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 godotgit 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/godot)<a href="https://agentmods.dev/skills/metaspartan/cybara/godot"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/godot/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/godot"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/godot.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 | $0.00046 | $0.00469 |
| Opus 5 | $0.00023 | $0.00234 |
| Sonnet 5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
godot 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 9d 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
Godot
Inspect first
- Read
project.godotand identify the renderer, entry scene, input map, autoloads, and engine features. - Inspect the owning scenes, scripts, resources, addons, tests, and export presets.
- Determine whether the project uses GDScript, C#, GDExtension, or a mixture.
- Resolve
godot,godot4, or the platform application binary instead of assuming one name.
Implementation rules
- Keep reusable behavior in scripts and resources with explicit scene ownership.
- Preserve node paths, signal contracts, resource identifiers, and autoload APIs.
- Avoid hand-rewriting large scene or resource files when an engine-aware edit is safer.
- Keep
_processand_physics_processresponsibilities distinct. - Free transient nodes and disconnect long-lived signals when ownership requires it.
- Do not change renderer or project feature versions unless requested.
Verification
Use project-provided test addons and scripts before inventing a test command.
- Parse focused scripts with
godot --headless --path <project> --check-only --script <script>when supported by the script shape. - Import resources with
godot --headless --path <project> --editor --quitwhen imports changed. - Run the project's GDScript, C#, or addon test suite.
- Run a focused scene or the main project and inspect engine output.
- Export with the existing preset using
--headless --path <project> --export-release <preset> <output>when release output is in scope. - Exercise the changed flow in a rendered build.
Performance
Measure CPU, GPU, physics, draw calls, node count, memory, resource loading, and stutter in the engine profiler. Test the selected renderer and target device; headless execution cannot validate rendering.
Completion criteria
Report Godot version, renderer, scripts or scenes checked, test runner, export preset, rendered flow, and any unavailable platform template or device.
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.
- 9d ago First seen · 42 lines · 46 tokens per session scan A 6d98069e1b6c
godot is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 469 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.