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 afaraha8403/balakit --skill cloakbrowser-fallbackgit clone --depth 1 https://github.com/afaraha8403/balakitWrote 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/afaraha8403/balakit/cloakbrowser-fallback)<a href="https://agentmods.dev/skills/afaraha8403/balakit/cloakbrowser-fallback"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/cloakbrowser-fallback/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/afaraha8403/balakit/cloakbrowser-fallback"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/cloakbrowser-fallback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00100 | $0.01270 |
| Opus 5.5 | $0.00040 | $0.00508 |
| Sonnet 5.5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
cloakbrowser-fallback 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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloakBrowser Fallback
Leading words: stealth browser, fallback, humanize, bot detection, Turnstile, headless failover, real Chromium binary.
Stealth Chromium for navigating sites that block ordinary automation. Drop-in Playwright API, but the browser is a custom-compiled Chromium binary, so detectors score it as a real human browser.
Already installed on this machine. Both languages share the same stealth binary at ~/.cloakbrowser/:
- Python (global):
pippackagecloakbrowser. - JS (self-contained in this skill's
scripts/): npmcloakbrowser+playwright-core.
Prefer Python by default. Use JS when the target codebase/repo is JS/TS or the user asks for it.
When to reach for this
Use as a fallback only — try the built-in browser tool or Chrome DevTools
MCP first. Escalate to CloakBrowser when any of the triggers in the
frontmatter when_to_use fire (403/429, Cloudflare/Turnstile/reCAPTCHA walls,
empty/blocked response, explicit user ask).
Headless failover pattern: start headless. If a Turnstile managed
challenge appears, re-run with --headed — it clears with one click after the
page settles. If an image CAPTCHA appears, stop and report to the user —
CloakBrowser does not solve image CAPTCHAs.
Quick start (one-shot fetch)
Run the helper — it prints final URL, title, and page text, and saves a screenshot.
Python:
python scripts/cloak_fetch.py "https://protected-site.com"
JS (run from this skill's scripts/ dir so node_modules resolves):
node scripts/cloak_fetch.mjs "https://protected-site.com"
Both accept the same flags:
--headed— show the window. Needed for Turnstile managed challenges (resolves with a single click).--screenshot path.png— where to save the screenshot (default:cloak_shot.png).--html path.html— also dump raw HTML.--wait 5000— extra ms to wait after load for JS challenges to clear.
Inline usage (when you need custom interaction)
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.
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.
- 1mo ago First seen · 133 lines · 100 tokens per session scan A 9d7fa2775c61
cloakbrowser-fallback is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,270 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-websearch
Search the web by keyword or reverse-search images with Moli to find subjects, sources, exact matches, or similar images—even when Moli is not named. For fetching a known URL, use moli-webfetch.