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 skills add german-krasnikov/unity-biome-mcp --skill unity-diagnostics-performancegit 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/skills/german-krasnikov/unity-biome-mcp/unity-diagnostics-performance)<a href="https://agentmods.dev/skills/german-krasnikov/unity-biome-mcp/unity-diagnostics-performance"><img src="https://agentmods.dev/badge/skills/german-krasnikov/unity-biome-mcp/unity-diagnostics-performance.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 85 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Agent Snooping · line 9 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 16 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00034 | $0.00772 |
| Opus 5 | $0.00017 | $0.00386 |
| Sonnet 5 | $0.00007 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
unity-diagnostics-performance 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 8d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Diagnostics And Performance
If it is not already loaded, read
.claude/skills/unity-mcp-operations/SKILL.md once. Diagnose from the cheapest
deterministic signal to the most expensive probe. Enable VERIFY, RUNTIME,
or MEDIA only when needed.
Diagnostic Ladder
mcp_statusfor connection and mode.await_compile(timeout=0)for compile state and corroborated errors.console_mark, reproduce once, thenget_console_since(mark_id=...).- Targeted hierarchy or component inspection.
scan_scene,scene_health, or domain-specific diagnostics.verify_after_change(...)when a completed change needs compile checks plus explicitly requested console, NUnit, or playtest gates.- Runtime snapshot, watch, frame statistics, or profile in Play Mode.
- Screenshot only for a visual symptom.
console_mark()
# reproduce once
get_console_since(mark_id="<exact returned token>")
runtime_snapshot(type="FeatureController", name="Subject", compress=True)
watch(
action="add",
path="/Subject",
component="FeatureController",
field="state",
condition="== Error",
trigger_action="log"
)
get_watches()
watch(action="clear")
Performance
- Establish the scenario and baseline before profiling.
- Use
get_frame_statsfor a compact snapshot, thenprofilefor a bounded capture when the snapshot indicates a problem. - Compare like-for-like Editor state, camera, scene, and time scale.
- Separate CPU, allocation, rendering, memory, and loading claims.
- Report measured values and capture conditions, not generic budgets.
Specialized Probes
| Symptom | Prefer |
|---|---|
| Animator state or transition | debug_animator |
| Rigidbody or collider behavior | debug_physics |
| Navigation or pathfinding | navmesh_query |
| Rendering or overdraw | render_analyze |
| Many runtime fields | query_state or runtime_snapshot |
| One changing field | a bounded watch, then clear it |
| Serialized field rename safety | serialized_field_rename_audit |
| Scene integrity check | scene_health(focus="...") with options: all, hierarchy, naming, duplicates, origins, missing, empty, or disabled |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 86 lines · 34 tokens per session scan A ccf2810c227e
unity-diagnostics-performance is a skill published in the GitHub repository german-krasnikov/unity-biome-mcp (29 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 772 once invoked, about $0.0002 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 skills, from other repositories
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
jahro-troubleshooting
Diagnoses common Jahro issues using decision trees: commands not appearing, watcher not updating, console not opening, snapshots failing, launch button missing. Use when the user reports something not working, missing, broken, or unexpected with Jahro, or when generated Jahro code doesn't behave as expected.
jahro-watcher
Analyzes C# fields and properties and generates [JahroWatch] attributes with groups and performance-safe patterns. Use when the user wants to monitor variables at runtime, add watchers, track game state, replace Debug.Log polling, or mentions JahroWatch, real-time inspection, or variable monitoring.
jahro-production
Configures Jahro lifecycle controls for safe production deployment including JAHRODISABLE, auto-disable, and build validation. Use when the user mentions production builds, release builds, disabling Jahro, shipping, CI/CD, lifecycle controls, or production safety.
mosaic-shader
Ray — Mosaic Bridge shader expert. Use for ShaderGraph creation, node wiring, HLSL shader writing, shader debugging, and render pipeline shader issues. Use when the user says "create a shader", "ShaderGraph", "Voronoi", "water shader", or "shader is not compiling".
godot-auditor
Godot Expert Auditor: Aurelius. Exhaustive never-list enforcement and architectural slap-down for Godot 4.7 projects.