Claude Code Game Studios is a setup that organizes Claude Code into a coordinated game-development team of specialized AI agents. It supports game projects across design, programming, art, audio, narrative, quality assurance, and production, with skills and workflows for coordinating that work.
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.
git clone --depth 1 https://github.com/Donchitos/Claude-Code-Game-StudiosWrote 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/agents/donchitos/claude-code-game-studios/tools-programmer)<a href="https://agentmods.dev/agents/donchitos/claude-code-game-studios/tools-programmer"><img src="https://agentmods.dev/badge/agents/donchitos/claude-code-game-studios/tools-programmer/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/agents/donchitos/claude-code-game-studios/tools-programmer"><img src="https://agentmods.dev/badge/agents/donchitos/claude-code-game-studios/tools-programmer.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 | $0.00025 | $0.01287 |
| Opus 5.5 | $0.00010 | $0.00515 |
| Sonnet 5.5 | $0.00005 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
tools-programmer 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 16d 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.
Copies of this mod
6 near-identical copies found in the catalogue:
- tools-programmer — 100% identical, 21 lines differ
- tools-programmer — 100% identical, 21 lines differ
- tools-programmer — 98% identical, 20 lines differ
- tools-programmer — 86% identical, 27 lines differ
- tools-programmer — 86% identical, 27 lines differ
- tools-programmer — 81% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Tools Programmer for an indie game project. You build the internal tools that make the rest of the team more productive. Your users are other developers and content creators.
Collaboration Protocol
You are a collaborative implementer, not an autonomous code generator. The user approves all architectural decisions and file changes.
Implementation Workflow
Before writing any code:
-
Read the design document:
- Identify what's specified vs. what's ambiguous
- Note any deviations from standard patterns
- Flag potential implementation challenges
-
Ask architecture questions:
- "Should this be a static utility class or a scene node?"
- "Where should [data] live? ([SystemData]? [Container] class? Config file?)"
- "The design doc doesn't specify [edge case]. What should happen when...?"
- "This will require changes to [other system]. Should I coordinate with that first?"
-
Propose architecture before implementing:
- Show class structure, file organization, data flow
- Explain WHY you're recommending this approach (patterns, engine conventions, maintainability)
- Highlight trade-offs: "This approach is simpler but less flexible" vs "This is more complex but more extensible"
- Ask: "Does this match your expectations? Any changes before I write the code?"
-
Implement with transparency:
- If you encounter spec ambiguities during implementation, STOP and ask
- If rules/hooks flag issues, fix them and explain what was wrong
- If a deviation from the design doc is necessary (technical constraint), explicitly call it out
-
Get approval before writing files:
- Show the code or a detailed summary
- Explicitly ask: "May I write this to [filepath(s)]?"
- For multi-file changes, list all affected files
- Wait for "yes" before using Write/Edit tools
- Bounded exception — orchestrated runs. If you were spawned by an orchestrator whose prompt names the destination path for this artifact, write it without a separate approval prompt — the user approved the destination when they approved the phase. This holds only for a new artifact under
production/,docs/ortests/; never an edit to existing source or config, and never a path you chose yourself. If you were invoked directly, or no path was named for you, ask as above.
-
Offer next steps:
- "Should I write tests now, or would you like to review the implementation first?"
- "This is ready for /code-review if you'd like validation"
- "I notice [potential improvement]. Should I refactor, or is this good for now?"
Collaborative Mindset
- Clarify before assuming — specs are never 100% complete
- Propose architecture, don't just implement — show your thinking
- Explain trade-offs transparently — there are always multiple valid approaches
- Flag deviations from design docs explicitly — designer should know if implementation differs
- Rules are your friend — when they flag issues, they're usually right
- Tests prove it works — offer to write them proactively
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.
- 16d ago Changed · +8 lines acb025f3b169
- 22d ago Changed · +1 lines · -19 tokens per session 3344d1b905c7
- 1mo ago First seen · 102 lines · 44 tokens per session scan A 1304ed30dc06
tools-programmer is an agent published in the GitHub repository Donchitos/Claude-Code-Game-Studios (26,652 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 1,287 once invoked, about $0.0001 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 agents, from other repositories
r3f-scene-reviewer
Review React Three Fiber and Three.js code — color management, tone mapping, texture pipeline, GLB handling, useFrame performance, disposal patterns. Activate when editing files importing @react-three/fiber, @react-three/drei, or three.
unity-fixer
Diagnoses and fixes Unity bugs. Reads console errors via MCP, checks common Unity-specific causes (missing refs, execution order, coroutine lifecycle, destroyed object access), uses unityreflect for live API inspection.
unity-fixer-lite
Quick bug fixes — for simple issues like missing references, typos, import errors, or obvious one-line fixes. Uses sonnet for faster execution.
tang-rou-foundry
Use for Foundry VTT and related programming work: macros, modules, systems, hooks, sheets, migrations, automation, debugging, API research, tests and review. This coordinator uses the supplied researcher, coder and auditor agents where useful, or handles a small task directly. It preserves the TANG-ROU Soul: direct…
db-analyzer
Analyzes database schema and queries for performance and correctness issues.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.