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
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 gamedev-skills/awesome-gamedev-agent-skills --skill card-gamegit clone --depth 1 https://github.com/gamedev-skills/awesome-gamedev-agent-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/gamedev-skills/awesome-gamedev-agent-skills/card-game)<a href="https://agentmods.dev/skills/gamedev-skills/awesome-gamedev-agent-skills/card-game"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/card-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/card-game"><img src="https://agentmods.dev/badge/skills/gamedev-skills/awesome-gamedev-agent-skills/card-game.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00054 | $0.01770 |
| Opus 5.5 | $0.00022 | $0.00708 |
| Sonnet 5.5 | $0.00011 | $0.00354 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
card-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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Card Game
A playbook for card games — card data, the deck/hand/discard zones, the turn structure, and how card effects resolve. This is a compositional skill: it models cards as data and wires them to UI. It does not re-teach data assets or UI nodes; it defines the zone model, the draw machinery, and the effect-resolution rules that keep a card game correct and bug-free.
When to use
- Use when building any game where the core objects are cards moving between zones (deck → hand → play → discard): deckbuilder, TCG/CCG, solitaire, roguelike deckbuilder.
- Use when designing draw/shuffle/reshuffle, turn structure, card costs, or how effects resolve.
When not to use: board/tile state with matching rules → puzzle. RPG with an
incidental card battler → start from rpg. For defining cards as assets, use godot-resources
/ unity-scriptableobjects; for the hand/drag UI, use godot-ui-control.
Core loop
Draw to your hand → spend resources to play cards → effects resolve and change the board → end the turn (cleanup/discard) → opponent/next phase → repeat until a win condition. Depth comes from the combinations a hand allows; the engine's job is to resolve them unambiguously.
Must-have systems
- Card data — id, name, cost, type, text, and an effect spec (data, not code).
- Zones — deck (draw pile), hand, play/board, discard, exile/removed; cards live in exactly one.
- Draw + shuffle + reshuffle — draw from deck to hand; reshuffle discard into deck when empty.
- Turn structure — phases (untap/draw/main/combat/end) as a state machine.
- Resource system — mana/energy/actions that gate how much you do per turn.
- Effect resolution — apply a card's effects in a defined order; handle targets and triggers.
- Win/loss condition — life total, deck-out, objective.
- UI — hand layout, drag/drop or tap-to-play, zone counts, targeting affordances.
Design knobs
| Knob | Effect | Notes |
|---|---|---|
| Starting hand / draw-per-turn | tempo, consistency | More draw = less variance. |
| Hand size limit | hoarding vs. use | Discard down at end of turn. |
| Deck size (min) | consistency | Smaller = more reliable combos. |
| Resource curve | what's playable when | "Mana curve" paces power. |
| Card rarity / power budget | balance | Stronger cards cost more / are rarer. |
| Determinism vs. randomness | skill vs. swing | Shuffle + random effects add variance. |
| Reshuffle rules | deck-out, fatigue | Reshuffle discard, or punish empty deck. |
| Removal / answers | counterplay | Every threat needs an answer in the pool. |
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.
- 2d ago Changed · +7 lines cc9b25b66e71
- 1mo ago First seen · 132 lines · 54 tokens per session scan A 1d9729293332
card-game is a skill published in the GitHub repository gamedev-skills/awesome-gamedev-agent-skills (4,867 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,770 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 2026-08-30.
Other skills, from other repositories
editor-session-quit
Save and quit an editor that a CLI session started (unity-mcp-cli exec, open --headless). Needs the session lease nonce; an editor the user opened is never closed. Used by unity-mcp-cli close.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
dialogue-manager
Use when using the Dialogue Manager addon — .dialogue files with titles, responses, conditions and mutations, runtime balloons, and C# support.
event-bus
Use when implementing decoupled communication between nodes — global EventBus autoload with typed signals.
physics-system
Use when working with physics bodies, collision shapes, raycasting, areas, rigid bodies, ragdolls, soft bodies, Jolt physics, and physics interpolation in Godot 4.3+.
biome-detail-tuning
Configure and tune Unity Terrain detail (grass/flower/fern) placement for MapGenerator biomes using prefabs and noise-driven clustering. Covers the full workflow from prefab selection through noise parameter tuning to external audit verification and performance optimization. Use when: setting up detail for any biome…