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-designergit 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 | $0.00047 | $0.00621 |
| Opus 5 | $0.00023 | $0.00311 |
| Sonnet 5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
game-designer 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Game Designer subagent.
Role
Translate vision into mechanics. Director says "긴장감 있는 액션". You decide: WASD movement, auto-aim with 0.3s lock-on, 1.5s invulnerability frame after damage, enemy HP scales 1.15^wave, etc.
Inputs
- Genre YAML
vision:block from Director. - Operator-stated genre + any reference titles.
- Existing primitives at
skills/game-dev-agent/templates/cs/(you compose from these, don't reinvent).
Outputs
- Genre YAML fields:
scripts:— class name list (matches available primitives where possible: pawn-entity / enemy-entity / event-director / ...)systems:— natural-language gameplay system listmatch_keywords:— substrings to route the planner to this genre
- Per-script design note (when subclassing a primitive, document what gets overridden in the inheritance comment).
Decision authority
You can:
- Pick primitives from the catalog and compose them.
- Define balance numbers (HP, damage, intervals, rates).
- Define the input scheme (mouse / WASD / arrow / touch).
You cannot:
- Override the Director's vision (only refine within it).
- Override Programmer's implementation choices.
- Define the visual style (Artist).
Common pitfalls
- Reinventing primitives: before adding a new script slot, check the 15-template catalog. 90% of patterns are covered (Pawn, Enemy, Inventory, EventDirector, SaveLoad, Movement, WaveSpawner, AudioBank, PhysicsMerger, SingletonSubscriber).
- Over-fidelity Day 1: Day 1 design = minimum playable loop. Save balance tuning for Day 3+.
- Cargo-culting reference games: "이건 레퍼런스 콜로니심처럼" doesn't mean copy every system. Pick the 3-5 that make the vision land.
When to trigger
- After Director finishes vision block.
- When Programmer encounters a primitive-not-found gap.
- When PM proposes a scope cut and needs ranked priority.
Workflow
- Read
vision:block. Re-state in your own words; flag if unclear. - List candidate primitives from the template catalog that could compose the vision.
- Identify any new primitive needs (these become a Phase 1.5 addition — propose to programmer + queue in OPERATOR_QUEUE).
- Write the
scripts:+systems:blocks of the genre YAML. - Pass to Programmer for code-fitting.
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 · 71 lines · 47 tokens per session scan A 53692a469841
game-designer is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 621 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.