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/garageband-workflownpx skills add gaelic-ghost/socket --skill garageband-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/garageband-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/garageband-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/garageband-workflow.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.00714 |
| Opus 5 | $0.00030 | $0.00357 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
garageband-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 3d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GarageBand Workflow
Use this skill for GarageBand app operation. GarageBand is a companion workflow, not an Apple Creator Studio subscription-app claim.
Source Check
Search the local Tips/Help Viewer catalog for GarageBand or open GarageBand Help. Confirm the guide matches the installed app/version. Read references/project-and-handoff-contract.md before recording, replacing regions, changing audio devices, exporting, or moving work into Logic Pro.
Workflow
- Classify the task: project setup, device/input issue, recording, software instrument/MIDI, Apple Loops, arrangement, automation, movie soundtrack, mix, export, missing content, or Logic Pro handoff.
- Establish the project contract: project location, source-preservation decision, tempo/key/sample-rate intent, device/input/monitoring requirements, target deliverable, output location, and overwrite rule.
- Inspect before changing: project settings, tracks, regions/takes, selected track controls, automation, plug-in state, audio/MIDI device state, existing media, unresolved warnings, and export state.
- Preserve recordings and project media. Use an explicit copy or non-destructive path before replacing recordings, deleting tracks/regions, flattening project decisions, or making broad routing changes.
- Configure only the needed audio/MIDI path. State the device, input, output, monitoring, and likely interruption consequence. Get confirmation immediately before recording or changing an audio-device/routing state.
- Make arrangement, loop, automation, or mix changes with a stated purpose. Do not replace a region, take, or loop selection merely to experiment unless the user has approved that edit.
- Before exporting or sharing, state the range, output type, quality settings, output name, destination, overwrite behavior, and whether the result is a review mix, final audio file, or a movie soundtrack. Get confirmation before writing output.
- Verify the resulting artifact exists in the intended directory, opens or plays, matches the intended range/format, and leaves the source project intact. For Logic Pro handoffs, state what transferred and what still needs inspection in Logic.
What ships with it
2 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.
- 3d ago First seen · 38 lines · 59 tokens per session scan A e048b4b94de5
garageband-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 59 tokens to every session and 714 once invoked, about $0.0003 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
caveman
Persistent token-compression mode (75% reduction) — now always-on by default. Strips filler while keeping code exact.
authoring-workflows
当你要调用 Workflow 工具，或要写 / 调试 / 启动一个 Claude Code dynamic-workflow 脚本时用——author / debug / launch a Claude Code dynamic-workflow script，当你要写 workflow 脚本时——哪怕你自觉已经懂这套 API。当你发现自己在猜 workflow 引擎的 determinism 或 resume 规则、没查 shape 就伸手够 parallel() / pipeline()、想手写一个 validation linter、或刚被 harness 报错正要 relaunch 时用。先查再猜，别等跑挂了才来。.
comfyui-core
Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage.
ai-toolkit-trainer
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
installer-packs
Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and tells you to invite the user to contribute new packs back upstream.
agentsop-context-scope-discipline
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under 25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-map, and drop files once edited. Use when an LLM coder-agent edits multiple files, when the working set must stay focused…