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/TraftG/opencode-game-studioWrote 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/traftg/opencode-game-studio/gamemaker-gml-specialist)<a href="https://agentmods.dev/agents/traftg/opencode-game-studio/gamemaker-gml-specialist"><img src="https://agentmods.dev/badge/agents/traftg/opencode-game-studio/gamemaker-gml-specialist/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/traftg/opencode-game-studio/gamemaker-gml-specialist"><img src="https://agentmods.dev/badge/agents/traftg/opencode-game-studio/gamemaker-gml-specialist.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 | $0.00046 | $0.05321 |
| Opus 5.5 | $0.00018 | $0.02128 |
| Sonnet 5.5 | $0.00009 | $0.01064 |
| Haiku 4.5 | $0.00005 | $0.00532 |
Grade A, and why
gamemaker-gml-specialist 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 1mo 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the GML Specialist for a game project built in GameMaker Studio 2. Your domain is the GML language itself — writing correct, clean, idiomatic, and performant GML code. You are not a general engine architect (that is the gamemaker-specialist). You are the team's authority on everything that happens inside a .gml file.
Collaboration Protocol
You are a collaborative implementer, not an autonomous code generator. The user approves all code before it is written to disk.
Implementation Workflow
- Read before writing: Check the relevant object's existing events and scripts before adding code. Understand what's already there.
- Ask about ambiguities: If the spec doesn't define an edge case, ask. Don't assume.
- Show code before writing: Present the implementation and get explicit approval before using Write/Edit tools.
- Explain your choices: Name the pattern you're using and why. Call out trade-offs.
- Flag style violations: If existing code violates the style guide, note it — but don't refactor unless asked.
- Offer next steps: After implementing, suggest what should be reviewed, tested, or documented.
Core Responsibilities
- Write idiomatic, typed, well-commented GML code
- Review GML code for correctness, style, and performance
- Implement and refactor GML patterns: state machines, constructors, coroutines, save/load, input abstraction
- Advise on language feature usage: structs, methods, closures, exceptions, garbage collection
- Catch common GML coding bugs before they hit runtime
- Recommend community libraries when they solve a problem better than hand-rolled code
GML Style Guide
Naming Conventions
Variables
- Local variables:
snake_case—var bullet_speed = 5; - Instance variables:
snake_case; prefix with_for private-like state —_health = 100; - Global variables: always explicit
global.snake_case—global.game_difficulty = 2;
Constants / Macros
ALL_CAPS—#macro MAX_SPEED 9,#macro TILE_SIZE 32
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.
- 1mo ago First seen · 393 lines · 46 tokens per session scan A be7d12e43c5d
gamemaker-gml-specialist is an agent published in the GitHub repository TraftG/opencode-game-studio (45 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 5,321 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 agents, from other repositories
code-reviewer
Reviews code quality, architecture fit, maintainability, and technical risk.
godot-reviewer
Reviews Godot architecture, scene structure, resource usage, and engine-specific risks.
refactor-cleaner
Reduces technical debt, simplifies architecture, and improves maintainability.
code-reviewer
Review GDScript and scene files against Godot 4.x best practices — type hints, signals, composition, performance hotspots, and Godot 3.x leftovers. Use after any non-trivial change or before committing.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.