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 vre/flow-state --skill firefox-controlgit clone --depth 1 https://github.com/vre/flow-stateWrote 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/vre/flow-state/firefox-control)<a href="https://agentmods.dev/skills/vre/flow-state/firefox-control"><img src="https://agentmods.dev/badge/skills/vre/flow-state/firefox-control/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/vre/flow-state/firefox-control"><img src="https://agentmods.dev/badge/skills/vre/flow-state/firefox-control.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 | $0.00027 | $0.01777 |
| Opus 5.5 | $0.00011 | $0.00711 |
| Sonnet 5.5 | $0.00005 | $0.00355 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
firefox-control 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 24d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firefox Control
Control Firefox via WebDriver BiDi on port 9223. Direct BiDi WebSocket, no geckodriver. Use port 9223 because more popular Chrome CDP occupies 9222.
Launch Firefox: firefox --remote-debugging-port 9223
TEST TOOL: navigator.webdriver=true — detected by every anti-bot
system. No toggle exists. Use Chrome CDP for production automation.
Usage
Just run a command — the daemon auto-starts on first call and connects to Firefox on port 9223. If Firefox isn't running or doesn't have remote debugging enabled, the error message will say so.
Full command list: uv run firefoxctl.py --help
Per-command help: uv run firefoxctl.py COMMAND --help
Always use uv run (PEP 723 inline dependencies):
uv run firefoxctl.py list
uv run firefoxctl.py --json list
uv run firefoxctl.py open https://example.com
uv run firefoxctl.py status
uv run firefoxctl.py targets
uv run firefoxctl.py stop
--json goes BEFORE the subcommand (global flag). The daemon idles out after 5 min. Unix socket: /tmp/firefoxctl-{uid}.sock. Tool responses are sanitized against prompt injection.
Target commands
All target commands: uv run firefoxctl.py CONTEXT COMMAND [ARGS]
Context ID from list output (full UUID required — no prefix match).
uv run firefoxctl.py CONTEXT eval "document.title"
uv run firefoxctl.py CONTEXT screenshot -o page.png
uv run firefoxctl.py CONTEXT console-tail --for 30
uv run firefoxctl.py CONTEXT navigate https://example.com
navigate and open may hand you a different context back. Firefox sometimes answers a
navigation by replacing the browsing context rather than reusing it — the id you
asked for is destroyed and a new one appears at the target URL. navigate follows
the swap when it can identify the replacement:
uv run firefoxctl.py --json navigate "$ctx" https://example.com/feed.json
# {"navigation": "...", "url": "...", "context": "<same id>"}
# {"navigation": null, "url": "...", "context": "<NEW id>", "context_swapped": true}
What ships with it
7 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.
- 24d ago Changed · +98 lines · -10 tokens per session a355322402ef
- 1mo ago First seen · 84 lines · 37 tokens per session scan A f9e49487ca3f
firefox-control is a skill published in the GitHub repository vre/flow-state (11 stars, last pushed 25d ago), licensed MIT. It adds 27 tokens to every session and 1,777 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
browser-mode
Show or switch how web-interact connects to the browser: auto (CLI decides), real (user's running Chrome/Edge), or sandbox (managed browser with persistent profile).
mode
Show or switch the web-interact browser engine between default (Playwright) and assistant (Patchright). Use when the user asks to change browser mode, enable stealth/assistant mode, or check which engine is active.
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
web-interact
Browser automation CLI for navigating websites, filling forms, clicking buttons, extracting data, taking screenshots, and automating any web workflow. Use when users ask to interact with a website, test a web app, fill a form, scrape data, take screenshots, log into a service, automate a browser task, or inspect a web…
proof-video
Capture, edit, inspect, and attach real ClawHub browser proof directly to a GitHub PR, with captions, focused zooms, and clearly separated before/after results.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser…