feishu-cli is a command-line tool for controlling the Feishu collaboration platform, including documents, knowledge bases, spreadsheets, messages, calendars, and tasks. People and AI coding agents use it to manage Feishu through commands, with particular support for converting Markdown to Feishu documents and back. Its catalogue skills provide ready-made AI-agent workflows for these operations.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/riba2534/feishu-clinpx agentmods add skills/riba2534/feishu-cli/feishu-cli-docsWrote 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/riba2534/feishu-cli/feishu-cli-docs)<a href="https://agentmods.dev/skills/riba2534/feishu-cli/feishu-cli-docs"><img src="https://agentmods.dev/badge/skills/riba2534/feishu-cli/feishu-cli-docs/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/riba2534/feishu-cli/feishu-cli-docs"><img src="https://agentmods.dev/badge/skills/riba2534/feishu-cli/feishu-cli-docs.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 | $0.00357 | $0.01791 |
| Opus 5.5 | $0.00143 | $0.00716 |
| Sonnet 5.5 | $0.00071 | $0.00358 |
| Haiku 4.5 | $0.00036 | $0.00179 |
Grade A, and why
feishu-cli-docs 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 15d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书文档
只读取当前任务需要的工作流；跨步骤任务可以按顺序读取多个。
加载后，将工作流中的 references/、scripts/、templates/、examples/ 相对路径按该
workflow.md 所在目录解析；执行脚本时使用解析后的实际路径，不要依赖当前 shell 目录。
路由
| 意图 | 读取文件 |
|---|---|
| 阅读、总结、分析 docx/wiki/sheet，大文档按大纲/章节/关键词局部读取，获取块结构，不主动落盘 | references/workflows/read/workflow.md |
取文档内容转成可直接发 IM 的 Markdown（doc read --doc-format im-markdown，--lang 控制 @人显示语言） |
references/workflows/read/workflow.md |
带 block id 读取（doc read --with-ids / --engine docs_ai），为精确修改做准备 |
references/workflows/read/workflow.md |
从零创作文档（写 / 起草方案、PRD、周报、纪要、报告、教程等），选体裁、写 DocxXML 草稿并用 doc script 初始化与预检 |
references/workflows/author/workflow.md |
创建 docx（含 doc create --content 带本地图片/附件、HTML 块、画板源文件建文档）、追加、覆盖、替换、删除或移动内容，按 block id 精确改写，插入本地或剪贴板图片/附件（--from-clipboard） |
references/workflows/write/workflow.md |
设置、下载或删除文档封面（doc resource update/download/delete --type cover） |
references/workflows/write/workflow.md |
查看历史版本、回滚文档（doc history list/revert/revert-status） |
references/workflows/write/workflow.md |
| 把 Markdown 文件导入为飞书 docx（含 Mermaid/PlantUML/SVG 转画板） | references/workflows/import/workflow.md |
导出 docx/wiki/sheet 到本地 Markdown/PDF/Word/Excel，下载或预览文档内图片、附件、评论图片或画板缩略图（doc media-download / doc media-preview） |
references/workflows/export/workflow.md |
上传、下载、覆盖、查找替换或比较云盘原生 .md |
references/workflows/markdown/workflow.md |
读取已有思维笔记的节点，新增子节点或更新节点（mindnote nodes list/create） |
references/workflows/mindnote/workflow.md |
关键边界
- “查看并总结”走 read；明确要求保存到路径才走 export。
- 从零写一篇文档走 author；只建空文档、原样写入用户给定的完整内容或改已有文档走 write。
- Markdown 转为可阅读 docx 走 import；把
.md源文件原样存入云盘走 markdown。 mindnote nodes create只在已有思维笔记里新增/更新节点，不新建思维笔记；新建思维导图走feishu-cli-visual的画板。- DOCX/XLSX 等二进制文件导入走
feishu-cli-storage的 drive 工作流。 doc htmlbox属于feishu-cli-visual；权限和转移所有权属于feishu-cli-storage。
执行规则
/wiki/链接或类型不明的 token 先drive inspect --url解析；Bitable 链接用bitable resolve。wiki 链接解析后区分 node_token 与底层文档 obj_token；底层是 sheet/bitable/slides 时按类型交给对应技能。- 修改已有文档一律用
doc content-update，不要用doc import --document-id（只会追加到文末）；改几个字用文本级替换， 改章节或块先doc read --with-ids拿 block id。写入前确认目标、更新模式和影响范围；content-update没有 dry-run， 不确定时先在测试文档上验证。 - 写命令默认 Bot 身份：Bot 新建的文档会自动给当前登录用户授予
full_access（输出permission_grant）；编辑用户自己的 文档而 Bot 无权限时，显式--user-access-token "$(feishu-cli auth token --as user)"。读命令 User 优先、Bot 兜底。 - 按退出码处理结果：2 = 参数或定位有歧义（选择器多处命中、方言占位无法写回、本地文件不存在），修正参数后重试；
1 且有失败明细（
doc import的failures、content-update的partial_success、本地资源failed）时按明细补齐， 不要整篇重导；10 = 危险操作缺--yes（doc delete、doc history revert）。 - 导入前读取
references/workflows/import/references/doc-guide.md。 - 用户明确指定接收人时按其要求授权；其余按 write 工作流读取生效的
owner_email/transfer_ownership，仅在已配置 owner 时处理。未要求通知时在当前会话返回文档链接。
What ships with it
45 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.
