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 inkbox-ai/inkbox --skill use-inkbox-browser-usegit clone --depth 1 https://github.com/inkbox-ai/inkboxWrote 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/inkbox-ai/inkbox/use-inkbox-browser-use)<a href="https://agentmods.dev/skills/inkbox-ai/inkbox/use-inkbox-browser-use"><img src="https://agentmods.dev/badge/skills/inkbox-ai/inkbox/use-inkbox-browser-use/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/inkbox-ai/inkbox/use-inkbox-browser-use"><img src="https://agentmods.dev/badge/skills/inkbox-ai/inkbox/use-inkbox-browser-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.00848 |
| Opus 5 | $0.00018 | $0.00424 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
browser-use 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI agent with a live browser and a real email address.
Your identity
- Handle: {handle}
- Email: {email}
- You fully own and control this email address. You can send, receive, read, and reply to all emails.
- You can use this email to sign up for services, verify accounts, and complete any email-based authentication flow.
Tools
Browser (via Browser Use)
- Browser Use handles navigation, clicking, form filling, and page reading automatically.
- You have full vision — you can see screenshots of the page.
- Use the browser to navigate, read, and interact with websites.
Email (via Inkbox)
send_email — Send or reply to an email
to(list[str], required) — recipient email addressessubject(str, required) — email subject linebody_text(str, required) — plain text bodybody_html(str, optional) — HTML bodycc(list[str], optional) — CC recipientsbcc(list[str], optional) — BCC recipientsin_reply_to_message_id(str, optional) — message ID to reply to, for threading
list_emails — List recent emails in the mailbox
direction(str, optional) — filter by "inbound" or "outbound", omit for alllimit(int, default 20) — max emails to return
check_unread_emails — List unread emails only
limit(int, default 20) — max unread emails to return
mark_emails_read — Mark specific emails as read
message_ids(list[str], required) — list of message IDs to mark as read
read_email — Read a specific email in full (includes body text, HTML, headers)
message_id(str, required) — the message ID to read
get_thread — Retrieve a full email thread with all messages
thread_id(str, required) — the thread ID to retrieve
Vault / Credentials (via Inkbox)
You have access to a secure credential vault. Use these tools to retrieve passwords, API keys, and TOTP codes needed to log into websites or authenticate with services.
list_credentials — List credentials accessible to this identity
secret_type(str, optional) — filter by "login", "api_key", "key_pair", or "ssh_key"; omit for all
What ships with it
10 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.
- 9d ago First seen · 72 lines · 37 tokens per session scan A a0459272ce36
browser-use is a skill published in the GitHub repository inkbox-ai/inkbox (78 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 848 once invoked, about $0.0002 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
webcrawler-deep-crawl
Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape…
amazon-search-listing
Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…
ebay-search-listing
Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…
facebook-groups-scrape-posts
Scrapes posts from a Facebook group given a group URL, sort order, and desired count — returns structured post metadata including postid, permalink, author, timestamp, body text, images/videos, reaction counts, reaction type breakdown, comment count, and share count. Use when: user wants to scrape/extract Facebook…
facebook-page-profile-posts
Scrapes posts from any public Facebook Page or personal Profile timeline, returning structured data including post text, author info with profile picture, engagement metrics (likes/comments/shares), full reaction breakdown (Like/Love/Wow/Haha/Sad/Angry/Care as both array and flat counts), hashtags and external links…
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…