dream

An ideation workflow for defining an audio-plugin concept, its controls, and its visual direction before implementation. It can initialize the project's idea files and status after the required concept details are known.

In plain words
What is it for?
Use /dream with a plugin name to shape its character, main controls, and aesthetic, then create the project's planning documents and tracking file.
Why use it?
It turns an unclear plugin idea into a written creative brief and parameter specification, while preventing code or build files from being generated too early.

Skill for Claude CodeCodex

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 skills/noizefield/audio-plugin-coder/dream
Any agent
npx skills add Noizefield/audio-plugin-coder --skill dream
Clone the repo
git clone --depth 1 https://github.com/Noizefield/audio-plugin-coder

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 738 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 $0.00000 $0.00738
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 2d ago against content hash ae2515a16bb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dream 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agent/skills/dream/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: IDEATION & DREAMING

Goal: Define the plugin concept and initialize the project state. Trigger: /dream [Name] Output Location: $PluginPath/

⛔ OUTPUT RESTRICTIONS (MANDATORY)

  • NO C++ Code.
  • NO Build Scripts.
  • NO CMake configurations.

STEP 1: THE INTERVIEW

Do NOT generate files yet. If the user prompt is vague, ask 3 clarifying questions:

  1. Sonic Goal: What is the character? (e.g., "Dirty Tape Delay", "Clean EQ")
  2. Controls: What are the top 3 parameters?
  3. Vibe: Visual aesthetic?

STOP and WAIT for the user's response.

STEP 2: CONCEPT GENERATION

Only after the user answers, generate these files:

1. $PluginPath/.ideas/creative-brief.md

The vision statement.

  • Hook: Marketing pitch.
  • Description: Detailed behavior.

2. $PluginPath/.ideas/parameter-spec.md

The definitive list of controls.

ID Name Type Range Default Unit
gain Gain Float 0.0 - 1.0 0.5 dB

3. $PluginPath/status.json (ROOT)

Initialize the project tracking file in the plugin root using the standardized schema.

Use the state management system:

# Import state management
. "$PSScriptRoot\..\scripts\state-management.ps1"
$PluginPath = Get-ApcPluginPath -PluginName $PluginName

# Initialize state
New-PluginState -PluginName $PluginName -PluginPath $PluginPath

Schema structure:

{
  "plugin_name": "[Name]",
  "version": "v0.0.0",
  "current_phase": "ideation",
  "ui_framework": "pending",
  "complexity_score": 0,
  "created_at": "2026-01-04T20:20:00Z",
  "last_modified": "2026-01-04T20:20:00Z",
  "phase_history": [],
  "validation": {
    "creative_brief_exists": true,
    "parameter_spec_exists": true,
    "architecture_defined": false,
    "ui_framework_selected": false,
    "design_complete": false,
    "code_complete": false,
    "tests_passed": false,
    "ship_ready": false
  },
  "framework_selection": {
    "decision": "pending",
    "rationale": "",
    "implementation_strategy": "pending"
  },
  "error_recovery": {
    "last_backup": null,
    "rollback_available": false,
    "error_log": []
  }
}

Read the full file on GitHub · 94 lines

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 · 94 lines · 0 tokens per session scan A ae2515a16bb6

Subscribe to this mod's changes

dream is a skill published in the GitHub repository Noizefield/audio-plugin-coder (313 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 738 tokens. 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

vox-director

Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…

Alisa0808/vox-director · 236 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

model-compatibility

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.

artokun/comfyui-mcp · 47 tokens

comfyui-topology-viz

Turn a network topology into one stylized, AI-generated still image via a self-hosted ComfyUI instance — reuses the same topology model as threejs-network-viz (any of 8 topology-source integrations, or a freeform description). Use when the operator asks for a stylized, flashy, or AI-generated…

automateyournetwork/netclaw · 93 tokens