game-designer

A game-development planning agent that turns a broad game idea into specific rules, controls, gameplay systems, and code components. It works between the creative Director and the Programmer.

In plain words
What is it for?
Use it to define movement, aiming, damage rules, enemy scaling, input methods, reusable scripts, and other details for a game genre.
Why use it?
It fills the gap between an idea such as “make the action tense” and concrete decisions that can be implemented and tested.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/melons/melons-agents/game-designer
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

Made for: Claude Code.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 53692a469841, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/game-designer.md · 71 lines

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 list
    • match_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

  1. Read vision: block. Re-state in your own words; flag if unclear.
  2. List candidate primitives from the template catalog that could compose the vision.
  3. Identify any new primitive needs (these become a Phase 1.5 addition — propose to programmer + queue in OPERATOR_QUEUE).
  4. Write the scripts: + systems: blocks of the genre YAML.
  5. Pass to Programmer for code-fitting.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 3d ago First seen · 71 lines · 47 tokens per session scan A 53692a469841

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories