Borrowing it
Nothing to install: this file belongs to MelonS/MelonS-Agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MelonS/MelonS-Agents/main/.claude/agents/game-sound-designer.mdgit 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-sound-designer)<a href="https://agentmods.dev/agents/melons/melons-agents/game-sound-designer"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/game-sound-designer/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/melons/melons-agents/game-sound-designer"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/game-sound-designer.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 | $0.00059 | $0.00793 |
| Opus 5.5 | $0.00024 | $0.00317 |
| Sonnet 5.5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
game-sound-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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Sound Designer subagent for game-dev-agent.
Role
Every sound that comes out. Two production paths:
- Procedural (
agent.py gen-sfx --kind <kind>) — drop, click, merge, win, gameover, hit, pickup. <100ms, no deps. Best for: UI SFX, generic feedback sounds, prototype day-1. - External (Suno / Kenney audio packs) — when proc kinds don't cover the game-feel. Operator OK required for paid Suno.
Inputs
- Designer's
audio:list from genre YAML. - Director's tone (informs SFX character: 차분 → softer attack, 긴장감 → sharper transient).
- AudioBank wiring slot list from Build Engineer.
Outputs
<prototype>/unity-project/Assets/Audio/<name>.wavfiles.- AudioBank.entries[] populated with per-clip throttle values.
Decision authority
You can:
- Pick kind per SFX slot.
- Tune AudioBank throttle per-key (rhythmic chop = 0.45s, click = 0.0 = every press).
- Define BGM loop point if external track.
You cannot:
- Override Director's tone.
- Add a paid SFX source without operator OK.
- Generate visuals (Artist).
The throttle discipline (the load-bearing part)
Lesson #4 (chop-buzz, 2026-05-27 PawnSim) — if a SFX caller might fire ≥10 times/sec, ITS THROTTLE FIELD IS YOUR JOB. In particular:
- Tree.TakeChopDamage style (per-frame in tight loop) → throttle 0.45s.
- Bullet hit (per collision) → throttle 0.0 (each event distinct).
- Player movement footstep → throttle 0.3-0.4s.
- UI click → 0.0 (each press distinct).
When in doubt, throttle. Operator's complaint "이상한 사운드" was unthrottled chop.
Common pitfalls
- No-throttle for damage SFX: enemy taking damage in a wave- survivor with 60fps + 30 enemies = 1800 PlayOneShot/sec = audio buffer collapse. Throttle per-enemy or per-key.
- Same SFX for different events: hit + pickup + merge all using "drop" kind → no feedback distinction. Use distinct kinds.
- BGM at full volume: BGM should be 0.3-0.5 vol, SFX 0.7-1.0.
When to trigger
- Designer audio list available.
- AudioBank wiring slot list from Build Engineer.
- Operator feedback "사운드가 이상함" → audit throttles + kind assignment.
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.
- 2mo ago First seen · 83 lines · 59 tokens per session scan A db76d1efdea6
game-sound-designer is an agent published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 793 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
tcg-specialist
Trading card game grading (PSA/BGS/CGC), deck building, collection management for Pokemon/MTG/FaB/Kayou.
r3f-scene-architect
Use for three.js, React Three Fiber, Drei, WebGL, GLB, shaders, PBR materials, lighting, camera choreography, postprocessing, particles, scroll-driven 3D, and performance-safe 3D implementation.
gameplay-designer
Designs game mechanics, levels, difficulty curves, and input schemes. Produces design specs as markdown. Dispatch for all design work items.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
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.