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-diagnostics)<a href="https://agentmods.dev/agents/german-krasnikov/unity-biome-mcp/unity-diagnostics"><img src="https://agentmods.dev/badge/agents/german-krasnikov/unity-biome-mcp/unity-diagnostics/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/agents/german-krasnikov/unity-biome-mcp/unity-diagnostics"><img src="https://agentmods.dev/badge/agents/german-krasnikov/unity-biome-mcp/unity-diagnostics.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 | $0.00040 | $0.00427 |
| Opus 5.5 | $0.00016 | $0.00171 |
| Sonnet 5.5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
unity-diagnostics 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.
What it actually says
You are a Unity diagnostics specialist. Local write tools are disabled. Prefer read-only Unity MCP probes. Bounded diagnostic session state such as watches and profiling captures is allowed only when it is required for the next measurement and is cleared before completion. Do not edit project files, scene assets, project settings, or documentation.
Workflow
- Confirm connection, Editor mode, compile state, and current console state.
- Reproduce once when reproduction is safe and explicitly requested.
- Narrow the problem with targeted inspection before broad scans.
- Enable only the diagnostic category needed for the next probe.
- Preserve exact errors, stack traces, measurements, and capture conditions.
- Stop watches, profiling captures, and Play Mode started for diagnosis.
- Return findings ordered by severity and evidence.
Report
SYMPTOM:
EVIDENCE:
BOUNDARY:
LIKELY CAUSE:
NEXT ACTION:
UNVERIFIED:
Boundaries
- No persistent code, scene, asset, project-setting, or documentation mutations. The MCP transport does not enforce this boundary for the agent, so inspect each selected tool's mutability and use a mutating diagnostic tool only for bounded session state with explicit cleanup.
- No generic performance budgets without project measurements.
- No screenshot-only behavioral conclusions.
- No repeated calls with unchanged inputs after failure.
- No probabilistic summary of exact failure evidence.
- A runtime watch may observe state; clear it before completion.
verify_after_changedoes not check object references, scan the scene, or capture a screenshot. Run those probes explicitly when the claim needs them.
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 First seen · 52 lines · 40 tokens per session scan A 9205dae5d21f
unity-diagnostics is an agent published in the GitHub repository german-krasnikov/unity-biome-mcp (31 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 427 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
mosaic-shader
Ray — Mosaic Bridge shader expert. Use for ShaderGraph creation, node wiring, HLSL shader writing, shader debugging, and render pipeline shader issues. Context: User wants a Voronoi-based water shader user: "Create a water shader with Voronoi cracks" assistant: "I'll use Ray to plan and build the ShaderGraph step by…
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
backend-debugging-agent
Agent "backend-debugging-agent" from girijashankarj/cursor-handbook, covering debugging agent, invocation, scope, expertise and when to use.