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 sandbaseai/sandbase-skills --skill game-devgit clone --depth 1 https://github.com/sandbaseai/sandbase-skillsWrote 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/sandbaseai/sandbase-skills/game-dev)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/game-dev"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/game-dev/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/sandbaseai/sandbase-skills/game-dev"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/game-dev.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.01213 |
| Opus 5.5 | $0.00020 | $0.00485 |
| Sonnet 5.5 | $0.00010 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
game-dev 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 21d 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 Dev
Turn a game brief into a playable, visually coherent browser game. Keep the game code, deterministic asset processing, builds, and tests local. Use SandBase only for optional generative assets that the user requests.
Read the SandBase API map before generating concept art, textures, sprites, backgrounds, or other AI media.
Establish the build target
Before implementation, resolve only the choices that materially affect the architecture:
- genre, player goal, failure and success conditions;
- input methods and target devices;
- 2D or 3D presentation, camera, aspect ratio, and art direction;
- required mechanics, content scope, and accessibility expectations;
- supplied assets, rights restrictions, target repository, and delivery format.
Inspect the existing project and preserve its framework, package manager, engine, and conventions. For a new project, choose the smallest suitable stack: native canvas or a focused 2D engine for simple 2D games, and a WebGL engine such as Babylon.js for substantial 3D work. Do not replace an established engine merely because another is familiar.
Plan around risk
Write a compact implementation plan for work that spans more than one mechanic. Identify the riskiest slice first: physics feel, procedural generation, animation state, navigation, camera behavior, pointer lock, shaders, networking, asset import, or performance.
Define observable acceptance criteria for each slice. A criterion should describe something a player can see or do, not merely a class or file that exists.
Keep gameplay state and rules independent from the UI shell where practical. Separate input, simulation, rendering, audio, persistence, and scene transitions enough that each can be tested without rebuilding the entire game.
Build a playable vertical slice
Implement the smallest loop that demonstrates the intended experience:
- load into a valid starting state;
- accept the primary controls;
- update the world deterministically enough to debug;
- communicate goals, feedback, damage or progress, and end states;
- restart without a page reload or corrupted state.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago First seen · 94 lines · 50 tokens per session scan A 44eaefa3c059
game-dev is a skill published in the GitHub repository sandbaseai/sandbase-skills (201 stars, last pushed 22d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,213 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 2026-09-27.
Other skills, from other repositories
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
browser-use-cli
Drive a real browser from the shell with the browser-use CLI when a task needs page interaction, rendered DOM, or a logged-in session.
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply.…
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply.…
quantum-ground-state
A narrowly defined quantum solver for the ground-state energy of a two-quantum-bit Pauli Hamiltonian in a specified one-excitation sector. It uses a noiseless statevector VQE and checks the result against an exact calculation; VQE is a method that searches for a low-energy quantum state.