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-drivenpx skills add DropFan/claude-code-plugins --skill lark-drivegit 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 | $0.00208 | $0.06734 |
| Opus 5 | $0.00104 | $0.03367 |
| Sonnet 5 | $0.00042 | $0.01347 |
| Haiku 4.5 | $0.00021 | $0.00673 |
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 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.
This is a copy
94% identical to lark-drive — 29 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 — 224 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。)
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 files 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 / 另存为副本时,使用
lark-cli drive files copy。先用lark-cli schema drive.files.copy --format json确认参数;如果来源是 wiki URL/token,先用lark-cli 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-cli drive files copy --params '{"file_token":"<DOC_TOKEN>"}' --data '{"folder_token":"<FOLDER_TOKEN>","name":"<COPY_NAME>","type":"docx"}'。如返回confirmation_required,按lark-shared高风险审批协议向用户确认后,在原命令末尾追加--yes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-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。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。 - 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
57 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-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 906 B
- references/lark-drive-export-download.md 1.5 KB
- references/lark-drive-export.md 7.8 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-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 3.3 KB
- references/lark-drive-pull.md 9.7 KB
- references/lark-drive-push.md 17 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-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.
- 2d ago First seen · 224 lines · 208 tokens per session scan A 82813973e136
lark-drive is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 208 tokens to every session and 6,734 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to lark-drive, differing in 29 lines, and is treated as a copy.
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.