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 safari-extension-control-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/safari-extension-control-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/safari-extension-control-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/safari-extension-control-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/safari-extension-control-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/safari-extension-control-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 | $0.00091 | $0.02229 |
| Opus 5.5 | $0.00036 | $0.00892 |
| Sonnet 5.5 | $0.00018 | $0.00446 |
| Haiku 4.5 | $0.00009 | $0.00223 |
Grade A, and why
safari-extension-control-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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safari Extension Control Workflow
Purpose
Guide Safari integration work for macOS apps, with enough platform awareness to choose the right Safari extension or SafariServices surface before implementation starts.
This skill owns the decision between Safari Web Extensions, Safari Web Inspector Extensions, Safari App Extensions, content blockers, SafariServices APIs, app-to-extension messaging, and limited external automation paths. It is not a generic browser-extension guide and it is not a replacement for xcode-build-run-workflow or xcode-testing-workflow.
When To Use
- Use this skill when the user wants a macOS app to extend Safari, communicate with Safari content, or coordinate native app state with a Safari extension.
- Use this skill when choosing between a Safari Web Extension, Safari Web Inspector Extension, Safari App Extension, Safari content blocker,
SFSafariApplication,SFSafariExtensionManager,SFSafariViewController,ASWebAuthenticationSession, AppleScript, Shortcuts, or URL-opening behavior. - Use this skill when the work involves WebExtension manifests, Web Inspector developer-tool panels, native messaging, app groups, injected scripts, toolbar items, content blockers, Safari profiles, temporary extension loading, unsigned extension testing, or App Store distribution.
- Use this skill when a user says they want to "control Safari" from a Mac app and the first job is distinguishing supported SafariServices control from broader GUI or scripting automation.
- Recommend
explore-apple-swift-docswhen the user primarily needs direct Apple documentation lookup rather than integration-shape guidance. - Recommend
xcode-build-run-workflowwhen the next step is target setup, build settings, entitlements, signing, file membership, running the containing app, or guarded Xcode project mutation. - Recommend
xcode-testing-workflowwhen the next step is repeatable XCTest, XCUITest, extension-state checks, or test-plan work. - Recommend
swiftui-app-architecture-workflowwhen the Safari work is settled and the remaining question is native app scene, command, focus, or settings structure.
What ships with it
7 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.
- agents/openai.yaml 728 B
- references/extension-shape-decision.md 5.5 KB
- references/messaging-shared-data-and-permissions.md 2.9 KB
- references/safari-services-control-surfaces.md 3.0 KB
- references/snippets/apple-xcode-project-core.md 26 KB
- references/testing-debugging-and-distribution.md 3.4 KB
- references/web-inspector-extensions.md 2.5 KB
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 · 142 lines · 91 tokens per session scan A 13b4fc30d3a3
safari-extension-control-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,229 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
browser-agent
Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.
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.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.