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/chav0/unityfigmamcp/setup-projectnpx skills add chav0/UnityFigmaMCP --skill setup-projectgit clone --depth 1 https://github.com/chav0/UnityFigmaMCPWhat 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 | $0.01219 |
| Opus 5 | $0.00066 | $0.00609 |
| Sonnet 5 | $0.00026 | $0.00244 |
| Haiku 4.5 | $0.00013 | $0.00122 |
Grade A, and why
setup-project 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Project — UnityFigmaMCP Environment Check
This skill runs a diagnostic sequence to verify that all parts of the UnityFigmaMCP bridge are properly configured and connected. It checks each layer of the stack and produces a clear status report with actionable next steps.
Why this matters
UnityFigmaMCP has three independent systems that need to be working together: the Figma API (token + network), the MCP sidecar server, and the Unity Editor plugin connected via SignalR. A problem in any layer blocks the entire workflow, and the symptoms can be confusing — so a structured check saves time.
Diagnostic sequence
Run these checks in order. Each step depends on the previous one succeeding, but continue through all steps even if some fail — the user needs the full picture.
Step 1 — Server, Figma token and Unity connection
Call status. One response covers three things:
figma.tokenConfigured/figma.tokenValid— whetherFIGMA_ACCESS_TOKENis set and actually works.tokenValidis true only after a real API call succeeded, so it catches expired and revoked tokens, not just missing ones.figma.usershows who it belongs to.unity.editorConnected— whether a Unity Editor is attached to the SignalR hub, plusunity.hubUrlfor the address the Editor plugin connects to.protocolVersionand ahintnaming the next concrete action when something is off.
If ready is true, both halves work. Otherwise note what failed and continue —
the remaining checks are still informative.
Step 2 — Unity Editor round-trip
Call unity_get_pipelines.
status already reported whether an Editor is registered on the hub, but this is the
first call that actually travels the full path — MCP → server → SignalR → Unity Editor
and back — and returns data the Editor had to produce. A connected-but-wedged Editor
(blocked on a modal dialog, mid-compile) shows up here and not in status.
Step 3 — Pipeline configuration
From the unity_get_pipelines response, check:
- Are there any pipelines configured?
- List each pipeline's ID and steps
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 · 115 lines · 131 tokens per session scan A 2e6e3a12213e
setup-project is a skill published in the GitHub repository chav0/UnityFigmaMCP (2 stars, last pushed 17d ago), licensed MIT. It adds 131 tokens to every session and 1,219 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 2026-08-31.
Other skills, from other repositories
figma-typings-audit
Upgrade @figma/plugin-typings and absorb what the new version exposes. Diffs the .d.ts between the installed and the target version (that package ships no changelog), sorts the changes into breakage / new API / silently-added fields, maps each onto the sandbox handlers, the hand-written Zod mirrors in shared, and the…
mcp-sdk-audit
Upgrade @modelcontextprotocol/server (the MCP TypeScript SDK v2) and prove the wire contract survived. The SDK is a runtime dependency whose breakage lands on the wire, not in the type checker — so this sorts each release by which SDK source files it touched (Figwright uses only the server + stdio slice of a…
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
figma-build
Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…
unity-runtime-bug-hunt
Unity Editor PlayMode 中のランタイム挙動不具合・例外・応答不能の原因特定スキル。uloop execute-dynamic-code でランタイム状態を広く浅くダンプし、JetBrains Rider debugger で狭く深く変数/BPヒットを観測する。TRIGGER when: (1) ユーザーのメッセージに PlayMode 実行時のランタイム例外スタックトレースが貼られている（NullReferenceException / TimeoutException / IndexOutOfRangeException 等）(2)…
recipe-chain-machine-count
Use when the user wants a moorestech item produced at a target throughput — whether they ask "how many machines" explicitly OR just state a desired production rate (per minute or per second) without mentioning machine count. The rate may be phrased per second (個/秒・毎秒N個) — convert to per minute (×60) before computing.…