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 game-playtestinggit 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/game-playtesting)<a href="https://agentmods.dev/skills/metaspartan/cybara/game-playtesting"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/game-playtesting/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/game-playtesting"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/game-playtesting.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 | $0.00048 | $0.00405 |
| Opus 5.5 | $0.00019 | $0.00162 |
| Sonnet 5.5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
game-playtesting 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 1mo 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
Game playtesting
Establish the test contract
Identify the engine, build, target platform, expected controls, core loop, success and failure states, save behavior, and performance target. Use a development or instrumented build when possible, then repeat critical checks in a shipping-shaped build.
Verification journey
- Start from a clean launch and observe loading, first frame, and actionable state.
- Exercise every primary input and confirm visible and audible feedback.
- Complete one representative gameplay loop.
- Trigger damage, failure, pause, resume, restart, scene transition, and quit paths that apply.
- Save, reload, and verify state boundaries.
- Resize, background, restore, disconnect, or change input devices where supported.
- Repeat the riskiest path after a warm reload to catch leaked state.
Visual and interaction checks
- HUD readability and playfield obstruction
- Camera bounds, clipping, jitter, and reset behavior
- Animation transitions and collision alignment
- Loading placeholders and asset pop-in
- Keyboard, pointer, controller, and touch focus ownership
- Menus that pause or release gameplay input correctly
- Text scaling, localization expansion, safe areas, and color contrast
- Screenshot consistency at important checkpoints
Performance checks
Capture frame time rather than only average frames per second. Watch CPU, GPU, memory, allocations, asset streaming, shader compilation, loading, network stalls, and long-session growth. Reproduce spikes at the same gameplay checkpoint before diagnosing them.
Findings
Report issues by severity with exact build, platform, starting state, steps, actual result, expected result, frequency, evidence, and likely owning subsystem. Separate confirmed defects from observations that need a profiler or target 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.
- 1mo ago First seen · 40 lines · 48 tokens per session scan A 4e6a7294119f
game-playtesting is a skill published in the GitHub repository metaspartan/cybara (32 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 405 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
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.
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders…
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite…
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
01-acceptance-qa
Validate a reviewed candidate's observable behavior against its acceptance criteria and record short named videos as reviewer evidence. Use when acceptance criteria exist and a browser-observable journey needs proof it holds. Do NOT use for diff review, unit or integration tests, or application fixes.