Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kwannoel/the-controllernpx agentmods add skills/kwannoel/the-controller/firefox-browserWrote 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/kwannoel/the-controller/firefox-browser)<a href="https://agentmods.dev/skills/kwannoel/the-controller/firefox-browser"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/firefox-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/kwannoel/the-controller/firefox-browser"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/firefox-browser.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 | $0.00085 | $0.04681 |
| Opus 5.5 | $0.00034 | $0.01872 |
| Sonnet 5 | $0.00017 | $0.00936 |
| Haiku 4.5 | $0.00009 | $0.00468 |
Grade C, and why
firefox-browser scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
execSync(`rm -rf "${tempProfile}" && cp -R "${sourceProfile}" "${tempProfile}"`); Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { execSync } = require('child_process'); How it starts
The opening of the file, as written. The whole thing — 620 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firefox Browser Automation with Playwright
Always use the user's real Firefox profile instead of launching a fresh automated instance. Fresh automated browsers get flagged by bot detection (Google login bans, CAPTCHAs, account locks). Using the real profile inherits cookies, extensions, and fingerprint.
Uses Playwright's Firefox engine. Install with npx playwright install firefox.
Setup: Find Your Firefox Profile
# macOS
ls ~/Library/Application\ Support/Firefox/Profiles/
# Look for: xxxxxxxx.default-release
# Linux
ls ~/.mozilla/firefox/
Set the FIREFOX_PROFILE env var for convenience:
# macOS
export FIREFOX_PROFILE="$HOME/Library/Application Support/Firefox/Profiles/YOUR_PROFILE.default-release"
# Linux
export FIREFOX_PROFILE="$HOME/.mozilla/firefox/YOUR_PROFILE.default-release"
Core Pattern — Use Real Profile
Copy the user's profile to a temp directory (avoids lock conflicts with running Firefox) and launch with it:
node <<'SCRIPT'
const { firefox } = require('playwright');
const { execSync } = require('child_process');
const os = require('os');
const path = require('path');
(async () => {
const sourceProfile = process.env.FIREFOX_PROFILE;
const tempProfile = path.join(os.tmpdir(), 'firefox-automation-profile');
// Copy profile (preserves cookies, extensions, history)
execSync(`rm -rf "${tempProfile}" && cp -R "${sourceProfile}" "${tempProfile}"`);
// Remove lock files and compatibility markers (Playwright's Firefox is a different version)
execSync(`rm -f "${tempProfile}/lock" "${tempProfile}/.parentlock" "${tempProfile}/parent.lock" "${tempProfile}/compatibility.ini"`);
const context = await firefox.launchPersistentContext(tempProfile, {
headless: false,
});
const page = context.pages()[0] || await context.newPage();
await page.goto('https://example.com');
await page.waitForLoadState('domcontentloaded');
console.log('Title:', await page.title());
console.log('URL:', page.url());
await page.screenshot({ path: '/tmp/firefox-screenshot.png' });
await context.close();
})();
SCRIPT
What ships with it
3 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.
- yesterday First seen · 620 lines · 85 tokens per session scan C 4bf5903ab178
firefox-browser is a skill published in the GitHub repository kwannoel/the-controller (13 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 4,681 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.