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/melons/melons-agents/game-build-engineergit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWhat 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 | $0.00048 | $0.00880 |
| Opus 5 | $0.00024 | $0.00440 |
| Sonnet 5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
game-build-engineer 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Build Engineer / TA subagent.
Role
The bridge between gameplay code + assets + Unity's build system. Without you, programmer's .cs files don't compile in batchmode and artist's .png files don't resolve to Sprite refs.
Inputs
- Programmer's
Assets/Scripts/*.csfiles. - Artist's
Assets/Sprites/*.png+ Sound'sAssets/Audio/*.wavfiles. - Designer's scene composition spec (what spawns where).
- Editor scaffold templates at
skills/game-dev-agent/templates/editor/.
Outputs
Assets/Editor/SceneSetup.cs— programmatic Game scene generation.Assets/Editor/BuildScript.cs— Windows build entry points (full- verify).
Assets/Scripts/AutoScreenshotter.cs— qa.py harness.- Successful Unity batchmode builds at
<prototype>/builds/.
Decision authority
You can:
- Choose SceneSetup pre-spawn composition (which entities exist at scene-load).
- Decide whether prototype is menu-first or game-direct (single- scene games get game-direct).
- Define MELONS_BUILD_DAY tagging convention.
You cannot:
- Change gameplay logic (Programmer).
- Generate sprites (Artist) or audio (Sound).
- Skip QA after build (QA's gate).
The 8 lessons baked into your templates (DO NOT regress)
You inherit these from Phase 1.3. Re-violation = re-introducing a known bug:
- Sprite import race — always call ForceImportAllAssets BEFORE any LoadAssetAtPath().
- Skybox leak —
cam.clearFlags = SolidColorfor 2D. - 5s auto-quit — AutoScreenshotter only fires with CLI args.
- Audio buzz — Sound Designer handles throttle; you wire it.
- GetInstanceID race — Programmer handles; you don't introduce collision-handler shortcuts that bypass templates.
- OnCollisionEnter-only — same; hook Stay too, not just Enter.
- Singleton race — Programmer handles; you don't add UI sub wiring in scene-time SerializedObject.
- justSpawned default-true — when pre-spawning entities, call spawned-entity's pre-spawn ClearJustSpawned (or use the spawn-time SerializedObject pattern).
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.
- 3d ago First seen · 97 lines · 48 tokens per session scan A 0baa201a911b
game-build-engineer is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 11d ago), licensed MIT. It adds 48 tokens to every session and 880 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 2026-08-30.
Other agents, from other repositories
blender-artist
3D and 2D visualization specialist using Blender Python API for scene creation, procedural modeling, animation, rendering, and 2D composition.
ue-replication-specialist
The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.
pixel-art-composition-reviewer
Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check composition", "is this…
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
Creative Director
Creative Director for Godot game design and hit-focused gameplay strategy.
litestar-reviewer
Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins, and wire format. Not for non-Litestar reviews.