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/jacklandrin/onlyswitch/onlyswitch-deeplinknpx skills add jacklandrin/OnlySwitch --skill onlyswitch-deeplinkgit clone --depth 1 https://github.com/jacklandrin/OnlySwitchWrote 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/jacklandrin/onlyswitch/onlyswitch-deeplink)<a href="https://agentmods.dev/skills/jacklandrin/onlyswitch/onlyswitch-deeplink"><img src="https://agentmods.dev/badge/skills/jacklandrin/onlyswitch/onlyswitch-deeplink.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 | $0.00085 | $0.00468 |
| Opus 5 | $0.00043 | $0.00234 |
| Sonnet 5 | $0.00017 | $0.00094 |
| Haiku 4.5 | $0.00009 | $0.00047 |
Grade A, and why
onlyswitch-deeplink 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 4d 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.
What it actually says
OnlySwitch Deeplink
Invoke OnlySwitch built-in switches or one-shot buttons by opening its deeplink. OnlySwitch must be installed and allowed to handle the onlyswitch:// URL scheme.
Workflow
-
Resolve intent to switch id
Map the user's request to a single built-in switch/button using references/switch-ids.md. Match phrases like "empty trash", "toggle keep awake", "mute mic", "clear xcode cache" to the correct id (e.g. empty trash → 16384, keep awake → 16). -
Open the deeplink
Run on the user's machine (macOS):open "onlyswitch://run?type=builtIn&id=<id>"Replace
<id>with the numeric id from the reference table. Example for "empty trash":open "onlyswitch://run?type=builtIn&id=16384" -
Confirm
Tell the user which action was triggered (e.g. "Emptied trash via OnlySwitch" or "Toggled Keep Awake via OnlySwitch").
Notes
- One deeplink per request: resolve to exactly one switch id per user message.
- If the request doesn't match any built-in (e.g. custom switch or unknown action), say that OnlySwitch deeplinks only support the built-in list and suggest checking the app or docs.
- IDs are raw enum values from
SwitchTypein the OnlySwitch app (see project'sSwitchType.swiftfor the source of truth; this skill's reference table is derived from it).
What ships with it
1 file 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.
- 4d ago First seen · 37 lines · 85 tokens per session scan A 97ca6303b5e8
onlyswitch-deeplink is a skill published in the GitHub repository jacklandrin/OnlySwitch (5,904 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 468 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 2026-08-30.
Other skills, from other repositories
awesome-swift-macos-apps-docs
Use when adding, updating, or validating app entries in the awesome-swift-macos-apps repository, especially when maintaining both README.md and README.zh.md with concise one-sentence descriptions, correct category placement, and consistent bilingual formatting.
vocello-design
Use this skill to generate well-branded interfaces and assets for Vocello (a local-first, Apple-native macOS voice-generation app — formerly QwenVoice). Contains essential design guidelines, colors, type, fonts, assets, and a Mac-app UI kit for prototyping voice-studio interfaces, marketing surfaces, and slides.
maintainer-bar
Operate the MaintainerBar SwiftUI menu bar app and its ghcrawl backend. Use for: refreshing issue clusters, searching issues semantically, checking repo pulse, managing notifications, building/running the app, and coordinating ghcrawl data pipelines.
swift-focusengine-pro
Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.
github-issue-workflow
How to start work on a GitHub issue in the munkel repo — check for an existing draft PR and the issue's assignee first to avoid duplicating work someone already owns, claim the issue by assigning it, then open a draft PR linked with "Closes.
macos-patterns
Essential native macOS development patterns that web developers don't know about. Use this skill whenever the user is building a macOS app and needs guidance on native patterns, or when they ask about menu bar apps, floating panels, window levels, keyboard shortcuts, file pickers, clipboard, drag and drop, screen…