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 unbrowse-ai/unbrowse --skill skillgit clone --depth 1 https://github.com/unbrowse-ai/unbrowseWrote 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/unbrowse-ai/unbrowse/skill)<a href="https://agentmods.dev/skills/unbrowse-ai/unbrowse/skill"><img src="https://agentmods.dev/badge/skills/unbrowse-ai/unbrowse/skill/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/unbrowse-ai/unbrowse/skill"><img src="https://agentmods.dev/badge/skills/unbrowse-ai/unbrowse/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.04134 |
| Opus 5.5 | $0.00019 | $0.01654 |
| Sonnet 5.5 | $0.00010 | $0.00827 |
| Haiku 4.5 | $0.00005 | $0.00413 |
Grade A, and why
unbrowse 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unbrowse
Use the hosted service at https://unbrowse.ai. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then Allow. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
- MCP: if
unbrowse_discoveris in this session's tool list, the MCP is signed in. - CLI:
npx unbrowse whoami. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}}
The host runs the OAuth sign-in itself (in Claude Code: /mcp, pick unbrowse, Authenticate). Do not put a bearer header in the config; with one set, hosts skip OAuth. A URL in a config is not a signed-in session: until the host finishes OAuth, the Unbrowse tools are not listed.
Sign in the CLI:
npx skills add unbrowse-ai/unbrowse && npx unbrowse login
unbrowse login opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses Allow; the CLI prints Signed in to https://unbrowse.ai (workspace ws_…) and stores the token at ~/.config/unbrowse/cli.json (mode 0600, refreshed automatically).
From an agent's shell (no terminal for the person): run npx unbrowse login --no-open in the background, give the person the https://unbrowse.ai/authorize?… link it prints, and wait for the Signed in line. The link returns to 127.0.0.1 on this machine, so the person must open it in a browser on the same machine. On a remote or headless box, run npx unbrowse login --device and approve the code it shows from any device, or use an API key (below). Any other command run with no sign-in starts the same browser sign-in when it has a terminal; without one it exits 3 and asks for unbrowse login.
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.
- 9d ago Changed 79965d41b4c5
- 16d ago Changed · +8 lines 3a439ae260f4
- 17d ago Changed · +4 lines · -4 tokens per session 1f5ea8a201b6
- 29d ago Changed · +32 lines d8ea2e997aec
- 1mo ago Changed · -19 lines · -8 tokens per session a78b35b1b60b
- 1mo ago Changed · -259 lines · -139 tokens per session 0d1e906702c5
- 1mo ago First seen · 387 lines · 199 tokens per session scan A 1cba1bca74bb
unbrowse is a skill published in the GitHub repository unbrowse-ai/unbrowse (810 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 4,134 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
transcriptapi
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, or anything…
youtube-playlist
Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.
cross-validated-search
OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. Use it to verify factual answers with live search results and explicit source handling.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
travel-explore
You are a network explorer on a travel adventure. Your mission is to browse the internet freely, discover interesting content, and optionally interact socially on the Naga Network forum.
agent-browser
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…