team-audio
Skill5 starsChanged 4 months agoMITView on GitHub
Use when an audio feature needs coordinated direction, sound design, technical integration, and gameplay hooks.
We split this skill into the rules it gives an agent
20 rules. 4 are common, 10 are distinctive, and 6 are very specific to this project.
4
Common
Most of the 11 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Before default delegation, run python3 ../../../tools/codex_studio/agent_delegation.py resolve --project-root <project-root> --role <role> …
- Distinctive: line 15
Ask one decision question per turn and wait for the answer before asking another.
- Very specific: line 16
Use request_user_input for structured choices when it is available.
- Distinctive: line 17
Use Codex custom agents by role and profile when delegation is useful.
- Distinctive: line 18
Treat any approved write as one complete proposed changeset.
- Very specific: line 27
Read .codex/studio.toml as the only persistent review-mode source.
- Distinctive: line 42
No subagent commits, publishes, or expands scope.
- Distinctive: line 45
If a delegated task blocks, surface the evidence and stop dependent work while preserving independent results.
- Very specific: line 49
Every phase before ## Parent Changeset Gate is read-only or draft-only.
- Common: line 61
Create detailed SFX specifications for every audio event
- Common: line 70
Check that no gameplay state is communicated by audio alone (all must have a visual fallback)
- Distinctive: line 88
If no engine is configured, mark the engine-specific subsection N/A.
- Distinctive: line 96
Only after approval may the parent execute or delegate the exact approved changes.
- Common: line 104
Write unit tests for audio event triggers
- Common: line 117
If the pipeline stops because a dependency is unresolved (e.g., critical accessibility gap or missing GDD not resolved by the user):
- Very specific: line 124
Use $dev-story to implement the audio manager and event system once the design is approved.
- Very specific: line 125
Run $asset-audit after audio assets are created to verify naming and format compliance.
- Distinctive: line 129
If any delegated agent (through Codex custom-agent delegation) returns BLOCKED, errors, or cannot complete:
- Distinctive: line 132
Assess dependencies: Check whether the blocked agent's output is required by subsequent phases.
- Distinctive: line 136
Stop here and resolve the blocker first
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- codex-studio-delegation: governed -->Resolve every role through ../../../.codex/docs/plugin-agent-delegation.md;
do not require a repository-local .codex/agents/ or .codex/agent-packs/ tree.
Before default delegation, run python3 ../../../tools/codex_studio/agent_delegation.py resolve --project-root <project-root> --role <role> and use only its returned role contract.
Team Audio
Codex Interaction Contract
- Ask one decision question per turn and wait for the answer before asking another.
- Use
request_user_inputfor structured choices when it is available; otherwise ask the same concise question directly. - Use Codex custom agents by role and profile when delegation is useful.
- Treat any approved write as one complete proposed changeset. Before writing, present every target path and material edit together; do not add unlisted files or behavior.
- A new path, expanded scope, or material change requires a revised complete proposed changeset and fresh approval.
Invocation
Usage: $team-audio [feature or area] [--review full|lean|solo]. If the required objective cannot be inferred safely, ask for that single missing decision and wait; do not delegate yet.
Review Mode
Read .codex/studio.toml as the only persistent review-mode source. Map review_mode = "phase-gated" to lean optional-review depth; mandatory director gates still run. A --review argument applies only to the current run. Use ../../../.codex/docs/director-gates.md and .codex/docs/technical-preferences.md for native gate and engine context.
Team Roster
audio-directorsound-designertechnical-artistgameplay-programmer
Delegation Plan
- Delegate only tasks that are independent and bounded.
- Name the Codex custom-agent role and the exact artifact or evidence it must return.
- Team members must not spawn additional agents (
agents.max_depth = 1). - The parent agent synthesizes all results, resolves overlap, and communicates with the user.
- No subagent commits, publishes, or expands scope.
- Parallel delegation is read-only or draft-only until the parent presents a consolidated result.
- Any multi-file implementation requires one complete changeset approval before work begins.
- If a delegated task blocks, surface the evidence and stop dependent work while preserving independent results.
Pipeline
Every phase before ## Parent Changeset Gate is read-only or draft-only. Phase 1 returns direction notes; no agent writes files or implementation.
