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 gaelic-ghost/socket --skill avaudio-engine-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/avaudio-engine-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/avaudio-engine-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/avaudio-engine-workflow/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/gaelic-ghost/socket/avaudio-engine-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/avaudio-engine-workflow.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 | $0.00077 | $0.01507 |
| Opus 5.5 | $0.00031 | $0.00603 |
| Sonnet 5.5 | $0.00015 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
avaudio-engine-workflow 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AVAudio Engine Workflow
Purpose
Guide AVAudioEngine graph design and repair. This skill owns audio-node ownership, graph construction, connection formats, typed AVFAudio buffer and format surfaces, taps, manual rendering, offline processing, Audio Unit hosting through AVAudioUnit, and real-time safety boundaries.
It is not the app audio-session workflow, not the AVFoundation capture or asset workflow, and not a low-level Core Audio C API repair workflow except where AVAudioEngine wraps the lower-level behavior.
When To Use
- Use this skill when code creates, connects, mutates, starts, stops, or repairs an
AVAudioEnginegraph. - Use this skill for
AVAudioPlayerNode,AVAudioInputNode,AVAudioOutputNode,AVAudioMixerNode,AVAudioSourceNode,AVAudioSinkNode, taps,AVAudioFormat, manual rendering, offline processing,AVAudioUnit, Audio Unit instantiation, and render-block safety. - Use this skill when existing code crashes from unattached nodes, format mismatches, missing input or output hardware, illegal graph mutation, callback allocation, actor isolation mistakes, or UI work inside real-time audio paths.
- Recommend
avfaudio-session-workflowwhen the primary problem is category, route, permission, interruption, or activation policy. - Recommend
coreaudio-modernization-repair-workflowwhen the primary problem is legacyAudioQueue,AudioUnit,AudioConverter, pointer, callback, orOSStatuscode outside AVAudioEngine.
Single-Path Workflow
- Classify the engine request:
- playback graph
- input capture or tap
- processing chain or effects
- source or sink node
- manual rendering or offline processing
- Audio Unit hosting
- repair of an existing graph
- Apply the Apple docs gate:
- read current AVFAudio docs for the relevant engine, node, format, or rendering behavior
- state the documented graph, format, or real-time behavior relied on
- apply
../../shared/references/apple-media-type-ownership.mdbefore introducing custom graph, buffer, format, or unit-hosting abstractions
- Map the graph:
- engine owner and lifetime
- attached nodes
- connection order
- bus formats and conversion points
- start, schedule, stop, and teardown lifecycle
- real-time and non-real-time boundaries
- Repair common failure modes:
- node used before
attach(_:) - exact format mismatch where no mixer or output conversion applies
- input or output node used when hardware is unavailable
- graph mutation that breaks mixer or channel-count assumptions
- render callback that allocates, locks, logs, awaits, or touches UI
- hand-rolled format or buffer structs replacing
AVAudioFormat,AVAudioPCMBuffer,AVAudioFile,AVAudioConverter, orAudioStreamBasicDescriptionwhile still configuring Apple audio APIs - completion handlers that mutate engine state from an arbitrary thread without a clear hop
- node used before
- Return one recommendation with:
- graph class
- documented Apple behavior relied on
- graph ownership and connection plan
- format and rendering plan
- repair findings
- validation and handoff expectation
What ships with it
4 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.
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.
- 1mo ago First seen · 118 lines · 77 tokens per session scan A 89d1760cbe62
avaudio-engine-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,507 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
flutter-screenshots
Automate App Store & Google Play screenshot generation for Flutter apps. Scans routing and screens, scores high-value marketing screens, generates self-contained mock harness, runs native simulator captures (iPhone 6.9", iPad 13", Android Phone/Tablet), strips alpha channels, and validates exact store resolutions.
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.