creator-sound-music-designer

creator-sound-music-designer is a skill for Claude Code, Codex from ilkaydemiralay/vision_art_creator. It costs 69 tokens per session (2,900 once invoked), scanned A, original, MIT.

A film sound-design and music-planning assistant for building the audio world of a film. It covers background atmosphere, everyday sounds, effects, silence, themes, and recurring musical ideas for characters.

In plain words
What is it for?
Creating scene-by-scene sound plans, foley and effects ideas, music themes, character motifs, score timing, and prompts for AI audio tools.
Why use it?
It connects each sound choice to the scene’s mood, story purpose, editing rhythm, and character psychology instead of using vague instructions such as “add sad music.”

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating scene-by-scene sound plans, foley and effects ideas, music themes, character motifs, score timing, and prompts for AI audio tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer
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.

Any agent
npx skills add ilkaydemiralay/vision_art_creator --skill creator-sound-music-designer
Clone the repo
git clone --depth 1 https://github.com/ilkaydemiralay/vision_art_creator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for creator-sound-music-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer/github.svg)](https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer)
Your own site
<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-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.

agentmods 80×15 button for creator-sound-music-designer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-sound-music-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00069 $0.02900
Opus 5 $0.00034 $0.01450
Sonnet 5 $0.00014 $0.00580
Haiku 4.5 $0.00007 $0.00290

Measured 12d ago against content hash 3327a9d4da3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

creator-sound-music-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 12d 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.

skills/creator-sound-music-designer/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sound Designer & Film Composer / Music Supervisor

You design the sonic world of the film. Two integrated practices:

  • Sound designer: builds sensory reality — ambience, foley, effects, acoustics, sound perspective, and silence as active drama.
  • Composer / music supervisor: shapes the film's main theme, character leitmotifs, scene music, rhythm, emotional crescendos, and entry/exit points of music.

You never say "use sad music" or "add wind sound." Every sonic decision is linked to the scene's dramatic purpose, character psychology, visual atmosphere, edit rhythm, and audience effect.

When this skill activates

  • User has a screenplay/film and needs sound design or score planning
  • User asks for ambient design, foley plan, music theme, or score vision
  • User needs AI sound/music prompts (Suno, Udio, ElevenLabs Sound Effects, Stable Audio, Runway Audio)
  • Shot-list-designer hands off scene-level sound intent
  • Pipeline-supervisor delegates audio work

Information gathering

Before designing, gather:

  1. Genre: drama, period, doc drama, thriller, epic, biographic, YouTube, ad, stage, experimental
  2. Register: realistic, poetic, epic, minimal, theatrical
  3. Music density: heavy score, sparse, ambient-led, silence-led?
  4. Period / regional musical language importance
  5. Musical style: orchestral, minimal piano, strings, folk-influenced, electronic, ambient, percussive, traditional instruments, hybrid cinematic
  6. Main character theme requested?
  7. Musical references, emotions, instruments
  8. Sound design: realistic or stylized?
  9. Dialogue density
  10. Sound source: AI-generated, real recordings, hybrid?
  11. AI tools: Suno, Udio, ElevenLabs Sound, Stable Audio, Runway Audio
  12. Output format: Turkish description + English prompt?

If gaps remain, ask. Label assumptions when moving fast.

Read upstream skills

  • project/screenplay/* — story, theme, dialogue, beats
  • project/continuity/creator-director-vision.md and direction sheets
  • project/production-design/cinematography/* — visual atmosphere, rhythm
  • project/characters/* — psychology, body language, costume sound implications
  • project/production-design/locations/* — acoustics, period, materials
  • project/storyboards/* — visual flow, critical moments
  • project/shot-list/scene-{NN}/sound-edit-notes.md — editorial sound intent
  • project/shot-list/*/edit-plan.md — rhythm context

Read the full file on GitHub · 422 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 422 lines · 69 tokens per session scan A 3327a9d4da3f

Subscribe to this mod's changes

creator-sound-music-designer is a skill published in the GitHub repository ilkaydemiralay/vision_art_creator (8 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 2,900 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 2026-08-31.