stealth-browser

stealth-browser is a skill for Claude Code, Codex from WingedGuardian/GENesis-AGI. It costs 13 tokens per session (3,030 once invoked), scanned A, original, MIT.

A set of behaviour rules for browser automation designed to reduce signs that an automated browser is a bot. It applies across supported browser engines and focuses on actions and timing rather than browser fingerprints alone.

In plain words
What is it for?
Use it when navigating websites with the default Camoufox anti-detection browser, including profile warm-up, timing, headed display, and human-observation modes.
Why use it?
Bot-detection systems can notice repetitive or robotic behaviour even when the browser looks like a normal one. The rules guide more human-like navigation and account for whether a person is watching.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it when navigating websites with the default Camoufox anti-detection browser, including profile warm-up, timing, headed display, and human-observation modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wingedguardian/genesis-agi/stealth-browser
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.

Any agent
npx skills add WingedGuardian/GENesis-AGI --skill stealth-browser
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/GENesis-AGI

Made for: Claude Code, Codex.

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 stealth-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/stealth-browser.svg)](https://agentmods.dev/skills/wingedguardian/genesis-agi/stealth-browser)
Your own site
<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/stealth-browser"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/stealth-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00013 $0.03030
Opus 5 $0.00006 $0.01515
Sonnet 5 $0.00003 $0.00606
Haiku 4.5 $0.00001 $0.00303

Measured 8d ago against content hash 95be940c3576, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

stealth-browser 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 8d 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.

src/genesis/skills/stealth-browser/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stealth Browser Skill

Tool-agnostic anti-detection behavioral rules for browser automation. Applies regardless of browser engine (Camoufox, Playwright, future tools).

Load this skill when: The browser_navigate tool is used with the default Camoufox (anti-detection) mode. The tool's docstring directs you here.

Core Principle

Bot detection systems look for behavioral signals, not just fingerprints. A perfect fingerprint with robotic behavior is still detectable. The browser engine handles fingerprinting. This skill handles behavior.


Always-Headed Mode

Camoufox always launches headed on VNC display :99. This means:

  • Human can always observe the browser via noVNC
  • CAPTCHA/Turnstile escalation doesn't require browser restart
  • browser_collaborate(True) speeds up timing (human watching)
  • browser_collaborate(False) restores stealth timing (nobody watching)

Layer 1: Current Infrastructure (use now)

These rules work with the existing browser tools. The tools already implement human-like delays automatically — this section covers what YOU (the LLM session) must do on top.

Profile Pre-Warming

Before navigating to a target form (especially ATS job applications), browse the company's public careers page first. This builds browsing history and cookie trail in the persistent profile. A cold browser going straight to an application form is a bot signal.

Page Load Warm-Up

After browser_navigate, wait before interacting. Read the page snapshot, plan your actions. Do NOT immediately call browser_fill or browser_click. A human would look at the page first. 1-3 seconds minimum.

Honeypot Detection

Before filling ANY form field, check the accessibility snapshot for hidden fields. Do NOT fill fields that appear to be:

  • display: none or visibility: hidden in the snapshot
  • Zero-dimension elements
  • Fields with names like url, website, fax that aren't expected for the form type (common honeypot names)
  • Fields positioned off-screen

Read the full file on GitHub · 335 lines

Files

What ships with it

4 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.

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. 8d ago First seen · 335 lines · 13 tokens per session scan A 95be940c3576

Subscribe to this mod's changes

stealth-browser is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 3,030 once invoked, about $0.0001 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.