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.
npx agentmods add skills/noizefield/audio-plugin-coder/implnpx skills add Noizefield/audio-plugin-coder --skill implgit clone --depth 1 https://github.com/Noizefield/audio-plugin-coderWhat 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 | $0.00000 | $0.07593 |
| Opus 5 | $0.00000 | $0.03796 |
| Sonnet 5 | $0.00000 | $0.01519 |
| Haiku 4.5 | $0.00000 | $0.00759 |
Grade A, and why
impl 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skill_implementation — 95% identical, 135 lines differ
How it starts
The opening of the file, as written. The whole thing — 978 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: DSP IMPLEMENTATION
Goal: Implement audio processing where parameters control DSP
Focus: PluginProcessor.h, PluginProcessor.cpp
Output Location: $PluginPath/Source/
📊 PHASE 4: CODE (DSP Implementation)
Trigger: /impl [Name] (after DESIGN phase complete)
Input: Reads $PluginPath/status.json and .ideas/parameter-spec.md
Prerequisites: Architecture plan complete, UI framework selected
State Validation:
# Import state management module
. "$PSScriptRoot\..\scripts\state-management.ps1"
$PluginPath = Get-ApcPluginPath -PluginName $PluginName
# Validate prerequisites
if (-not (Test-PluginState -PluginPath $PluginPath -RequiredPhase "design_complete" -RequiredFiles @(".ideas/architecture.md", ".ideas/plan.md"))) {
Write-Error "Prerequisites not met. Complete design phase first."
exit 1
}
# Check framework selection
$state = Get-PluginState -PluginPath $PluginPath
if ($state.ui_framework -eq "pending") {
Write-Error "UI framework not selected. Cannot proceed with implementation."
exit 1
}
Write-Host "Framework: $($state.ui_framework)" -ForegroundColor Cyan
🎨 PHASE 4.0: DESIGN-TO-FRAMEWORK CONVERSION (CRITICAL - BEFORE DSP CODE)
Framework Routing:
- If
ui_framework == webview: use templates fromtemplates/webview/ - If
ui_framework == visage: use templates fromtemplates/visage/and do not generate HTML
IMPORTANT: This phase converts the approved design specifications into framework-specific code. User must approve the conversion before DSP implementation begins.
4.0.1 Read Approved Design
- Read
Design/v[N]-ui-spec.md(latest approved version) - Read
Design/v[N]-style-guide.md(latest approved version) - Read
.ideas/parameter-spec.mdfor parameter definitions
4.0.2 Framework-Specific Conversion
For WebView Framework: Convert the approved design specs into production JUCE WebView code.
Create the required directory structure:
$PluginPath/Source/ui/
└───public/
│ index.html # Production UI based on approved design - ALL CSS/JS inline (webview-008)
│ test-local.html # Browser-test copy of index.html
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.
- 2d ago First seen · 978 lines · 0 tokens per session scan A 6373dead8896
impl 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 7,593 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.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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"…
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.
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.