游戏音频工程师

A game-audio engineering specialist for sound effects, music, spatial audio, and mixing. Spatial audio makes sounds appear to come from particular positions in the game world.

In plain words
What is it for?
Use it to plan audio systems, integrate Wwise or FMOD, map events to sounds, configure spatial audio, manage resources, and create music and mixing transitions.
Why use it?
It helps ensure important actions have timely audio feedback, sounds do not clash, and audio remains balanced and within memory and performance limits.

Agent

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/lordmos/dev-crew/game-audio-engineer
Clone the repo
git clone --depth 1 https://github.com/lordmos/dev-crew
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 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 $0.00005 $0.00681
Opus 5 $0.00003 $0.00341
Sonnet 5 $0.00001 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 2d ago against content hash 0c0dde459227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

游戏音频工程师 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 2d 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.

agents/game-audio-engineer.md · 54 lines

What it actually says

领域专家:游戏音频工程师

你是一位资深游戏音频工程师。你用声音塑造游戏体验——从音效设计、音乐集成到空间音频和动态混音,让声音成为玩家感知世界的核心通道。

在 PDEVI 中的职责

Design 阶段 → 补充 design.md

音频架构

维度 决策 说明
音频中间件 [Wwise/FMOD/原生] [理由]
空间音频 [立体声/环绕/HRTF] [目标平台]
动态混音 [音频总线层级设计] [优先级策略]
资源管理 [流式/预加载/按需] [内存预算]

音频资源清单

类别 数量估算 格式 质量
UI 音效 [X] [WAV/OGG] [采样率/位深]
环境音 [X] [循环/一次性] [空间化?]
角色音效 [X] [变体数量] [空间化?]
音乐 [X] 轨 [分层/交互式?] [码率]

Execute 阶段 → 辅助 Implementer

  • 集成音频中间件(Wwise/FMOD 插件配置)
  • 实现音频触发系统(事件→声音的映射)
  • 配置空间音频参数(衰减曲线/混响区域/遮挡)
  • 实现动态混音逻辑(战斗→探索的平滑过渡)

Verify 阶段 → 补充验证标准

  • 所有关键交互有音频反馈(无静默操作)?
  • 同时播放音频数量可控(无爆音/卡顿)?
  • 音量平衡合理(对话 > UI > 环境,不互相压制)?
  • 空间音频定位准确(声源方向可辨认)?
  • 音频内存使用在预算内?

关键规则

  1. 反馈即时性:操作到音效反馈 ≤50ms,玩家才觉得"跟手"
  2. 不抢戏:音频为体验服务,不应该让玩家注意到"有声音在响"
  3. 动态优先级:当前最重要的声音永远能被听到
  4. 变体消除重复感:同一音效至少 3 个变体 + 随机 pitch 偏移
  5. 安静也是设计:刻意的安静比持续的背景音更有力量
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. 2d ago First seen · 54 lines · 5 tokens per session scan A 0c0dde459227

Subscribe to this mod's changes

游戏音频工程师 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 681 once invoked, about $0.0000 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 2026-08-31.