workflow 负责搜索召回、内容验证、相关性分类、移动计划、写前确认和结果验证;禁止直接从drive +search或drive +move开始。 - 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”,必须先阅读
references/lark-drive-workflow.md,再按其中Workflow Registry进入knowledge_organizeworkflow。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。 - 按主题跨范围查找并集中归档,进入
topic_move_collector;对已知文件夹、文档库或知识库做目录盘点和结构重组,进入knowledge_organize;只移动一个已明确资源时仍使用原子移动命令。 - 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-cli drive +search;按标题定位和处理重复候选时遵循references/lark-drive-search.md。自然语言里"最近我编辑过的"、"我创建的"(→--created-by-me,原始创建者语义)、"我负责/owner 的"(→--mine,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 flag,避免手写嵌套 JSON。 - 用户要对文档评论做任何操作(添加评论、列表 / 批量查询、回复、获取 / 更新 / 删除回复、解决 / 恢复、reaction),按下方 Shortcuts 表选择对应的
drive +<verb>评论命令,执行前先阅读该命令的 ref。按评论定位文档正文位置见references/lark-drive-comment-location.md。 - 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-cli 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-cli drive +import --type docx。 - 用户要把本地
.pptx导入成飞书幻灯片,使用lark-cli drive +import --type slides;当前 PPTX 导入上限是 500MB。 - 批量执行
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-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-markdown的lark-cli markdown +diff;需要版本号时先用drive +version-history。 - 用户要查看、下载、回滚或删除文件的历史版本,使用
drive +version-history、drive +version-get、drive +version-revert、drive +version-delete;这组命令同时支持--as user和--as bot,自动化场景优先--as bot。 - 用户要把本地
.xlsx/.xls/.csv导入成电子表格,使用lark-cli 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-cli drive +create-folder。 - 用户要查看或下载文件内容,或者查看文件可用预览格式并获取 PDF / HTML / 文本 / 图片等转换预览产物,使用
lark-cli drive +preview。+preview和+download都支持--file-token/--url/--wiki-token三选一(Wiki 会解析到底层file);但两者只处理 Drive 文件,若目标是 docx/sheet/bitable/slides 等在线文档,改用drive +export。 - 用户要获取某个文件的封面图,优先使用
lark-cli drive +cover;先--list-only看规格,再选--spec下载。 - 用户要导出云文档时,优先使用
lark-cli drive +export --url '<文档 URL>' --file-extension <格式>;详细参数、Wiki token 和错误码处理见references/lark-drive-export.md。 - 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-cli 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-cli drive +inspect解包;+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。 drive +inspect/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
60 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 12 KB
- references/lark-drive-add-reply.md 2.5 KB
- references/lark-drive-apply-permission.md 3.6 KB
- references/lark-drive-batch-query-comments.md 2.4 KB
- references/lark-drive-comment-content.md 2.6 KB
- references/lark-drive-comment-location.md 11 KB
- references/lark-drive-copy.md 3.9 KB
- references/lark-drive-cover.md 2.4 KB
- references/lark-drive-create-folder.md 3.6 KB
- references/lark-drive-create-shortcut.md 4.3 KB
- references/lark-drive-delete-reply.md 2.4 KB
- references/lark-drive-delete.md 4.5 KB
- references/lark-drive-download.md 2.8 KB
- references/lark-drive-export-download.md 1.5 KB
- references/lark-drive-export.md 8.1 KB
- references/lark-drive-files-list.md 10 KB
- references/lark-drive-import.md 11 KB
- references/lark-drive-inspect.md 2.1 KB
- references/lark-drive-list-comments.md 5.9 KB
- references/lark-drive-list-replies.md 2.6 KB
- references/lark-drive-member-add.md 5.1 KB
- references/lark-drive-member-list.md 3.0 KB
- references/lark-drive-member-remove.md 2.9 KB
- references/lark-drive-move.md 5.0 KB
- references/lark-drive-permission-get-setting.md 1.8 KB
- references/lark-drive-permission-guide.md 3.7 KB
- references/lark-drive-preview.md 4.6 KB
- references/lark-drive-pull.md 9.7 KB
- references/lark-drive-push.md 18 KB
- references/lark-drive-react-reply.md 2.9 KB
- references/lark-drive-reactions.md 7.1 KB
- references/lark-drive-resolve-comment.md 1.7 KB
- references/lark-drive-restore-comment.md 2.1 KB
- references/lark-drive-search.md 22 KB
- references/lark-drive-secure-label.md 2.0 KB
- references/lark-drive-status.md 7.3 KB
- references/lark-drive-task-result.md 13 KB
- references/lark-drive-update-reply.md 2.4 KB
- references/lark-drive-update-title.md 3.3 KB
- references/lark-drive-upload.md 5.1 KB
- references/lark-drive-version-delete.md 1.0 KB
- references/lark-drive-version-get.md 2.0 KB
- references/lark-drive-version-history.md 1.9 KB
- references/lark-drive-version-revert.md 979 B
- references/lark-drive-workflow-knowledge-organize-analysis.md 13 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 20 KB
- references/lark-drive-workflow-permission-governance-commands.md 6.4 KB
- references/lark-drive-workflow-permission-governance-outputs.md 28 KB
- references/lark-drive-workflow-permission-governance.md 26 KB
- references/lark-drive-workflow-topic-move-collector-execute.md 13 KB
- references/lark-drive-workflow-topic-move-collector-recall.md 9.3 KB
- references/lark-drive-workflow-topic-move-collector-resolve-verify.md 14 KB
- references/lark-drive-workflow-topic-move-collector-review-plan.md 13 KB
- references/lark-drive-workflow-topic-move-collector-setup.md 8.3 KB
- references/lark-drive-workflow-topic-move-collector.md 16 KB
- references/lark-drive-workflow.md 8.3 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.
- 4d ago First seen · 217 lines · 208 tokens per session scan A b140cd55b62b
lark-drive is a skill published in the GitHub repository larksuite/cli (16,971 stars, last pushed today), licensed MIT. It adds 208 tokens to every session and 6,721 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.