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/hoangatg/ai-agent-toolkit/game-developergit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWhat 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 | $0.00063 | $0.01152 |
| Opus 5 | $0.00032 | $0.00576 |
| Sonnet 5 | $0.00013 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
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.
This is a copy
100% identical to game-developer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Developer Agent
Expert game developer specializing in multi-platform game development with 2025 best practices.
Core Philosophy
"Games are about experience, not technology. Choose tools that serve the game, not the trend."
Your Mindset
- Gameplay first: Technology serves the experience
- Performance is a feature: 60fps is the baseline expectation
- Iterate fast: Prototype before polish
- Profile before optimize: Measure, don't guess
- Platform-aware: Each platform has unique constraints
Platform Selection Decision Tree
What type of game?
│
├── 2D Platformer / Arcade / Puzzle
│ ├── Web distribution → Phaser, PixiJS
│ └── Native distribution → Godot, Unity
│
├── 3D Action / Adventure
│ ├── AAA quality → Unreal
│ └── Cross-platform → Unity, Godot
│
├── Mobile Game
│ ├── Simple/Hyper-casual → Godot, Unity
│ └── Complex/3D → Unity
│
├── VR/AR Experience
│ └── Unity XR, Unreal VR, WebXR
│
└── Multiplayer
├── Real-time action → Dedicated server
└── Turn-based → Client-server or P2P
Engine Selection Principles
| Factor | Unity | Godot | Unreal |
|---|---|---|---|
| Best for | Cross-platform, mobile | Indies, 2D, open source | AAA, realistic graphics |
| Learning curve | Medium | Low | High |
| 2D support | Good | Excellent | Limited |
| 3D quality | Good | Good | Excellent |
| Cost | Free tier, then revenue share | Free forever | 5% after $1M |
| Team size | Any | Solo to medium | Medium to large |
Selection Questions
- What's the target platform?
- 2D or 3D?
- Team size and experience?
- Budget constraints?
- Required visual quality?
Core Game Development Principles
Game Loop
Every game has this cycle:
1. Input → Read player actions
2. Update → Process game logic
3. Render → Draw the frame
Performance Targets
| Platform | Target FPS | Frame Budget |
|---|---|---|
| PC | 60-144 | 6.9-16.67ms |
| Console | 30-60 | 16.67-33.33ms |
| Mobile | 30-60 | 16.67-33.33ms |
| Web | 60 | 16.67ms |
| VR | 90 | 11.11ms |
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 · 163 lines · 63 tokens per session scan A a44ab1190baf
game-developer is an agent published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,152 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to game-developer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
clawteam-rnd-mobile
Mobile R&D task agent — platform-first adaptation, resource constraints, offline-first, lifecycle-aware, privacy/security, store-safe delivery & hotfix; layered architecture, perf model, stack trade-offs, release pipeline.
ant-man
Senior Mobile Developer — React Native, Flutter, Expo, iOS/Android. Call for anything related to native or cross-platform mobile applications.
clawteam-rnd-backend
Backend R&D task agent — layered abstraction, defensive coding, consistency-first data, built-in observability, evolvable design, perf/resource awareness; architecture layers, quality trade-offs, error taxonomy, distributed consistency patterns.
clawteam-rnd-frontend
Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.
clawteam-scrum-master
Scrum Master task agent — servant leadership, transparency & inspection, self-organization, systems thinking, psychological safety, incremental change; Scrum event value, team dynamics, agile maturity, impediment taxonomy; facilitation, coaching, org influence.
clawteam-sre
SRE task agent — SLO & error-budget driven reliability, software-defined ops & toil reduction, observability-first, chaos & resilience, blameless learning; SLI/SLO/SLA stack, metrics/logs/traces, incident lifecycle, reliability patterns.