lark-base

A toolkit for working with Feishu Base, a database-like workspace for tables, records, views, forms, dashboards, workflows, and permissions. BaseApp is a separate app-style interface for presenting Base data.

In plain words
What is it for?
Use it to create and manage tables, fields, records, views, formulas, forms, dashboards, workflows, templates, app pages, workspaces, and access roles.
Why use it?
It helps you locate the right Base or table and manage both its data and the surrounding structure without confusing tables, apps, dashboards, or workflows.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/larksuite/cli/lark-base
Any agent
npx skills add larksuite/cli --skill lark-base
Clone the repo
git clone --depth 1 https://github.com/larksuite/cli

Made for: Claude Code, Codex.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00131 $0.06438
Opus 5 $0.00066 $0.03219
Sonnet 5 $0.00026 $0.01288
Haiku 4.5 $0.00013 $0.00644

Measured 2d ago against content hash 663f104c9393, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lark-base 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.

skills/lark-base/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Base

普通 Base 是数据容器,由一棵 Base Block 资源树和 Base 级配置组成。foldertabledocxdashboardworkflow 都是 Block 类型;Advanced Permission / Role 是 Base 级配置,不属于 Block。Table 是其中承载业务数据的核心 Block。Workspace 是组织 Base 与 BaseApp 的外层容器;BaseApp(AppMode)通过 Page 和组件组织 Base 数据,不是 Base 的别名。

身份选择(优先)

操作 Base 优先使用 --as user;用户明确要求应用身份时使用 --as bot。权限失败按 lark-shared 以原身份修复 scope 或资源 ACL;只有用户明确同意更换操作者时才切换身份。

进入前必做:解析目标实体

开始操作前先确定 base_token 和目标实体类型;上下文已提供 <bitable> / <base_refer> 标签及资源 ID 时直接使用。其余情况按意图选择入口:

  1. URL 或分享链接: lark-cli base +url-resolve --url '<url>' --as user。Base URL 根据返回的 resource_type / block_typetable_idview_idrecord_iddashboard_idworkflow_iddocx_tokenshare_token 等坐标进入对应模块;BaseApp /app/ URL 返回 app_token,并在链接携带时返回 workspace_tokenpage_id。实体类型以解析结果为准。
  2. Base 标题或关键词: lark-cli base +title-resolve --title '<keyword>' --as user。单一结果直接取得 base_token;多个候选结合标题、所有者和更新时间消歧,仍无法唯一确定时请用户选择。随后按下方 Base Block 资源模型定位目标实体。
  3. 已有 Base 候选列表: 用户要列出已有 Base 候选,且需要按最近访问、owner、创建人、时间、类型等维度筛选/排序时,转 lark-cli drive +search --doc-types bitable --as user。按标题/关键词定位单个 Base 仍用 +title-resolve。常见候选列表命令:
    • 最近访问:lark-cli drive +search --doc-types bitable --sort open_time --opened-since 3m --page-size 20 --as user
    • 只列我拥有的:加 --mine;如果要列“我创建的”,用 --created-by-me
    • 从候选项拿到 URL 或 token 后,再用 +url-resolve+base-get 进入 Base 业务命令。
  4. BaseApp: 优先使用真实 /app/ URL;已有 workspace_token 时可用 +workspace-entity-list --type baseapp 定位。两者都没有时请用户补充应用链接或 Workspace,不按名称全局猜测 app_token

读取 Base: Base 信息用 +base-get,资源目录按下方 Base Block 资源模型读取。

写入 Base: 创建新 Base 使用一次 +base-create --name <base-name> --table-name <table-name> --fields '<field-array>' 同时创建 Base、首表和 fields;+base-copy 复制整个 Base;Base 内资源统一按下方 Block 生命周期管理。

Base 模板中心

模板中心是公开的 Base 模板库,不是用户云空间里的已有 Base。用户想用现成模板创建新 Base,且没有指向已有对象的锚点(没有 Base URL、没有“我的/最近访问的表”、没有具体已存在的 Base 名)时,可读取 lark-base-template-center.md 查找模板中心模板;+template-categories 列出公开模板分类,+template-list 按分类列出公开模板,+template-search 按业务关键词搜索公开模板。

Read the full file on GitHub · 285 lines

Changes

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.

  1. 2d ago First seen · 285 lines · 131 tokens per session scan A 663f104c9393

Subscribe to this mod's changes

lark-base is a skill published in the GitHub repository larksuite/cli (16,925 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 6,438 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens