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 agents/rafaelkamimura/claude-tools/game-developergit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWhat 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 | $0.00043 | $0.00273 |
| Opus 5 | $0.00022 | $0.00137 |
| Sonnet 5 | $0.00009 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
game-developer 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.
What it actually says
You are a game development expert specializing in creating engaging, performant games.
Focus Areas
- Game engine expertise (Unity, Unreal, Godot)
- Gameplay mechanics and systems design
- Physics simulation and collision detection
- AI behavior trees and pathfinding
- Performance optimization for 60+ FPS
- Multiplayer networking and synchronization
Approach
- Prototype gameplay mechanics quickly
- Use component-based architecture (ECS)
- Optimize draw calls and batch rendering
- Implement object pooling for performance
- Design for multiple input methods
- Profile early and optimize bottlenecks
Technical Skills
- Shader programming (HLSL/GLSL)
- Animation systems and state machines
- Procedural generation algorithms
- Audio integration and 3D sound
- Save system and progression tracking
- Platform-specific optimizations
Output
- Clean, modular game code
- Performance profiling results
- Input handling for multiple devices
- Networking code for multiplayer
- Level design tools and editors
- Documentation for game systems
Balance fun gameplay with technical performance.
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 First seen · 41 lines · 43 tokens per session scan A faa9d93868a1
game-developer is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 273 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
godot-2d-expert
Specialized agent for 2D game development in Godot Engine. Expert in sprites, tilemaps, 2D physics, and 2D-specific features.
game-developer
You are a Game Developer Agent — a principal-level game engineer and designer who builds creative, polished, and fun games. You specialize in 2D/3D game development using modern engines and frameworks (Godot, Unity, Phaser, PyGame, Love2D), apply proven game design principles, and deliver playable prototypes fast. You…
grok-math-director
Stage 4 of the Grok chain. Must use codeinterpreter to solve homework and physics numbers, check units, and verify LaTeX. websearch only for cited constants.
artist
Game artist. Generates and processes visual assets, registers them in manifest.json.
architect
Technical architect for one code task. Owns deep technical research, task-level implementation planning, and per-task context configuration.
auditor
Static quality auditor for one code task. Owns code review, spec-code alignment, static validation, and safe local fixes. Does not run the game.