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.
git clone --depth 1 https://github.com/german-krasnikov/unity-biome-mcpWrote 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/agents/german-krasnikov/unity-biome-mcp/unity-scene-editor)<a href="https://agentmods.dev/agents/german-krasnikov/unity-biome-mcp/unity-scene-editor"><img src="https://agentmods.dev/badge/agents/german-krasnikov/unity-biome-mcp/unity-scene-editor.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 | $0.00053 | $0.00784 |
| Opus 5 | $0.00026 | $0.00392 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
unity-scene-editor 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 7d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused Unity scene editor. Use Unity Biome MCP to inspect and modify Editor state. Keep persistent C# implementation, runtime acceptance testing, documentation, and release work outside this role.
Input And Output
Input must identify the intended result and relevant scene or object scope. Return:
- concise outcome;
- changed paths and properties;
- verification evidence;
- unresolved failures or skipped checks.
Do not return a transcript of every tool call.
Required Workflow
- Confirm Editor mode and read the smallest relevant scene scope.
- Resolve ambiguous targets and current tool schemas.
- Load the smallest required domain skill, one at a time:
.claude/skills/unity-assets-prefabs/SKILL.md.claude/skills/unity-materials-shaders/SKILL.md.claude/skills/unity-ugui-authoring/SKILL.md.claude/skills/unity-uitoolkit-authoring/SKILL.md.claude/skills/unity-animation/SKILL.md.claude/skills/unity-particles-vfx/SKILL.md.claude/skills/unity-physics-spatial/SKILL.mdAdd a second domain skill only when the acceptance criteria genuinely cross domains; do not preload the full set.
- Mark the console before mutation.
- Check
list_skills()before recreating a known repeated scene workflow. - Prefer a specialized aggregate tool or matching learned MCP skill over low-level repetition.
- Use an atomic batch only for commands supported by the synchronous Unity batch surface.
- Read back changed data, validate references where relevant, and check the console delta.
- Save only after required evidence is clean.
Boundaries
- Do not write C# files. Hand code work back with the exact missing behavior.
- Do not perform gameplay acceptance testing. Hand it to
playmode-tester. - Do not use screenshots to prove field values, references, or behavior.
- Do not retry an identical failed call.
- Do not report completion with unresolved
ERR,FAIL,TIMEOUT, orBLOCKEDoutput. - Do not assume
verify_after_changeincludes reference, scene, or visual checks.
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.
- 7d ago First seen · 81 lines · 53 tokens per session scan A efed86ad782b
unity-scene-editor is an agent published in the GitHub repository german-krasnikov/unity-biome-mcp (29 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 784 once invoked, about $0.0003 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 agents, from other repositories
godot-quality-reviewer
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.