unigine-simulation-engineer

unigine-simulation-engineer is a skill for Claude Code from qfoldit/Protein-Design-MCP. It costs 112 tokens per session (773 once invoked), scanned A, original, Apache-2.0.

A workflow for exporting a validated description of a 3D scene or simulation into UNIGINE 2, a game and simulation engine. It checks UNIGINE documentation before using API calls and can use experimental plugins when available.

In plain words
What is it for?
Use it to turn a Universal Assembly Graph—a structured description of objects and their relationships—into a UNIGINE scene while checking that the implementation matches the engine's documentation.
Why use it?
UNIGINE has less publicly known coding information than engines such as Unity or Unreal, so guessed class or method names are more likely to be wrong.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the qfoldit-skills plugin — 20 skills shipped together

Good fit Use it to turn a Universal Assembly Graph—a structured description of objects and their relationships—into a UNIGINE scene while checking that the implementation matches the engine's documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qfoldit/protein-design-mcp/unigine-simulation-engineer
Install

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.

Any agent
npx skills add qfoldit/Protein-Design-MCP --skill unigine-simulation-engineer
Clone the repo
git clone --depth 1 https://github.com/qfoldit/Protein-Design-MCP

Made for: Claude Code.

Or install qfoldit-skills, the plugin that ships this one along with the rest of its 20 skills.

Wrote 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.

agentmods badge for unigine-simulation-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer/github.svg)](https://agentmods.dev/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer)
Your own site
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer/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.

agentmods 80×15 button for unigine-simulation-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unigine-simulation-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.00773
Opus 5 $0.00056 $0.00387
Sonnet 5 $0.00022 $0.00155
Haiku 4.5 $0.00011 $0.00077

Measured 10d ago against content hash f6c51561885d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

unigine-simulation-engineer 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.

claude-skills/skills/unigine-simulation-engineer/SKILL.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unigine-simulation-engineer

Status: official pattern, partially unverified in this session. Based on the official unigine-engine/ai-docs GitHub organization (confirmed to exist) and official UNIGINE SDK 2.21 release notes (confirmed: AI-ready workflow, experimental MCPBridge Editor Plugin for text-prompt scene editing, DataBridge Plugin for external data/Python/ML connections). The exact current text of unigine-engine/ai-docs/CLAUDE.md was not re-verified line-by-line when this skill was last edited -- check the live repo before relying on specifics not stated here.

Core principle: verify against docs, don't guess

UNIGINE is far less represented in general LLM training data than Unreal/Unity, so a plausible-sounding but nonexistent class/method name is a real risk here specifically. Before writing any UNIGINE API call:

  1. If the project vendors ai_docs/ (from unigine-engine/ai-docs), search it for the class/method first.
  2. If not found, or ai_docs/ isn't present, say so explicitly and suggest cloning unigine-engine/ai-docs or checking https://developer.unigine.com/en/docs/latest -- do not invent a signature that "should" exist.

UAG -> UNIGINE mapping

Baseline from game-designer/references/uag_schema.md (mesh -> ObjectMeshStatic, light -> LightWorld/LightPoint, parent_child -> Node.setParent, physics_collision -> BodyRigid).

Two paths to realize a UAG in UNIGINE

  • Live scene editing (experimental): if the project has UNIGINE SDK 2.21+ with the MCPBridge Editor Plugin enabled, this is the closest UNIGINE equivalent to Unreal/Unity's live MCP control -- warn the user it's marked experimental by UNIGINE itself before using it in an important session.
  • Data-driven / digital-twin (DataBridge): the DataBridge Plugin connects a UNIGINE scene to external systems (sensors, robotics, Python, ML pipelines) -- this is the more natural fit for qFoldIT's science-skill outputs (e.g. streaming plant-growth indices into scene parameters live) rather than one-shot scene construction. Untested hypothesis in this codebase -- validate on one simple case (e.g. plant-growth output) before relying on it architecturally.

Read the full file on GitHub · 29 lines

Changes

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.

  1. 10d ago First seen · 29 lines · 112 tokens per session scan A f6c51561885d

Subscribe to this mod's changes

unigine-simulation-engineer is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 112 tokens to every session and 773 once invoked, about $0.0006 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.

Related

Other skills, from other repositories