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 citedy/adclaw --skill camoufoxgit clone --depth 1 https://github.com/citedy/adclawWrote 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/citedy/adclaw/camoufox)<a href="https://agentmods.dev/skills/citedy/adclaw/camoufox"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/camoufox.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00407 |
| Opus 5 | $0.00031 | $0.00204 |
| Sonnet 5 | $0.00012 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
camoufox 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.
What it actually says
Camoufox
Use instead of OpenClaw's built-in browser tool for bot-detection sites.
Setup (one-time)
bash scripts/setup.sh
Usage
source ~/.openclaw/workspace/camoufox-env/bin/activate
xvfb-run -a --server-args="-screen 0 1920x1080x24" python3 your_script.py
Required Settings
from camoufox.sync_api import Camoufox
with Camoufox(
headless=False, # MUST be False (True gets detected)
os='linux', # MUST match server OS (stack traces leak real OS)
humanize=True,
persistent_context=True,
user_data_dir='~/.openclaw/camoufox-profile'
) as browser:
page = browser.new_page()
# Use standard Playwright API from here
Paths
- venv:
~/.openclaw/workspace/camoufox-env/ - profile:
~/.openclaw/camoufox-profile/
CAPTCHA Handling
First visit to protected sites may need manual CAPTCHA:
DISPLAY=:1 python3 scripts/login_session.py https://site.com/login
Solve via VNC, session saves to profile for future automation.
Scripts
scripts/setup.sh- Install dependenciesscripts/browse.py <url> --screenshot out.png- Quick browsescripts/login_session.py <url>- VNC manual login
What ships with it
5 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.
- 8d ago First seen · 52 lines · 62 tokens per session scan A c030815ec8d1
camoufox is a skill published in the GitHub repository citedy/adclaw (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 407 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.
Other skills, from other repositories
playwright-uitest
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.
actionbook
MUST USE AUTOMATICALLY when user sends URLs from x.com, twitter.com, or any site that webfetch fails on. Do NOT ask the user — just load this skill and use it. Browser automation and web scraping with anti-detection stealth mode. Capabilities: (1) Scrape Twitter/X content without login, (2) Extract data from…
browser
A browser-control skill for opening web pages, interacting with them, viewing browser history, and managing bookmarks. It can use a separate browser session for actions such as clicking, filling forms, and taking screenshots.
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
update-setup
A one-time setup wizard for creating a personalised upgrade skill in a nanobot agent workspace. It checks whether an upgrade skill already exists and gathers version and installation details.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.