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 agentmods add skills/metaspartan/cybara/web-game-developmentnpx skills add metaspartan/cybara --skill web-game-developmentgit 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/web-game-development)<a href="https://agentmods.dev/skills/metaspartan/cybara/web-game-development"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/web-game-development.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00446 |
| Opus 5 | $0.00024 | $0.00223 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
web-game-development 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 2d 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
Web game development
Select the existing engine
Read package.json, source imports, renderer initialization, and asset loaders before editing. Preserve the chosen engine unless the user requests a migration.
- Phaser: scene-driven 2D games, sprites, tilemaps, cameras, and arcade or matter physics.
- Three.js: imperative 3D scene, camera, renderer, loaders, and render-loop control.
- React Three Fiber: React-owned composition around Three.js with explicit per-frame boundaries.
- Babylon.js: engine-managed 3D scenes, loaders, physics, GUI, and WebGPU or WebGL paths.
- PlayCanvas: component and entity workflows using the project's selected editor or engine package.
Implementation rules
- Use Bun for dependency and script commands.
- Keep simulation state separate from rendering objects and DOM UI.
- Map keyboard, pointer, touch, and controller input into explicit game actions.
- Handle resize, device pixel ratio, pause, visibility changes, audio unlock, and WebGL context loss.
- Keep text-heavy HUD and menus accessible and responsive.
- Bound texture resolution, geometry, particles, post-processing, and retained resources.
- Dispose GPU resources and listeners when scenes or components unload.
Verification
- Run the repository's typecheck, lint, and unit tests.
- Build the production bundle and inspect asset warnings and output size.
- Launch the real app in a browser rather than testing a detached mock.
- Exercise boot, loading, primary controls, pause and resume, scene transitions, failure and restart, and responsive resize.
- Capture screenshots from representative gameplay states.
- Check console errors, failed network requests, frame pacing, memory growth, and WebGL warnings.
- Repeat touch and safe-area checks when mobile browsers are supported.
Completion criteria
Report the engine, browser and viewport tested, player path, production build result, console state, screenshots, and measured performance limitations.
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.
- 2d ago First seen · 41 lines · 49 tokens per session scan A 628611223935
web-game-development is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 446 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
composio-webapp-testing
Skill "composio-webapp-testing" from KornLabs/truss, covering web application testing, decision tree: choosing your approach, example: using withserver.py, reconnaissance-then-action pattern and common pitfall.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…
web-browse
Open a REAL external web page so the user can see it in Kiro Crew's Browser panel. PRIMARY path is the browser MCP tool (drives the built-in native panel); playwright-cli is the fallback for remote/plain-browser sessions and for attached logged-in browsers. Use when the user wants to VIEW / verify / "show me" an…