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 liuboacean/mubu-integration --skill mubu-integrationgit clone --depth 1 https://github.com/liuboacean/mubu-integrationWrote 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/liuboacean/mubu-integration/mubu-integration)<a href="https://agentmods.dev/skills/liuboacean/mubu-integration/mubu-integration"><img src="https://agentmods.dev/badge/skills/liuboacean/mubu-integration/mubu-integration/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/liuboacean/mubu-integration/mubu-integration"><img src="https://agentmods.dev/badge/skills/liuboacean/mubu-integration/mubu-integration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.06058 |
| Opus 5 | $0.00037 | $0.03029 |
| Sonnet 5 | $0.00015 | $0.01212 |
| Haiku 4.5 | $0.00007 | $0.00606 |
Grade A, and why
mubu-integration 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 11d 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
幕布集成 Skill
幕布（mubu.com）是一款极简大纲工具，支持将大纲一键转为思维导图。本 Skill 提供 API 集成能力。
权限与安全边界
本 Skill 以你的幕布账号身份操作远程真实内容，使用前请知悉其权限边界：
- 读取：仅读取环境变量
MUBU_PHONE/MUBU_PASSWORD/MUBU_MEMBER_ID（环境变量未设置时，才由仓库外的~/.workbuddy/.env.mubu补全；MUBU_MEMBER_ID即幕布 colla 成员 ID，仅save写回需要。该值任何 API 都不返回，无法自动获取，必须手动设置MUBU_MEMBER_ID或提前写入 token 缓存的member_id）。 - 写入：仅在本地写入 Token 缓存文件
~/.mubu_token（权限0o600+ 跨进程fcntl锁），不写入其它文件。 - 网络：仅访问
api2.mubu.com（base URL 可由MUBU_BASE_URL覆盖，但仅限mubu.com家族域名，防 MITM），无第三方服务、无遥测、无数据外发。 - 写操作需确认：真实会改动幕布内容的写操作为
create（新建）、rename_folder（重命名文件夹）、save（保存文档，端点/colla/events，需member_id）、move（移动，端点/list/custom/drag）、rename_doc（文档重命名，端点/list/rename_doc）、purge（彻底删除，唯一真实调用服务端删除，不可逆）；delete现为软删除（仅标记进本地回收站，云端副本仍在）。save/move/rename_doc已在 v1.3.9 经真机验证可用。所有真实写操作均需显式传--yes才执行，否则中止并提示。 - 信任边界：Skill 不读取你的其它本地文件、不执行与幕布无关的 shell 命令；它只做「登录 → 读写你的幕布文档」这一件事。
功能概览
| 功能 | 接口 | 说明 |
|---|---|---|
| 用户登录 | POST /user/phone_login |
手机号密码登录获取 Token |
| Token 刷新 | 自动处理 | access_token 2小时过期，临近过期自动重新登录（重登仅重试 1 次，杜绝死循环） |
| 创建文件夹 | POST /list/create_folder |
在指定位置创建文件夹 |
| 创建文档 | POST /list/create_doc |
创建新的大纲文档 |
| 获取列表 | POST /list/get |
获取文件夹下的文档列表 |
| 获取文档 | POST /document/edit/get |
获取文档详细内容（真实端点；body 为 docId+password+isFromDocDir，返回 data.definition 为 JSON 字符串需二次解析） |
| 更新文档 | POST /colla/events |
保存/更新文档内容（v1.3.9 起可用；colla 协同端点，events 承载 changeset；需 member_id，私人文档由 MUBU_MEMBER_ID 或 token 缓存提供） |
| 删除文档 | POST /list/delete_doc |
删除文档（按类型区分端点） |
| 删除文件夹 | POST /list/delete_folder |
删除文件夹（原 /list/delete 实测非法，已弃用） |
| 移动文档 | POST /list/custom/drag |
移动文档/文件夹到其他位置（v1.3.9 起可用；body dst/src/folderId，已真机验证） |
| 导出 Markdown | 本地转换 | 将大纲结构转换为 Markdown |
API 基础信息
- Base URL:
https://api2.mubu.com/v3/api - 认证方式: JWT Token，通过请求头
Jwt-Token传递 - Content-Type:
application/json;charset=UTF-8
环境变量配置
在使用前，需要配置以下环境变量：
export MUBU_PHONE="your_phone_number" # 幕布账号手机号
export MUBU_PASSWORD="your_password" # 幕布账号密码
# 可选：幕布 colla 成员 ID（仅 save 写回需要；任何 API 都不暴露，必须手动设置，缺失时 save 会明确报错）
export MUBU_MEMBER_ID="your_collab_member_id"
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.
- 11d ago First seen · 437 lines · 75 tokens per session scan A 989beda96433
mubu-integration is a skill published in the GitHub repository liuboacean/mubu-integration (15 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 6,058 once invoked, about $0.0004 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
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
alive-cleanup
System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.
alive-daily
Morning operating system -- sync inputs, read everything, surface priorities, show the day.