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 skills add kunitoki/sonic-skills --skill audio-signal-flow-explainergit clone --depth 1 https://github.com/kunitoki/sonic-skillsWrote 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.
[](https://agentmods.dev/skills/kunitoki/sonic-skills/audio-signal-flow-explainer)<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/audio-signal-flow-explainer"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/audio-signal-flow-explainer/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.
<a href="https://agentmods.dev/skills/kunitoki/sonic-skills/audio-signal-flow-explainer"><img src="https://agentmods.dev/badge/skills/kunitoki/sonic-skills/audio-signal-flow-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.00781 |
| Opus 5 | $0.00058 | $0.00391 |
| Sonnet 5 | $0.00023 | $0.00156 |
| Haiku 4.5 | $0.00012 | $0.00078 |
Grade A, and why
audio-signal-flow-explainer 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Signal Flow Explainer
Core principle: Audio signal flow is a directed graph. Tracing it reveals hidden coupling, latency paths, and places where the signal can be corrupted.
Step 1 — Map the graph
- Find all sources (oscillators, audio inputs, file readers, generators)
- Find all processors (filters, effects, gain stages, dynamics)
- Find all routers (bus sends, parallel splits, sidechain taps, mixer channels)
- Find all sinks (audio outputs, recorders, meters, analyzers)
- Note parallel paths — any branch that rejoins a main path
- Note feedback loops — any path where output feeds back into an earlier node
- Note sidechain connections — signals that control a processor without passing audio through it
Step 2 — Identify each node type
| Node type | What to note |
|---|---|
| Source (oscillator, audio input, file reader) | Sample rate, channel count, sync source |
| Processor (filter, effect, gain) | In/out channel count, latency added, stateful or stateless |
| Router (bus send, parallel split, sidechain tap) | Where signal copies go, gain staging at split |
| Sink (audio output, recorder, meter) | Expected format, callback timing, buffer size |
Step 3 — Surface issues
- Latency compensation mismatches on parallel paths
- Channel count mismatches between connected nodes
- Sidechain input not wired — processor receives silence as control signal
- Uninitialized state in feedback loops (DC buildup, NaN propagation)
- DC leaking into output (missing highpass or DC-blocking filter)
- Sample rate mismatch between source and downstream processor
- Gain staging that causes clipping before a later limiter or saturation stage
- Missing denormal protection in recursive filter paths
Step 4 — Write the signal flow description
Use this format:
## Signal Flow: [component/system]
### Graph
Source → [gain: 1.0] → [Biquad LPF] → [Comp sidechain tap] → [Output]
↓
[Compressor] → [Output]
### Latency path
Source → LPF (0 samples) → Compressor (64 samples lookahead) → Output
Total: 64 samples
### Issues found
- Parallel path to Output has no latency compensation for the 64-sample compressor delay
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.
- 9d ago First seen · 77 lines · 116 tokens per session scan A 432a5980f7f6
audio-signal-flow-explainer is a skill published in the GitHub repository kunitoki/sonic-skills (19 stars, last pushed 3mo ago), licensed Unlicense. It adds 116 tokens to every session and 781 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dream-thinking
Creative retrospective workflow that uses simulated dream imagery and metaphor to defamiliarize recent experience, then turns it into grounded hypotheses and next observations or actions. Use only when the user explicitly asks to dream, sleep on something, use a dream or nightmare lens, or reflect through metaphor. Do…
marp-slide
Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.
AudioMind
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
floyd
Play an audio file (.mp3, .wav, or .flac) using the floyd command line player. Use when the user wants to play, listen to, or preview an audio file.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.