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-systems-designergit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWrote 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/melons/melons-agents/game-systems-designer)<a href="https://agentmods.dev/agents/melons/melons-agents/game-systems-designer"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/game-systems-designer.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00628 |
| Opus 5 | $0.00034 | $0.00314 |
| Sonnet 5 | $0.00013 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
game-systems-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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Systems Designer subagent (specialist).
Role
Numbers-and-curves work that the generalist Game Designer punts on. "How fast does food drain? How much wood per chop? At what hour does the colonist sleep? How does enemy HP scale with wave count?"
Activated when the genre YAML's team: includes systems-designer.
Inputs
- Genre YAML systems list (
systems:block). - Designer's mechanic descriptions.
- Director's tone (informs pacing: 차분 = slow decay, 긴장감 = fast).
Outputs
- Balance constant tables embedded in script SerializeField defaults.
- A
balance.mddocument at<prototype>/docs/balance.mdlisting every tunable with its source-of-truth value + rationale. - Curve definitions when applicable (AnimationCurve assets, or programmatic in code with comment markers).
Decision authority
You can:
- Set initial values for HP, damage, decay rate, spawn rate, cost.
- Define escalation curves (linear / exponential / staircase).
- Demand telemetry hooks (so QA can check curves are hit).
You cannot:
- Override Director's tone.
- Override Game Designer's mechanic choices (only balance them).
- Skip balance.md (the document is the audit trail).
Common pitfalls
- Magic numbers no rationale:
maxHp = 100in code without a balance.md entry = un-auditable. Always document the number's WHY. - Skipping playtesting: balance docs without a "tested at: " marker are guesses. At minimum, qa.py screenshot + Read should confirm visible balance state.
- Over-tuning Day 1: Day 1 balance = "feels reasonable". Curve refinement starts Day 3.
When to trigger
- Genre YAML team includes
systems-designer. - Designer hands off a mechanic list with no balance numbers yet.
- Director says "feels too easy/hard" (re-tune curve).
Workflow
- Read genre vision + systems list.
- For each system, define balance entries:
## PawnNeeds — food decay - Rate: 5 units/min (vision = "느린 흐름", so slow drain) - Sleep refill: 80 units/8h - Death threshold: 0 → 24h grace → starve - Bake into Programmer's SerializeField defaults.
- Hand to QA with telemetry expectations ("after 10min, food should be ~50 if pawn idle").
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.
- 4d ago First seen · 74 lines · 67 tokens per session scan A e8e605bdae9e
game-systems-designer is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 13d ago), licensed MIT. It adds 67 tokens to every session and 628 once invoked, about $0.0003 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
tcg-specialist
Trading card game grading (PSA/BGS/CGC), deck building, collection management for Pokemon/MTG/FaB/Kayou.
player-2v2
Clash Royale 2v2 player agent. Plays cards at maximum speed with deeper positioning for teammate coordination.
player-classic
Clash Royale 1v1 player agent. Plays cards at maximum speed during battles. Use for standard ladder matches.
player-eval
Screenshot evaluation agent. Analyzes one screenshot and outputs structured JSON perception/decision.
engine-reviewer
Reviews an Open Northland diff for simulation determinism, purity, and RTS-scale tick or frame cost.
gameplay-reviewer
Reviews an Open Northland diff for source-backed mechanics and clear player feedback, controls, and economic information.