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 kyh/vibedgames --skill game-uigit clone --depth 1 https://github.com/kyh/vibedgamesWrote 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/kyh/vibedgames/game-ui)<a href="https://agentmods.dev/skills/kyh/vibedgames/game-ui"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/game-ui/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/kyh/vibedgames/game-ui"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/game-ui.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 | $0.00106 | $0.01135 |
| Opus 5 | $0.00053 | $0.00567 |
| Sonnet 5 | $0.00021 | $0.00227 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
game-ui 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game UI
Build a game interface, not a web dashboard. The defining failure of
prompt-built game UI: nested cards, marketing-hero title screens, generic
dashboard styling, and web-app typography wrapped around a canvas.
Anti-patterns to reject on sight: stat cards in rounded boxes inside boxes,
a hero section with a tagline over the game, <h1>-styled headings in a HUD,
one-note purple/blue gradient panels.
Hierarchy follows gameplay priority: survival/status first, objective/progress second, immediate feedback third, flavor last. Prefer meters, icons, cooldown rings, badges, and compact clusters over labeled stat cards — a meter is read at glance-speed mid-dodge; a card is not.
HUD zoning
- Top-left: objective, wave, distance, timer, progress.
- Top-right: score, currency, combo, pause.
- Bottom-left/right: touch movement/action controls (mobile).
- Center: reserved for transient banners (wave start, combo, warnings) — never persistent chrome, never stacked banners over the play path.
- In-world (diegetic) where possible: target markers, off-screen threat indicators, damage numbers, prompts anchored to the thing itself.
- Keep all UI out of the play path — away from the player, threats, pickups, and the next decision.
Numbers that don't dance
- Fixed-width numeric containers for score, timer, ammo, speed, health:
tabular numerals (
font-variant-numeric: tabular-nums) or a monospace face. Changing values must never shift layout. - Test the longest likely value: max score,
MM:SStimer, multi-digit combo. No clipping, no wrap, no neighbor displacement. - Animate value changes briefly (count-up, meter fill, pulse) — a silently
incrementing corner number reads as broken (see
game-feel).
Color roles
One color = one meaning, everywhere: danger (damage, low health), reward (score, pickups), shield/defense, boost/power, objective, disabled. A limited status palette over neutral surfaces beats a rainbow. Critical states get two channels (color + shape/motion/sound) — never color alone.
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 · 94 lines · 106 tokens per session scan A bdb2b6a91257
game-ui is a skill published in the GitHub repository kyh/vibedgames (55 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,135 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
migrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.