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 unreal-enginegit 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/unreal-engine)<a href="https://agentmods.dev/skills/metaspartan/cybara/unreal-engine"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/unreal-engine/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/unreal-engine"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/unreal-engine.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 | $0.00049 | $0.00706 |
| Opus 5 | $0.00024 | $0.00353 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
unreal-engine 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unreal Engine
Inspect first
- Locate the
.uprojectfile and read its engine association and enabled plugins. - Inspect
Source, project plugins,Config, target files, module build files, and nearby tests. - Determine whether the behavior belongs in C++, Blueprint, data assets, editor tooling, or configuration.
- Discover the installed editor and
RunUATorRunUBTentrypoint without assuming one platform path.
Never text-edit .uasset or .umap files. Use source changes, configuration, commandlets, or an engine-aware editor workflow.
Implementation rules
- Keep gameplay rules out of actors and widgets when a subsystem, component, or plain testable type is a better owner.
- Preserve reflection macros, module boundaries, object lifetime, replication authority, and thread affinity.
- Treat asset references and gameplay tags as contracts; verify renames and redirects.
- Avoid broad Blueprint reconstruction or resaves for a focused code change.
- Do not rely on hot reload as final verification after changing reflected types.
Verification
Use the project's existing scripts when present. Otherwise select the narrowest engine-native checks:
- Compile the affected target with Unreal Build Tool.
- Run relevant Automation Tests through the editor or command line.
- Use a command shaped like
UnrealEditor-Cmd <project> -ExecCmds="Automation RunTest <filter>;Quit" -ReportExportPath=<path> -unattended -nop4only after resolving the actual executable and test filter. - Use Automation Tool for build, cook, stage, package, deploy, or Gauntlet flows already supported by the project.
- Launch the correct map and exercise the changed player flow.
- Inspect logs for ensures, access violations, asset load failures, shader failures, and automation errors.
Headless automation and visual verification
- Drive editor automation with Python when no C++ change is needed:
UnrealEditor-Cmd <project.uproject> -run=pythonscript -script=<absolute script.py> -unattended -nop4 -nosplashafter resolving the real editor binary; enable the Python Editor Script Plugin first. - Keep each generated script small and split large scripts across several write or edit calls; a tool call cut off by the output limit loses its arguments.
- For visual checks, capture stills with
HighResShotconsole commands,unreal.AutomationLibrary.take_high_res_screenshot, or a Movie Render Queue job, writing PNG files to absolute paths. - Inspect every capture with the
imagetool, compare it with the requested result, fix, re-run, and inspect again before reporting. - Keep captures you reported to the user; write new versions to new file names.
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.
- 3d ago Changed · +8 lines d775fc14d1e2
- 7d ago First seen · 43 lines · 49 tokens per session scan A effbe9ec5c8d
unreal-engine is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 706 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.
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.
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.
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.