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 ddpie/lark-mcp-on-agentcore --skill lark-whiteboardgit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-whiteboard)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-whiteboard"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-whiteboard/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/ddpie/lark-mcp-on-agentcore/lark-whiteboard"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-whiteboard.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 | $0.00103 | $0.00782 |
| Opus 5 | $0.00051 | $0.00391 |
| Sonnet 5 | $0.00021 | $0.00156 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
lark-whiteboard 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 10d 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.
What it actually says
飞书画板
飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。
快速决策
| 用户需求 | 行动 |
|---|---|
| 查看画板内容 / 导出图片 / 导出 SVG 矢量图 | lark_whiteboard_query(whiteboard_token="xxx", output_as="image", output="./preview.png")（SVG 用 output_as="svg"）— 详见 lark_get_skill(domain="whiteboard", section="query") |
| 获取画板的 Mermaid/PlantUML 代码 | lark_whiteboard_query(whiteboard_token="xxx", output_as="code") — 详见 lark_get_skill(domain="whiteboard", section="query") |
| 检查画板是否由代码绘制 | lark_whiteboard_query(whiteboard_token="xxx", output_as="code") — 详见 lark_get_skill(domain="whiteboard", section="query") |
| 仅微调节点文字/颜色 | lark_whiteboard_query(output_as="raw") → 手动改 JSON → lark_whiteboard_update(input_format="raw") |
| 用户已提供 Mermaid/PlantUML/SVG 代码，或明确指定用该格式 | 自己生成/使用代码 → lark_whiteboard_update(input_format="mermaid")、lark_whiteboard_update(input_format="plantuml") 或 lark_whiteboard_update(input_format="svg") — 详见 lark_get_skill(domain="whiteboard", section="update") |
| 新建/创作复杂图表（架构/流程/组织等） | → § 创作 Workflow（lark_get_skill(domain="whiteboard", section="workflow")） |
| 修改/重绘已有画板 | → § 修改 Workflow（lark_get_skill(domain="whiteboard", section="workflow")） |
Shortcuts
| Shortcut | 说明 |
|---|---|
lark_whiteboard_query |
查询画板，导出为预览图片、SVG 矢量图、代码或原始节点结构。 — 详见 lark_get_skill(domain="whiteboard", section="query") |
lark_whiteboard_update |
更新画板，支持 PlantUML、Mermaid、SVG 或 OpenAPI 原生格式 — 详见 lark_get_skill(domain="whiteboard", section="update") |
不在本 skill 范围
- 文档内容编辑 →
lark_get_skill(domain="doc") - 在文档中创建画板 →
lark_get_skill(domain="doc", section="whiteboard") - 表格 / Base 操作 →
lark_get_skill(domain="sheets")/lark_get_skill(domain="base")
What ships with it
29 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.
- elements/connectors.md 5.5 KB
- elements/content.md 1.5 KB
- elements/image.md 4.3 KB
- elements/layout.md 19 KB
- elements/schema.md 15 KB
- elements/style.md 11 KB
- elements/typography.md 2.1 KB
- references/lark-whiteboard-query.md 2.5 KB
- references/lark-whiteboard-update.md 4.1 KB
- references/lark-whiteboard-workflow.md 4.8 KB
- routes/dsl.md 6.6 KB
- routes/mermaid.md 1.1 KB
- routes/svg-edit.md 3.1 KB
- routes/svg.md 3.5 KB
- scenes/architecture.md 6.8 KB
- scenes/bar-chart.md 7.8 KB
- scenes/comparison.md 7.4 KB
- scenes/fishbone.md 9.6 KB
- scenes/flowchart.md 11 KB
- scenes/flywheel.md 8.6 KB
- scenes/funnel.md 4.2 KB
- scenes/line-chart.md 9.4 KB
- scenes/mermaid.md 3.4 KB
- scenes/milestone.md 4.0 KB
- scenes/organization.md 8.2 KB
- scenes/photo-showcase.md 6.0 KB
- scenes/pyramid.md 3.9 KB
- scenes/swimlane.md 20 KB
- scenes/treemap.md 6.3 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.
- 10d ago First seen · 38 lines · 103 tokens per session scan A 5c7d2d9219d7
lark-whiteboard is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 13d ago), licensed MIT. It adds 103 tokens to every session and 782 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
cherry-studio-design-language
A design system and template library for creating Cherry Studio presentations and other visual materials. It defines reusable page layouts, spacing, typography, icons, and visual rules.
feishu-whiteboard-pro
Builds, revises, restyles, and critiques deliberate, editable Feishu / Lark whiteboards from content, references, existing SVGs, or live boards. Use for whiteboards, infographics, diagrams, system maps, timelines, decision boards, posters, and visual explainers that need factual fidelity, strong hierarchy, intentional…
feishu-whiteboard-pro
An add-on that turns content into editable Feishu whiteboards, using planned layouts, colors, text roles, spacing, and a design review before saving the result to a Feishu document. Feishu is a Chinese collaboration and document platform.
recipe-generate-diagrams
Read code/docs and generate Mermaid architecture diagrams.
persona-designer
Design documentation and assets.
recipe-design-system-docs
Document design tokens and components in Notion and Markdown.