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 jacobrask/claude-skills --skill safari-tabsgit clone --depth 1 https://github.com/jacobrask/claude-skillsWrote 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/jacobrask/claude-skills/safari-tabs)<a href="https://agentmods.dev/skills/jacobrask/claude-skills/safari-tabs"><img src="https://agentmods.dev/badge/skills/jacobrask/claude-skills/safari-tabs/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/jacobrask/claude-skills/safari-tabs"><img src="https://agentmods.dev/badge/skills/jacobrask/claude-skills/safari-tabs.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 | $0.00119 | $0.00739 |
| Opus 5 | $0.00060 | $0.00369 |
| Sonnet 5 | $0.00024 | $0.00148 |
| Haiku 4.5 | $0.00012 | $0.00074 |
Grade A, and why
safari-tabs 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 12d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safari Tabs
Safari browser management via AppleScript.
Key Scripts
| Script | Purpose |
|---|---|
get_tabs.sh |
Get tabs with optional window filtering (TSV/markdown/JSON) |
close_by_pattern.sh |
RECOMMENDED: Close tabs matching URL pattern |
close_tabs.sh |
Close by window,tab index (advanced) |
find_duplicates.sh |
Find/close duplicate tabs |
domain_stats.sh |
Analyze tabs by domain |
export_tabs_*.sh |
Export as JSON/CSV/markdown/HTML |
get_reading_list.sh |
Export Reading List |
get_bookmarks.sh |
Export bookmarks |
search_history.sh |
Search history |
open_urls.sh |
Open URLs from file/stdin |
Getting Tabs
get_tabs.sh # All tabs as TSV
get_tabs.sh markdown # All tabs as markdown
get_tabs.sh -w 1 markdown # Window 1 only
get_tabs.sh -m "term" markdown # Window containing "term"
Closing Tabs
Always use close_by_pattern.sh (finds tabs by URL regardless of position):
close_by_pattern.sh "unique-url-substring"
# Examples
close_by_pattern.sh "adrianroselli.com"
close_by_pattern.sh "/article/css-has-guide"
Closes ALL matching tabs across all windows. Use unique substring.
Alternative: close by position (error-prone, avoid unless necessary):
close_tabs.sh "1,5" "2,3" # Window,tab pairs (1-indexed)
Analysis Workflow
- Fetch:
get_tabs.sh markdown - Analyze: group by domain, identify duplicates/clusters, flag stale content
- Report: stats, categorized list, suggestions
- Act: close with
close_by_pattern.sh "url-substring"
Process-and-close pattern:
- Fetch tab
- Process it
- Close:
close_by_pattern.sh "unique-url-part" - Next tab
Export Formats
export_tabs_markdown.sh [list|table|checklist|grouped]
export_tabs_json.sh
export_tabs_csv.sh
export_tabs_html.sh > bookmarks.html # Importable format
Other Features
Duplicates: find_duplicates.sh [--close]
Domain stats: domain_stats.sh
Reading list: get_reading_list.sh [tsv|markdown|json]
Bookmarks: get_bookmarks.sh [tree|flat|json]
History: search_history.sh [term] [--days N]
Open URLs: open_urls.sh urls.txt or pipe stdin
What ships with it
14 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.
- README.md 5.3 KB
- scripts/close_by_pattern.sh 722 B runs code
- scripts/close_tabs.sh 907 B runs code
- scripts/domain_stats.sh 2.0 KB runs code
- scripts/export_tabs_csv.sh 1.5 KB runs code
- scripts/export_tabs_html.sh 2.3 KB runs code
- scripts/export_tabs_json.sh 2.0 KB runs code
- scripts/export_tabs_markdown.sh 3.1 KB runs code
- scripts/find_duplicates.sh 2.3 KB runs code
- scripts/get_bookmarks.sh 3.2 KB runs code
- scripts/get_reading_list.sh 2.4 KB runs code
- scripts/get_tabs.sh 4.7 KB runs code
- scripts/open_urls.sh 1.7 KB runs code
- scripts/search_history.sh 2.1 KB runs code
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.
- 12d ago First seen · 85 lines · 119 tokens per session scan A 952f4996a643
safari-tabs is a skill published in the GitHub repository jacobrask/claude-skills (5 stars, last pushed 8mo ago), licensed MIT. It adds 119 tokens to every session and 739 once invoked, about $0.0006 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
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
cli-anything-macrocli
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes macro run and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
Apify
Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business…
BrightData
4-tier progressive web scraping that auto-escalates WebFetch to curl to Interceptor to Bright Data proxy for bot detection and CAPTCHAs, with single-URL and multi-page crawl modes, output as markdown. USE WHEN Bright Data, scrape URL, web scraping, bot detection, crawl site, CAPTCHA, can't access, site blocking…