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/kyh/vibedgames/deploynpx skills add kyh/vibedgames --skill deploygit clone --depth 1 https://github.com/kyh/vibedgamesWhat 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 | $0.00079 | $0.01496 |
| Opus 5 | $0.00039 | $0.00748 |
| Sonnet 5 | $0.00016 | $0.00299 |
| Haiku 4.5 | $0.00008 | $0.00150 |
Grade A, and why
deploy 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibedgames Deploy
Deploy static browser games to {slug}.vibedgames.com using the vibedgames CLI.
vgnot on PATH? The global install fromvibedgames initis best-effort. If anyvg <cmd>below fails with "command not found", substitutenpx vibedgames <cmd>— it works identically.
Starting a new game
If the user has no project yet, scaffold one in a single command. vg new pulls the official engine template (or a minimal inline starter) and drops a vibedgames.json in place so deploy works without further config:
vg new my-game # Phaser 4 + Vite + TS (official phaserjs template)
vg new my-game --engine threejs # Three.js + Vite + TS starter
vg new my-game --engine react-r3f # React + R3F + drei + Vite + TS starter
vg new my-game --engine none # minimal Vite + TS + canvas (offline; no engine)
vg new my-game --template foo/bar # any github degit spec
Pick the engine that matches the game the user described:
- 2D / pixel-art / arcade / platformer →
phaser(the default) - 3D / first-person / camera-driven, imperative scene code →
threejs - 3D with React component model, declarative scenes, lots of UI overlay →
react-r3f - Custom engine, plain canvas, or "I'll wire the deps myself" →
none
After scaffold:
cd my-game
npm install
npm run dev # local preview
The matching skill (phaser, threejs, etc.) will load automatically in Claude Code based on the deps in package.json. Pass --here to scaffold into the current directory.
Prerequisites
The game directory must contain an index.html at the root. Typically this is the dist/ output from a build tool (Vite, webpack, etc.).
Deploy flow
1. Make sure the user is logged in
Always check auth before building or deploying. whoami exits non-zero
when unauthenticated:
vg whoami
If it prints Not logged in (or similar) or exits with an error, run
login before anything else:
vg login
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 First seen · 149 lines · 79 tokens per session scan A ceda4fbb08a4
deploy is a skill published in the GitHub repository kyh/vibedgames (55 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,496 once invoked, about $0.0004 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
supabase
Use when doing ANY task involving Supabase: Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues, supabase-js, @supabase/ssr, RLS, schema migrations, CLI, MCP server. Includes security checklist.
game-development
Game development patterns, architectures, and best practices.
react-hook-form
Correct React Hook Form usage anywhere in the monorepo — data flow, subscriptions, reset, dirty state, number inputs, and controlled-input rules. Load this BEFORE writing or modifying ANY form code, adding a field to an existing form, touching watch/useWatch/formState/getValues/setValue/reset, wiring a form into a…
safe-sql-execution
Use whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix and never says "security," "injection," or "SafeSqlFragment." This covers: writing or editing any pg-meta function, query builder, or endpoint…
studio-e2e-tests
Write and run Playwright E2E tests for Supabase Studio (e2e/studio). Use when asked to run e2e tests, write new E2E tests, or debug flaky or failing Playwright tests. Covers running commands, avoiding race conditions, waiting strategies, selectors, helper functions, and CI vs local differences.
studio-mock-api-tests
Component tests for Supabase Studio that mock API requests at the network layer with MSW. Use when writing or reviewing a component test that exercises a React Query hook or mutation, or when migrating an existing test away from vi.mock('@/data/...'). Covers the customRender + addAPIMock template and the jsdom/MSW…