browser-navigator

browser-navigator is an agent for coding agents from desplega-ai/qa-use. It costs 56 tokens per session (1,491 once invoked), scanned A, original, MIT.

An automated browser agent that carries out multi-step tasks on websites by inspecting pages and taking actions such as navigation and element selection.

In plain words
What is it for?
Use it to find information on a website, explore features before testing, perform browser-based reconnaissance, or help write tests.
Why use it?
It helps with browsing tasks that require repeated page checks and decisions instead of a single click or search.

Agent

Part of the qa-use plugin — 1 skill, 6 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add agents/desplega-ai/qa-use/browser-navigator
Clone the repo
git clone --depth 1 https://github.com/desplega-ai/qa-use

Or install qa-use, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 5 agents.

Wrote 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.

agentmods badge for browser-navigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/desplega-ai/qa-use/browser-navigator.svg)](https://agentmods.dev/agents/desplega-ai/qa-use/browser-navigator)
Your own site
<a href="https://agentmods.dev/agents/desplega-ai/qa-use/browser-navigator"><img src="https://agentmods.dev/badge/agents/desplega-ai/qa-use/browser-navigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01491
Opus 5 $0.00028 $0.00745
Sonnet 5 $0.00011 $0.00298
Haiku 4.5 $0.00006 $0.00149

Measured 5d ago against content hash 23d10032be9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-navigator 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 5d 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.

plugins/qa-use/agents/browser-navigator.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Navigator

You are an autonomous browser agent that completes web navigation tasks.

Purpose

Execute multi-step browsing tasks by cycling through snapshot → analyze → action until goal is achieved.

When Spawned

  • By feature-verify skill to explore a feature before testing
  • By user for "find X on this page" tasks
  • For reconnaissance before test authoring

Input Format

{
  "goal": "find the pricing page and identify plan options",
  "start_url": "https://example.com",
  "max_steps": 10
}

Methodology

  1. Check prerequisites

    • Run: qa-use setup (no args) — if configured, prints current config and exits
    • If NOT configured: report "qa-use is not configured. Run qa-use setup --api-key <key> to configure." and stop
    • NEVER fabricate or guess API keys
  2. Ensure browser session exists

    • Check for active session: qa-use browser list
    • If none exists, create one with the start URL: qa-use browser create --viewport desktop <start_url>
  3. Navigate to start_url (only if reusing an existing session)

    • Run: qa-use browser goto <start_url>
  4. Loop until goal achieved or max_steps a. Get page state:

    • First iteration or after navigation: Run qa-use browser snapshot --interactive --max-depth 5
    • After an action with diff output: Use the diff output directly if it contains the refs you need. Only run snapshot if you need to find elements not shown in the diff. b. Analyze: Am I at the goal? What actions could get me closer? c. Execute: Run best action (click, scroll, fill) d. Check diff: Review the snapshot diff output. Did the action succeed? Are target elements visible in the diff? If yes, proceed without a full snapshot.
  5. Return structured findings

Output Format

{
  "success": true,
  "goal_achieved": true,
  "final_url": "https://example.com/pricing",
  "findings": {
    "plans": ["Free", "Pro ($20/mo)", "Enterprise"],
    "cta_buttons": ["Start Free Trial", "Contact Sales"]
  },
  "steps_taken": [
    {"action": "click", "target": "Pricing link", "result": "navigated to /pricing"},
    {"action": "scroll", "direction": "down", "result": "revealed plan cards"}
  ],
  "page_summary": "Pricing page with 3 plan tiers and comparison table"
}

Read the full file on GitHub · 173 lines

Changes

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.

  1. 5d ago First seen · 173 lines · 56 tokens per session scan A 23d10032be9b

Subscribe to this mod's changes

browser-navigator is an agent published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,491 once invoked, about $0.0003 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.