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/bergside/design-md-figma/figma-pluginnpx skills add bergside/design-md-figma --skill figma-plugingit clone --depth 1 https://github.com/bergside/design-md-figmaWrote 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/bergside/design-md-figma/figma-plugin)<a href="https://agentmods.dev/skills/bergside/design-md-figma/figma-plugin"><img src="https://agentmods.dev/badge/skills/bergside/design-md-figma/figma-plugin.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 5.1 | $0.00038 | $0.00563 |
| Opus 5 | $0.00019 | $0.00282 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
figma-plugin 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Plugin Development
Build plugins that extend Figma's functionality using the Plugin API.
Architecture
Figma plugins run in two threads communicating via postMessage:
- Main thread (sandbox): Plugin API access, node manipulation,
figma.*calls - UI thread (iframe): HTML/CSS/JS interface, no Figma API access, npm packages allowed
Key Principles
- Main thread handles all Figma document operations
- UI thread handles user interface and external APIs
- Communication between threads via
figma.ui.postMessage()andonmessage - Plugins must be performant — avoid blocking the main thread
Quick Start Checklist
- Set up project with
manifest.json(name, id, main, ui) - Create main thread code (
code.ts) with plugin logic - Create UI (
ui.html) with interface elements - Wire up postMessage communication between threads
- Test in Figma development mode
- Publish via Figma Community
References
| Reference | Description |
|---|---|
| project-structure-and-build.md | Manifest, TypeScript setup, build configuration |
| development-testing-and-publishing.md | Dev workflow, testing, publishing, troubleshooting |
| api-globals-and-nodes.md | Global objects, node types, components |
| api-rendering-and-advanced.md | Paints, effects, auto layout, styles, variables, events |
| ui-architecture-and-messaging.md | iframe UI, postMessage, typed messages, plain HTML |
| ui-react-and-theming.md | React setup, hooks, Figma theme colors |
| ui-patterns-and-resources.md | Loading states, tabs, color pickers, file downloads |
| selection-traversal-and-batching.md | Selection handling, node traversal, batch operations |
| colors-and-text.md | Color conversion, manipulation, text operations |
| layout-storage-and-utilities.md | Positioning, alignment, storage, error handling, utilities |
What ships with it
10 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/api-globals-and-nodes.md 8.3 KB
- references/api-rendering-and-advanced.md 7.9 KB
- references/colors-and-text.md 4.4 KB
- references/development-testing-and-publishing.md 6.0 KB
- references/layout-storage-and-utilities.md 7.8 KB
- references/project-structure-and-build.md 7.5 KB
- references/selection-traversal-and-batching.md 5.5 KB
- references/ui-architecture-and-messaging.md 7.0 KB
- references/ui-patterns-and-resources.md 6.4 KB
- references/ui-react-and-theming.md 5.5 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.
- 5d ago First seen · 46 lines · 38 tokens per session scan A 5a5c6cb02618
figma-plugin is a skill published in the GitHub repository bergside/design-md-figma (149 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 563 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
hatch3r-design-system-detect
Detects existing design tokens, component library, and theming convention in a project before authoring new UI primitives — output a concise inventory for downstream implementers.
ai-humanizer-zh
中文润色去AI味 助手适合市场营销、运营、内容创作者、产品在用户提出“怎么去AI味”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成AI 写作痕迹诊断、自然化改写稿、问题片段说明。.
ai-ab-testing
Skill "ai-ab-testing" from skillsaiagent/aiskills, covering ai-ab-testing a/b 测试设计助手, 概述, 什么时候使用, 调用方式 and 命令示例.
ai-accessibility
无障碍体验诊断助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这个页面好用吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成问题归因、服务改进建议、SOP 或 FAQ 清单。.
ai-account-research-sales-card
销售增长助手适合销售、市场营销、运营、产品在用户提出“客户为什么不推进”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。.
ai-account-research
客户研究助手适合市场营销、运营、software、教育培训在用户提出“这个客户怎么切入”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成销售策略、沟通素材、跟进计划。.