- evals/evals.json 10 KB
- evals/fixtures/local-image.md 52 B
- evals/fixtures/owner-config.yaml 96 B
- evals/fixtures/remote-image.md 64 B
- references/workflows/author/references/doc-script.md 7.1 KB
- references/workflows/author/references/docs-ai-markdown.md 2.9 KB
- references/workflows/author/references/docx-xml-extended-blocks.md 4.8 KB
- references/workflows/author/references/docx-xml.md 8.3 KB
- references/workflows/author/references/genres/business-analysis.md 3.2 KB
- references/workflows/author/references/genres/data-report.md 3.0 KB
- references/workflows/author/references/genres/email.md 4.1 KB
- references/workflows/author/references/genres/execution-plan.md 3.0 KB
- references/workflows/author/references/genres/formal-doc.md 4.5 KB
- references/workflows/author/references/genres/meeting-minutes.md 2.4 KB
- references/workflows/author/references/genres/memo-brief.md 2.1 KB
- references/workflows/author/references/genres/official-redhead.md 6.2 KB
- references/workflows/author/references/genres/prd.md 2.6 KB
- references/workflows/author/references/genres/proposal.md 2.2 KB
- references/workflows/author/references/genres/research-report.md 3.3 KB
- references/workflows/author/references/genres/retrospective.md 2.5 KB
- references/workflows/author/references/genres/route-consumer.md 3.9 KB
- references/workflows/author/references/genres/route-creative.md 3.7 KB
- references/workflows/author/references/genres/route-knowledge.md 4.8 KB
- references/workflows/author/references/genres/route-marketing.md 4.3 KB
- references/workflows/author/references/genres/route-media.md 3.8 KB
- references/workflows/author/references/genres/route-opinion.md 3.7 KB
- references/workflows/author/references/genres/route-personal-brand.md 3.5 KB
- references/workflows/author/references/genres/route-platform.md 743 B
- references/workflows/author/references/genres/route-report.md 1.3 KB
- references/workflows/author/references/genres/route-workplace.md 2.9 KB
- references/workflows/author/references/genres/sop-tutorial.md 4.1 KB
- references/workflows/author/references/genres/technical-doc.md 3.6 KB
- references/workflows/author/references/genres/wechat.md 4.0 KB
- references/workflows/author/references/genres/weekly-report.md 2.1 KB
- references/workflows/author/references/genres/white-paper.md 3.2 KB
- references/workflows/author/references/genres/xiaohongshu.md 3.3 KB
- references/workflows/author/workflow.md 11 KB
- references/workflows/export/workflow.md 12 KB
- references/workflows/import/references/doc-guide.md 7.6 KB
- references/workflows/import/references/mermaid-spec.md 15 KB
- references/workflows/import/workflow.md 14 KB
- references/workflows/markdown/workflow.md 13 KB
- references/workflows/mindnote/workflow.md 6.6 KB
- references/workflows/read/workflow.md 14 KB
- references/workflows/write/workflow.md 33 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.
- 15d ago Changed · +9 lines · +126 tokens per session fbebea777db6
- 1mo ago Changed · -1 lines · +19 tokens per session 8e043b53b258
- 1mo ago First seen · 47 lines · 212 tokens per session scan A 69cd7472b480
feishu-cli-docs is a skill published in the GitHub repository riba2534/feishu-cli (1,425 stars, last pushed 15d ago), licensed MIT. It adds 357 tokens to every session and 1,791 once invoked, about $0.0014 per session on Opus 5.5. 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
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
surfsense-documents
Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.