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 metaspartan/cybara --skill unitygit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/unity)<a href="https://agentmods.dev/skills/metaspartan/cybara/unity"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/unity/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/skills/metaspartan/cybara/unity"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/unity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00477 |
| Opus 5 | $0.00022 | $0.00238 |
| Sonnet 5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
unity 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity
Inspect first
- Read
ProjectSettings/ProjectVersion.txt,Packages/manifest.json, and relevant assembly definitions. - Locate the owning scripts, scenes, prefabs, ScriptableObjects, input actions, tests, and build scripts.
- Determine the active render pipeline and scripting backend without changing either.
- Discover the matching Unity Editor executable through the project or Unity Hub installation.
Preserve .meta files and GUID references. Avoid bulk text edits to scenes, prefabs, animation clips, and serialized assets when an editor-aware path is available.
Implementation rules
- Keep domain logic testable outside
MonoBehaviourwhere practical. - Keep frame-rate-independent simulation in the correct update loop.
- Preserve serialization compatibility when renaming fields or types.
- Respect assembly definition boundaries and package versions.
- Avoid repeated allocations, scene-wide searches, and unnecessary component lookup in hot paths.
- Do not trigger an automatic project or package upgrade unless requested.
Verification
Use existing project scripts first. For unattended validation, resolve the actual editor binary and use batch mode with explicit paths and logs.
- Run EditMode tests for pure and editor-owned behavior.
- Run PlayMode tests for scene, lifecycle, physics, and integration behavior.
- Use
-batchmode -projectPath <project> -runTests -testPlatform <platform> -testResults <xml> -logFile <log> -quitonly with the project's supported Unity Test Framework setup. - Run the established build method or build profile.
- Launch a player build and exercise the changed flow.
- Inspect editor and player logs rather than relying only on exit code.
Performance
Profile a representative scene on the target device. Separate main thread, render thread, jobs, garbage collection, draw calls, overdraw, shader variants, asset loading, and memory. Confirm optimizations in a development player rather than only in the editor.
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.
- 10d ago First seen · 44 lines · 44 tokens per session scan A 35e16997bb2f
unity is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 477 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 2026-09-03.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
superpowers-test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
ecc-agent-eval
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.
composio-webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
electron-testing
Autonomously plan, run, and assess evidence-driven tests for Electron applications. Use after implementing or refactoring Electron behavior, when reproducing an issue, or when validation crosses main, preload, renderer, IPC, multi-window, lifecycle, packaged-runtime, or native desktop boundaries. Select the smallest…
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.