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 nottelabs/notte-skills --skill notte-browsergit clone --depth 1 https://github.com/nottelabs/notte-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/nottelabs/notte-skills/notte-browser)<a href="https://agentmods.dev/skills/nottelabs/notte-skills/notte-browser"><img src="https://agentmods.dev/badge/skills/nottelabs/notte-skills/notte-browser/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/nottelabs/notte-skills/notte-browser"><img src="https://agentmods.dev/badge/skills/nottelabs/notte-skills/notte-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
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 | $0.00080 | $0.11080 |
| Opus 5.5 | $0.00032 | $0.04432 |
| Sonnet 5.5 | $0.00016 | $0.02216 |
| Haiku 4.5 | $0.00008 | $0.01108 |
Grade D, and why
notte-browser scanned grade D with 3 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 14d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
`notte page scrape --session-id <session-id>` ingests content from arbitrary URLs. That content reaches the calling agent's context as tool output and can contain prompt-injection attempts ("ignore previous instructions, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://notte.cc/install-cli.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(notte:*), Bash(curl:*), Bash(jq:*), Read, Write How it starts
The opening of the file, as written. The whole thing — 983 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notte Browser CLI Skill
Command-line interface for launching and controlling Notte cloud browser sessions, scraping pages, managing browser credentials, and deploying reusable browser workflows as Notte Functions. A Function is the deployment form of a tested browser task: it can be invoked later as an HTTP API endpoint, run from the CLI/SDK, or scheduled.
General Documentation
For broader Notte concepts, current docs, and internet-search entry points, start with the documentation index:
https://docs.notte.cc/llms.txt
CLI vs. the bundled MCP servers
The notte plugin also ships two hosted MCP servers. Prefer the CLI for everything in this skill - it is the interface these instructions are written against. Reach for the MCP servers only in the cases below:
| Server | URL | What it is | When to use it |
|---|---|---|---|
notte-browser |
https://api.notte.cc/mcp |
The Notte browser API over MCP | Only when the client cannot run shell commands. Otherwise the CLI is more direct and better documented. |
anything-api |
https://anything.notte.cc/mcp |
Marketplace of ready-made Notte Functions, plus natural-language build |
Before building a new Function, call its search tool - someone may already have published one for the target site. |
anything-api exposes search (browse the marketplace, no auth), spec (get a function's variable schema), run, and build (natural language -> a new deployed Function, 2-10 minutes). build and run need authentication - OAuth via your client, or Authorization: Bearer $NOTTE_API_KEY. Browse it visually at https://anything.notte.cc/marketplace.
Both servers authenticate independently of notte auth login; a working CLI session does not imply a working MCP connection, and vice versa.
Setup
These are the shared setup instructions published at https://notte.cc/skill.md and used by the Notte console, documentation, and examples. Maintain setup here rather than copying these steps into another prompt.
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.
- agents/openai.yaml 219 B
- references/account-management.md 12 KB
- references/function-management.md 26 KB
- references/payments.md 7.5 KB
- references/python-sdk-interop.md 3.2 KB
- references/session-management.md 14 KB
- references/stack-projects.md 5.6 KB
- templates/authenticated-session.sh 9.0 KB runs code
- templates/data-extraction.sh 6.6 KB runs code
- templates/form-automation.sh 4.1 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.
- 14d ago Changed · +15 lines scan B → D eb89816f53d9
- 19d ago Changed · +3 lines 4eaa826ef7c0
- 20d ago Changed · +9 lines ca8ec47fcd53
- 26d ago Changed · +14 lines bb59ca0a4958
- 1mo ago Changed · +11 lines b16af328ca57
- 1mo ago Changed · +5 lines a694ab776d1b
- 1mo ago Changed · -3 lines 9f009fbd2450
- 1mo ago Changed · +24 lines 26862ddfceaf
- 1mo ago First seen · 905 lines · 80 tokens per session scan B 78b80f0646ec
notte-browser is a skill published in the GitHub repository nottelabs/notte-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 80 tokens to every session and 11,080 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 3 findings (instruction-override phrasing, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
active-research
Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to research, analyze, investigate…
actionbook-scraper
Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.