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/zai-org/synapse/feishu-drivenpx skills add zai-org/Synapse --skill feishu-drivegit clone --depth 1 https://github.com/zai-org/SynapseWrote 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/zai-org/synapse/feishu-drive)<a href="https://agentmods.dev/skills/zai-org/synapse/feishu-drive"><img src="https://agentmods.dev/badge/skills/zai-org/synapse/feishu-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 | $0.00046 | $0.02821 |
| Opus 5 | $0.00023 | $0.01411 |
| Sonnet 5 | $0.00009 | $0.00564 |
| Haiku 4.5 | $0.00005 | $0.00282 |
Grade A, and why
feishu-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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书云空间文件管理
你是飞书云空间文件管理专家，负责通过 API 实现文件的上传、下载、移动、搜索和元数据管理。
一、API 基础信息
| 项目 | 值 |
|---|---|
| Base URL | https://open.feishu.cn/open-apis/drive/v1 |
| 认证方式 | Authorization: Bearer {tenant_access_token} |
| Content-Type | application/json（文件上传用 multipart/form-data） |
二、文件夹操作
1. 创建文件夹
POST /open-apis/drive/v1/folders
{ "name": "文件夹名", "folder_token": "root" }
实测心法：
folder_token为父文件夹 ID，root表示根目录。- 可见性保障 (重要)：通过 API 创建的文件夹默认只对机器人可见。强烈建议在创建后立即调用权限接口 (Skill 8)，将用户（如管理员）添加为
full_access协作者，这样文件夹才会出现在用户的「我的空间」列表中。 - 权限继承：一旦您被添加为父文件夹的管理员，AI 机器人在该文件夹下创建的所有子文件夹和文档，您都将自动拥有管理权限，无需重复授权。
三、文件上传
2. 上传文件（小文件一次性上传）
POST /open-apis/drive/v1/files/upload_all
Content-Type: multipart/form-data
表单字段：
| 字段 | 说明 |
|---|---|
file |
文件二进制内容 |
file_name |
文件名（如 report.pdf） |
parent_type |
父节点类型（explorer = 云空间，bitable_file = 多维表格附件） |
parent_node |
父节点 token（文件夹 token 或 app_token） |
size |
文件大小（字节） |
实测心法：大文件建议使用分片上传接口。
3. 分片上传（大文件）
第 1 步：准备上传
POST /open-apis/drive/v1/files/upload_prepare
{
"file_name": "large_file.zip",
"parent_type": "explorer",
"parent_node": "fldcnXXX",
"size": 104857600
}
返回 upload_id 和分片信息。
第 2 步：逐片上传
POST /open-apis/drive/v1/files/upload_part
Content-Type: multipart/form-data
第 3 步：完成上传
POST /open-apis/drive/v1/files/upload_finish
四、文件下载
4. 下载文件
GET /open-apis/drive/v1/files/:file_token/download
实测心法：流式读取响应体，注意保存路径。返回的是二进制流。
五、文件操作
5. 移动文件
POST /open-apis/drive/v1/files/:file_token/move
{ "type": "docx", "folder_token": "fldcn..." }
实测心法：需要同时拥有源文件夹和目标文件夹的权限。
6. 复制文件
POST /open-apis/drive/v1/files/:file_token/copy
{ "type": "bitable", "folder_token": "fldcn...", "name": "副本名称" }
实测心法：适用于从模板快速克隆多维表格、文档等。
六、文件查询
7. 获取文件元数据（批量）
POST /open-apis/drive/metadata/batch_query
What ships with it
2 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.
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 · 281 lines · 46 tokens per session scan A bbae71a490f5
feishu-drive is a skill published in the GitHub repository zai-org/Synapse (454 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,821 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…