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/gaelic-ghost/socket/camera-capture-depth-workflownpx skills add gaelic-ghost/socket --skill camera-capture-depth-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWhat 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 | $0.00087 | $0.01428 |
| Opus 5 | $0.00044 | $0.00714 |
| Sonnet 5 | $0.00017 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
camera-capture-depth-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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Camera Capture and Depth Workflow
Purpose
Guide AVFoundation camera, photo, depth, and computational-capture work while keeping general session topology, media pipelines, sample timing, audio policy, Vision analysis, and ARKit spatial sensing with their owning workflows.
When To Use
- Use for camera discovery, formats, controls, rotation, photo features, depth, calibration, synchronized outputs, mattes, pressure, and device-specific capture repair.
- Recommend
avfoundation-media-pipeline-workflowwhen general capture-session, output queue, player, asset, reader, writer, export, or back-pressure ownership is primary. - Recommend
vision-image-analysis-workflowwhen capture is working and image interpretation is the actual task.
Single-Path Workflow
- Classify the request:
- device discovery or selection
- format, frame rate, MultiCam, or constituent device
- focus, exposure, white balance, zoom, torch, stabilization, or low light
- rotation, orientation, or mirroring
- processed, RAW, bracketed, Live Photo, responsive, or deferred photo capture
- depth, disparity, calibration, or synchronized output
- portrait-effects, semantic, spatial, or cinematic capture
- authorization, interruption, pressure, dropped data, or runtime repair
- Apply the Apple docs gate:
- read current AVFoundation documentation for every requested feature and platform
- state the documented behavior relied on
- apply
../../shared/references/apple-camera-capability-contract.md - apply
../../shared/references/apple-media-type-ownership.md
- Discover before configuration:
- use
AVCaptureDevice.DiscoverySession, available devices, virtual-device constituents,AVCaptureDevice.Format, supported frame-rate ranges, depth formats, session support, output support, and connection support - never infer capability from a marketing device name, lens count, or OS version alone
- use
- Configure through one owner:
- keep session graph mutation on the serial session owner defined by
avfoundation-media-pipeline-workflow - balance
lockForConfiguration()andunlockForConfiguration()and mutate only supported device properties - configure output, settings, connection, rotation, mirroring, and delegate lifecycle explicitly
- keep session graph mutation on the serial session owner defined by
- Preserve typed capture data:
- keep
AVCapturePhoto,AVDepthData,AVCameraCalibrationData,AVPortraitEffectsMatte,AVSemanticSegmentationMatte,CMSampleBuffer, synchronized data, and dropped-data reasons inspectable - record timestamps, dimensions, orientation, pixel/depth formats, calibration, filtering, accuracy, and source identity
- keep
- Validate honestly:
- distinguish documented support, discovered runtime support, simulator limitations, and physically verified behavior
- return the capability evidence, configuration, output lifecycle, pressure/error policy, diagnostics, and device validation plan
What ships with it
5 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.
- 2d ago First seen · 95 lines · 87 tokens per session scan A ed4e295869eb
camera-capture-depth-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,428 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.
Other skills, from other repositories
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…
storescreens
Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…
poll-github-work
Poll and rank open GitHub issues, RFCs, and pull requests for maintainer work, or start one explicitly selected item. Use when a user asks what to work on, requests backlog priorities, says "poll work," wants actionable issues or pull requests, or says "start.
test
Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
ddg-apple-feedback-review
Invoke ONLY when the user explicitly runs /ddg-apple-feedback-review or names this skill by name. Do NOT auto-invoke from symptom/intent matching. If the user asks about Apple feedback, iOS or macOS issues, user reports, or feedback triage without naming this skill, answer directly instead.
release
Build, sign, notarize, and publish a new DroidProxy release. Use when the user wants to cut a release, merge a PR and ship it, or asks to build/notarize/publish. Covers the full pipeline: PR merge, version bump, swift build, code signing, Apple notarization, Sparkle appcast update, and GitHub release creation.