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/larksuite/cli/lark-basenpx skills add larksuite/cli --skill lark-basegit clone --depth 1 https://github.com/larksuite/cliWhat 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 | $0.00131 | $0.06438 |
| Opus 5 | $0.00066 | $0.03219 |
| Sonnet 5 | $0.00026 | $0.01288 |
| Haiku 4.5 | $0.00013 | $0.00644 |
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.
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。folder、table、docx、dashboard、workflow 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:
- 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_type及table_id、view_id、record_id、dashboard_id、workflow_id、docx_token、share_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_token和page_id。实体类型以解析结果为准。 - 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。 - 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或+base-get进入 Base 业务命令。
- 最近访问:
- 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。
What ships with it
25 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-base-advanced-permission-and-role.md 3.8 KB
- references/lark-base-app-block-data-config.md 7.8 KB
- references/lark-base-app.md 15 KB
- references/lark-base-dashboard-block-config.md 19 KB
- references/lark-base-dashboard-block-get-data.md 24 KB
- references/lark-base-dashboard.md 16 KB
- references/lark-base-data-query.md 19 KB
- references/lark-base-field-create.md 3.3 KB
- references/lark-base-field-extension.md 6.8 KB
- references/lark-base-field-formula.md 54 KB
- references/lark-base-field-lookup.md 18 KB
- references/lark-base-field-schema.md 14 KB
- references/lark-base-field-update.md 6.6 KB
- references/lark-base-filter-condition.md 6.0 KB
- references/lark-base-form-detail.md 2.9 KB
- references/lark-base-form-questions-create.md 9.7 KB
- references/lark-base-form-questions-update.md 7.2 KB
- references/lark-base-form-submit.md 7.0 KB
- references/lark-base-record-history-list.md 2.7 KB
- references/lark-base-record-query-and-analysis-sop.md 11 KB
- references/lark-base-role-config.md 21 KB
- references/lark-base-template-center.md 10 KB
- references/lark-base-view-set-filter.md 2.6 KB
- references/lark-base-workflow-schema.md 38 KB
- references/lark-base-workflow.md 27 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 · 285 lines · 131 tokens per session scan A 663f104c9393
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.
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.
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…
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…
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…