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-testing-verificationgit 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-testing-verification)<a href="https://agentmods.dev/skills/german-krasnikov/unity-biome-mcp/unity-testing-verification"><img src="https://agentmods.dev/badge/skills/german-krasnikov/unity-biome-mcp/unity-testing-verification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 8 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.
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 | $0.01286 |
| Opus 5 | $0.00017 | $0.00643 |
| Sonnet 5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
unity-testing-verification 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Testing And Verification
Read .claude/skills/unity-mcp-operations/SKILL.md once if it is not already
loaded. Evidence must match the claim: data proves behavior; images prove
appearance.
Choose The Smallest Test
| Goal | Use |
|---|---|
| Focused EditMode or PlayMode NUnit run | One correlated run_tests_wait(...) call |
| Explicit nonblocking dispatch or recovery | run_tests, then the exact get_test_run(run_id=...) |
| One repeatable runtime scenario | lint_playtest, then run_playtest |
| Several saved scenarios | lint_playtest_suite, then run_playtest_suite |
| One bounded runtime condition | wait_until after enabling RUNTIME |
| Invoke one public runtime action | invoke_method |
| Read several runtime values | query_state |
| Inspect appearance | Screenshot or frame capture plus separate state evidence when behavior matters |
Follow the consumer project's own test-framework version, fixture hierarchy, and cleanup conventions. Keep every test independent, use bounded waits, restore state it owns, and retain the exact failure output. Do not import Unity Biome MCP's repository fixtures or CI commands into another project.
Use set_property for supported serialized Edit Mode changes. Do not assume it
can mutate arbitrary Play Mode state; expose a bounded public action and call
invoke_method, or express the action in Playtest DSL.
NUnit Workflow
Use one blocking wrapper call for an ordinary run:
run_tests_wait(
mode="EditMode",
filter="InventoryTests",
timeout=300
)
Accept a verdict only from the terminal result returned for that logical run. Keep failing test names, expected and actual values, and stack traces. A caller timeout, disconnect, or partial result is not a pass.
Direct run_tests is low-level dispatch, not completion. Preserve its
request_id, run_id, and utf_guid. On START-UNKNOWN, resolve the original
request instead of starting another run. Once a run is dispatched, observe or
cancel that exact run_id; never create a replacement logical run. Do not
hand-roll this polling protocol for an ordinary test run.
What ships with it
6 files 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.
- 7d ago First seen · 143 lines · 34 tokens per session scan A 8c8d0598b3aa
unity-testing-verification is a skill published in the GitHub repository german-krasnikov/unity-biome-mcp (29 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,286 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
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
character-animation-qa
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
pie-testing
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.