avfaudio-session-workflow

A workflow for configuring and repairing audio sessions in Apple apps. An audio session tells the operating system how an app intends to record or play sound and how it should share audio with other apps and devices.

In plain words
What is it for?
Use it when setting recording or playback behavior, requesting microphone permission, handling interruptions and route changes, or diagnosing capture-session audio problems.
Why use it?
It helps fix silent recording, incorrect speaker or headphone routing, unwanted interruptions, and failures caused by calls, Bluetooth, AirPlay, or permission changes.

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/gaelic-ghost/socket/avfaudio-session-workflow
Any agent
npx skills add gaelic-ghost/socket --skill avfaudio-session-workflow
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,598 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 $0.00084 $0.01598
Opus 5 $0.00042 $0.00799
Sonnet 5 $0.00017 $0.00320
Haiku 4.5 $0.00008 $0.00160

Measured 2d ago against content hash d35aa9fe69a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

avfaudio-session-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 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.

plugins/apple-dev-skills/skills/avfaudio-session-workflow/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AVFAudio Session Workflow

Purpose

Guide Apple app audio-session design and repair. This skill owns the app-level audio intent boundary: what the app tells the system it wants to do with audio, when it activates that intent, how it responds to interruption and route changes, how it preserves typed AVFAudio policy surfaces, and how it explains failures.

It is not the audio-engine graph workflow, not the AVFoundation media-pipeline workflow, not the Core Media timing workflow, and not the Xcode execution workflow.

When To Use

  • Use this skill when configuring or repairing AVAudioSession, AVAudioApplication, AVAudioApplication.requestRecordPermission, recording permission, categories, modes, options, AVAudioSession.RouteSharingPolicy, activation, deactivation, interruptions, route changes, Bluetooth, AirPlay, speaker routing, or capture-session audio-session behavior.
  • Use this skill when existing audio code plays from the wrong route, fails silently, captures silence, interrupts other audio incorrectly, fails around calls, ignores headphones disconnects, or logs vague audio errors.
  • Recommend avaudio-engine-workflow when the primary issue is an AVAudioEngine graph, node connection, tap, render callback, manual rendering, or format conversion.
  • Recommend avfoundation-media-pipeline-workflow when the primary issue is capture, playback, media assets, readers, writers, export, or sample-buffer append policy.
  • Recommend coremedia-timing-samplebuffer-workflow when the primary issue is timestamps, timebases, CMSampleBuffer, or media synchronization.
  • Recommend xcode-build-run-workflow or xcode-testing-workflow when the next step is build, run, entitlement, Info.plist, simulator, device, or test execution.

Single-Path Workflow

  1. Classify the audio-session request:
    • playback-only behavior
    • recording or play-and-record behavior
    • capture-session audio interaction
    • route, Bluetooth, AirPlay, or speaker behavior
    • interruption or route-change handling
    • permission or privacy gate
    • repair of an existing implementation
  2. Apply the Apple docs gate:
    • read current AVFAudio or AVFoundation documentation first
    • use archive material only for legacy migration context
    • state the documented behavior relied on before recommending design or repair
    • apply ../../shared/references/apple-media-type-ownership.md before introducing string-backed audio policy, route, category, mode, or permission models
    • stop if current docs and code disagree in a way that changes the recommendation
  3. Choose the app-audio policy:
    • category, mode, route-sharing policy, and options
    • activation and deactivation point
    • permission request and denial behavior
    • interruption and route-change observers
    • capture-session automatic audio-session configuration stance
  4. Repair common failure modes:
    • missing microphone usage description or permission path
    • category, mode, route, permission, or output policy modeled as free-form strings instead of AVAudioSession and AVAudioApplication types
    • using overrideOutputAudioPort when defaultToSpeaker is the durable intent
    • leaving other apps interrupted after deactivation instead of using notifyOthersOnDeactivation when appropriate
    • treating denied permission as a hardware failure
    • ignoring headphones disconnect privacy expectations
    • allowing AVCaptureSession to mutate shared audio-session state unexpectedly
  5. Return one recommendation with:
    • request class
    • documented Apple behavior relied on
    • chosen category, mode, options, and activation lifecycle
    • permission, route, and interruption plan
    • repair findings
    • one execution or testing handoff when runtime validation is required

Read the full file on GitHub · 120 lines

Files

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.

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 · 120 lines · 84 tokens per session scan A d35aa9fe69a6

Subscribe to this mod's changes

avfaudio-session-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,598 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

scenekit-product-stages

Build and debug SceneKit scenes where one 3D object (a product, badge, coin, wheel) performs on a transparent stage inside a SwiftUI app - studio lighting, real shadows, baked keyframe choreography, hand-rolled physics, gestures and haptics, multi-scene sequencing. Use when working with SCNView or SceneView in…

dembsky/PropMotion · 306 tokens

music

Apple Music in your terminal. Play tracks, route to AirPlay speakers and AirPods, search 100 million songs, build playlists, play radio stations, discover new music, favorite tracks, seek within a song, browse your listening history, browse your library by artist, album, or track. This is the plugin's only entry…

anthonymaley/MusicTUI · 408 tokens

xcode-disk-cleanup

Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders…

AvdLee/Xcode-Disk-Cleanup-Agent-Skill · 147 tokens

qiaomu-icon-generator

Generate multiple app, favicon, or website icon candidates with either the local QM Icon Studio CLI or Codex built-in image generation with reference icons, then present a contact sheet so the user can choose. Use when building websites or apps and needing reusable icon options.

joeseesun/qiaomu-icon-generator · 58 tokens

macparakeet-stt

Use when the user asks to transcribe audio or video, inspect or manage MacParakeet meeting recordings, search prior dictations/transcripts, or give an AI agent local speech-to-text tools on Apple Silicon.

moona3k/macparakeet · 50 tokens