Borrowing it
Nothing to install: this file belongs to chav0/UnityFigmaMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chav0/UnityFigmaMCP/main/.claude/skills/bind-figma-unity/SKILL.mdgit clone --depth 1 https://github.com/chav0/UnityFigmaMCPWrote 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/chav0/unityfigmamcp/bind-figma-unity)<a href="https://agentmods.dev/skills/chav0/unityfigmamcp/bind-figma-unity"><img src="https://agentmods.dev/badge/skills/chav0/unityfigmamcp/bind-figma-unity/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/chav0/unityfigmamcp/bind-figma-unity"><img src="https://agentmods.dev/badge/skills/chav0/unityfigmamcp/bind-figma-unity.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 | $0.00106 | $0.01294 |
| Opus 5.5 | $0.00042 | $0.00518 |
| Sonnet 5.5 | $0.00021 | $0.00259 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
bind-figma-unity 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 1mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bind Figma–Unity — Component & Sprite Matching
Binding means linking Figma objects to Unity assets that already exist. It does not
download, create, or rebuild anything — it only writes entries in the component map
and sprite map so that unity_build_prefab can reuse them instead of rebuilding subtrees.
When to use (opt-in only)
Do not run this skill unless the user asks to bind, map, or link assets.
It is not a step before /build-prefab. The pipeline already registers keys
when you download sprites and build prefabs.
Use it only when:
- The user explicitly asks to bind / map / link Figma to existing Unity assets
- You are working with an old UI kit: prefabs and sprites already live in the project, but they were made without Figma keys and are not connected to Figma components
Do not re-bind assets that already have a figmaKey.
Input
The user needs to provide:
- Figma file key — the key from the Figma URL
- Node ID — the root node to scan (a page, frame, or component set)
If the user gives a Figma URL, extract the file key and node ID from it.
Workflow
Step 1 — Fetch the Figma tree
Call figma_get_node with the file key and node ID to download the full subtree.
Then call figma_get_node_names to get the slim hierarchy for analysis.
Step 2 — Get existing Unity assets
Call unity_list_assets twice in parallel:
kind: "prefab"— all prefabs with their names, paths, and existing bindingskind: "sprite"— all sprites with their names, paths, and existing bindings
Each entry carries a figmaKey — null means the asset is not bound yet.
Step 3 — Match by name
Walk the Figma node tree and collect components, component sets, and image/icon nodes. For each, try to find a matching unbound Unity asset by name:
- Normalize both names (lowercase, strip spaces/hyphens/underscores) for comparison
- A Figma component "Button / Primary" should match a prefab "ButtonPrimary", "button-primary", "Button_Primary", etc.
- Skip assets that already have a
figmaKey
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.
- 1mo ago Changed · +15 lines 4dde5c7ef8ed
- 2mo ago First seen · 129 lines · 106 tokens per session scan A ec1c8621904c
bind-figma-unity is a skill published in the GitHub repository chav0/UnityFigmaMCP (11 stars, last pushed 25d ago), licensed MIT. It adds 106 tokens to every session and 1,294 once invoked, about $0.0004 per session on Opus 5.5. 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.
bind-figma-unity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bind-figma-unitychav0/UnityFigmaMCP | Skill | 11 | 25d ago | MIT | A | 106 | Claude Code |
| figma-codegenawdr74100/figwright | Skill | 1.3k | yesterday | MIT | A | 145 | Claude Code, Codex |
| figma-buildawdr74100/figwright | Skill | 1.3k | yesterday | MIT | A | 180 | Claude Code, Codex |
| biome-creationmoorestech/moorestech | Skill | 85 | today | Apache-2.0 | A | 170 | Claude Code |
| before-after-auditmoorestech/moorestech | Skill | 85 | today | Apache-2.0 | A | 81 | Claude Code |
| vibefigmavibeflowing-inc/vibe_figma | Skill | 849 | 28d ago | AGPL-3.0 | A | 77 | Claude Code, Codex |
| design-pipelinesodam-ai/SoDam-Design-Kit | Skill | 7 | 4d ago | Apache-2.0 | A | 77 | Claude Code |