Step 1: Audio Direction (audio-director)
Delegate to the audio-director agent to:
- Define the sonic identity for this feature/area
- Specify the emotional tone and audio palette
- Set music direction (adaptive layers, stems, transitions)
- Define audio priorities and mix targets
- Establish any adaptive audio rules (combat intensity, exploration, tension)
Step 2: Sound Design and Audio Accessibility (parallel)
Delegate to the sound-designer agent to:
- Create detailed SFX specifications for every audio event
- Define sound categories (ambient, UI, gameplay, music, dialogue)
- Specify per-sound parameters (volume range, pitch variation, attenuation)
- Plan audio event list with trigger conditions
- Define mixing groups and ducking rules
Delegate to the sound-designer agent in parallel to:
- Identify which audio events carry critical gameplay information (damage received, enemy nearby, objective complete) and require visual alternatives for hearing-impaired players
- Specify subtitle requirements: which audio events need captions, what text format, on-screen duration
- Check that no gameplay state is communicated by audio alone (all must have a visual fallback)
- Review the audio event list for any that could cause issues for players with auditory sensitivities (high-frequency alerts, sudden loud events)
- Output: audio accessibility requirements list integrated into the audio event spec
Step 3: Technical Plan (draft-only, parallel)
Delegate to the technical-artist agent to:
- Design the audio middleware integration (Wwise/FMOD/native)
- Define audio bus structure and routing
- Specify memory budgets for audio assets per platform
- Plan streaming vs preloaded asset strategy
- Design any audio-reactive visual effects
Have technical-artist also read the configured Engine Specialists guidance in .codex/docs/technical-preferences.md and validate the integration approach:
- Is the proposed audio middleware integration idiomatic for the engine? (e.g., Godot's built-in AudioStreamPlayer vs FMOD, Unity's Audio Mixer vs Wwise, Unreal's MetaSounds vs FMOD)
- Any engine-specific audio node/component patterns that should be used?
- Known audio system changes in the pinned engine version that affect the integration plan?
- Output: engine audio integration notes merged into the technical-artist's plan
If no engine is configured, mark the engine-specific subsection N/A.
Parent Changeset Gate
The parent synthesizes all direction, asset, technical, and code-plan drafts before any mutation. Present one complete proposal containing exact file paths, exact diffs, tests and evidence, and all session-state, report, and milestone writes (use None where no such write exists). Obtain approval for the whole changeset; a new path or material change requires a revised proposal.
Approved Execution
Only after approval may the parent execute or delegate the exact approved changes. No subagent commits, publishes, or expands scope. Every delegate receives only its approved paths, diffs, tests, and acceptance criteria.
Step 4: Code Integration (gameplay-programmer)
Delegate to the gameplay-programmer agent to:
- Implement audio manager system or review existing
- Wire up audio events to gameplay triggers
- Implement adaptive music system (if specified)
- Set up audio occlusion/reverb zones
- Write unit tests for audio event triggers
- Compile the audio design document combining all team outputs.
Save to
design/audio/audio-[feature].md.Note: If
design/audio/does not exist, the sub-agent writing the document should create it (the directory will be created automatically when the file is written).- Output a summary with: audio event count, estimated asset count, implementation tasks, and any open questions between team members.
Verdict: COMPLETE — audio design document produced and team pipeline finished.
If the pipeline stops because a dependency is unresolved (e.g., critical accessibility gap or missing GDD not resolved by the user):
Verdict: BLOCKED — [reason]
Next Steps
- Review the audio design doc with the audio-director before implementation begins.
- Use
$dev-storyto implement the audio manager and event system once the design is approved. - Run
$asset-auditafter audio assets are created to verify naming and format compliance.
Error Recovery Protocol
If any delegated agent (through Codex custom-agent delegation) returns BLOCKED, errors, or cannot complete:
- Surface immediately: Report "[AgentName]: BLOCKED — [reason]" to the user before continuing to dependent phases
- Assess dependencies: Check whether the blocked agent's output is required by subsequent phases. If yes, do not proceed past that dependency point without user input.
- Offer options via request_user_input with choices:
- Skip this agent and note the gap in the final report
- Retry with narrower scope
- Stop here and resolve the blocker first
- Always produce a partial report — output whatever was completed. Never discard work because one agent blocked.
Common blockers:
- Input file missing (story not found, GDD absent) → redirect to the skill that creates it
- ADR status is Proposed → do not implement; run
$architecture-decisionfirst - Scope too large → split into two stories via
$create-stories - Conflicting instructions between ADR and story → surface the conflict, do not guess
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 10
- Donchitos/Claude-Code-Game-Studios★ 27k18% same
- striderZA/OpenCodeGameStudios★ 9357% same
- CoralGame/Claude-Code-Game-Studios★ 1940% same
- dawn840705/codex-code-studios★ 1758% same
- lilangMax/ClaudeCodeGameStudios★ 857% same
- dawn840705/claude-code-studios★ 157% same
- HunLuanZhiZhu/Game-Studios-Plugin★ 154% same
- scotidev/GameDevStudio★ 140% same
- Swih/godot-foundry★ 139% same
- venus2099/codex-game-studios★ 118% same
Wrote their own version · 2
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- ShiningPlague/shiningplague-studio★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Codex Studio Testing Framework/AGENTS.mdAGENTS.md
- prototypes/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- art-bibleSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- playtest-reportSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-gddsSkill
- scope-checkSkill
- security-auditSkill
- setup-engineSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- story-readinessSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

