awesome-gamedev-agent-skills is a collection of 73 instruction files that give AI coding agents specialized guidance for game development with engines and frameworks such as Godot, Unity, Unreal, and Phaser. It helps agents choose relevant engine and task guidance while building games. The catalogue entries are the collection's skills and plugins for agents including Claude Code, Cursor, Codex, and Gemini CLI.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gamedev-skills/awesome-gamedev-agent-skillsnpx agentmods add skills/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-gameWrote 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/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-game)<a href="https://agentmods.dev/skills/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-game"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-game/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/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-game"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/ebitengine-game.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 | $0.00108 | $0.02571 |
| Opus 5.5 | $0.00043 | $0.01028 |
| Sonnet 5.5 | $0.00022 | $0.00514 |
| Haiku 4.5 | $0.00011 | $0.00257 |
Grade A, and why
ebitengine-game 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 today.
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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ebitengine game
Deliver a game that is understandable, responsive and complete at the requested scope. One request can include several internal build/play/refine passes. A scaffold, successful build or attractive screenshot alone is not a finished game. For a focused fix, preserve the project's design and limit the workflow to the affected behavior.
The bundled starter targets Ebitengine v2.10.5 / Go 1.25+. This is a pinned baseline, not a claim about the latest release. Keep an existing project's versions unless an upgrade is needed and authorized. Check the pinned version's public API before using newer or experimental APIs. References contain patterns to adapt; only the bundled scripts and starter are executable deliverables. Their checks do not validate every reference snippet.
Delivery workflow
- Inspect and decide. Read repository instructions,
go.mod, theRunGameentrypoint and existing tests/assets. For new games, read Design and quality. Establish the player's goal, repeated decision, consequence, end/retry path, intended look, platform and supported input. Infer reasonable defaults; ask only for missing choices that materially change the product. Record a short brief and observable acceptance criteria in the project. - Build a representative playable slice. Make the central interaction and its feedback work with the intended controls and visual direction. Check the feel before expanding content. Keep scope small enough to finish; choose authored or procedural content based on the game, not the template. Calibrate content against actual player capabilities before multiplying levels. For an art set, establish shared perspective, scale, anchors and palette roles using Assets and animation.
- Complete and refine. Implement the promised start → play → outcome → retry/continue loop (or the appropriate persistent/sandbox loop). Refine hierarchy, animation, sound, difficulty and transitions in context. Read only the technical references needed for the selected systems. Fix discovered defects within this delivery rather than asking the user to iterate for you.
- Verify the product. Test rules and important transitions, exercise real input, inspect representative rendered states, and build/run requested targets. Include failure/retry and boundary cases. A scripted demo cannot establish control feel; a silent audio sink cannot establish sound quality. For automated multi-step interactions, pair observed images with actual state at the same tick; see Playtest diagnostics.
- Hand off. Supply launch/build instructions, actual artifact paths and asset licences. State what was run and observed, what remains unverified, and any material limitations. Publishing, purchases and external uploads are separate actions within the user's requested scope.
What ships with it
30 files 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.
- agents/openai.yaml 207 B
- assets/ci/github-actions.yml 5.1 KB
- assets/starter/assets.go 1.7 KB
- assets/starter/game.go 2.5 KB
- assets/starter/input.go 3.1 KB
- assets/starter/licenses/Go-Fonts.txt 1.9 KB
- assets/starter/main.go 1.7 KB
- assets/starter/scenes.go 5.8 KB
- assets/starter/sound.go 1.7 KB
- assets/starter/web/index.html 917 B
- assets/starter/world/world_test.go 3.6 KB
- assets/starter/world/world.go 4.6 KB
- references/architecture-and-testing.md 11 KB
- references/assets-and-animation.md 4.2 KB
- references/audio.md 6.8 KB
- references/ci-and-release.md 4.1 KB
- references/design-and-quality.md 8.0 KB
- references/gameplay-systems.md 12 KB
- references/input.md 9.0 KB
- references/monetization.md 5.4 KB
- references/networking.md 7.3 KB
- references/playtest-diagnostics.md 3.8 KB
- references/project-and-builds.md 7.4 KB
- references/publishing-and-platforms.md 6.6 KB
- references/rendering.md 11 KB
- references/text-and-ui.md 14 KB
- references/tilemaps.md 12 KB
- scripts/check_ebitengine.py 16 KB runs code
- scripts/new_game.py 6.4 KB runs code
- scripts/package_macos_app.py 8.7 KB runs code
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.
- today First seen · 207 lines · 108 tokens per session scan A bbd4d03e12b5
ebitengine-game is a skill published in the GitHub repository gamedev-skills/awesome-gamedev-agent-skills (3,490 stars, last pushed yesterday), licensed Apache-2.0. It adds 108 tokens to every session and 2,571 once invoked, about $0.0004 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 2026-10-24.
Other skills, from other repositories
script-execute
Compiles and runs C# in the Unity Editor (Roslyn): plain statements with the last expression as the result, or a full class with a static method. See the skill body for the modes, usings/include and Unity object parameters.
script-delete
Delete one or more .cs script files from disk, refresh the AssetDatabase, and wait for Unity compilation to settle before delivering the final result via the request's requestId. Pair with 'script-read' to inspect files before deletion.
script-read
Read a .cs script file and return its content as a string. Supports a 1-based lineFrom/lineTo slice for partial reads. Pair with 'script-update-or-create' to write back.
script-update-or-create
Write a .cs script file (create or overwrite) with the provided C# code. Validates syntax via Roslyn before write — invalid code is rejected with error details and the file is left untouched. Refreshes the AssetDatabase and delivers the final result via requestId after Unity finishes the triggered compilation. Use…
golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.