Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/evan108108/eyebrowse/skill)<a href="https://agentmods.dev/skills/evan108108/eyebrowse/skill"><img src="https://agentmods.dev/badge/skills/evan108108/eyebrowse/skill.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01427 |
| Opus 5 | $0.00009 | $0.00714 |
| Sonnet 5 | $0.00003 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
eyebrowse-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:7890/health How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eyebrowse Setup & Diagnostics
When this skill is invoked, run all diagnostic checks below in order and report a status table. Then offer to fix anything that's broken.
Architecture Quick Reference
Eyebrowse has three parts:
- Daemon — Bun HTTP/WS server on
localhost:7890(manages sessions, bridges MCP ↔ extension) - MCP Server — stdio wrapper that registers with the daemon and exposes browser tools to Claude Code
- Chrome Extension — WebSocket client that executes commands in Chrome via CDP
Flow: Claude Code → MCP (stdio) → Daemon (HTTP :7890) → Extension (WS) → Chrome
Diagnostic Checks
Run these checks and present results as a status table:
1. Daemon Health
curl -sf http://localhost:7890/health
- OK → daemon is running
- Connection refused → daemon is not running (see "Start the Daemon" below)
- Timeout → port 7890 may be blocked or daemon is hung
2. Extension Connected
Read the daemon token, then query windows:
TOKEN=$(cat ~/.eyebrowse/daemon.token 2>/dev/null)
curl -sf -H "Authorization: Bearer $TOKEN" http://localhost:7890/api/windows
- Returns JSON array with windows → extension is connected and Chrome is open
- Empty array
[]→ extension is installed but no Chrome windows are open - 401/no token → daemon token missing (daemon may need restart)
- Connection refused → daemon not running
3. MCP Config
Read ~/.claude.json and check for mcpServers.eyebrowse. It should look like:
{
"mcpServers": {
"eyebrowse": {
"command": "bun",
"args": ["run", "<EYEBROWSE_HOME>/mcp/index.ts"]
}
}
}
Where <EYEBROWSE_HOME> is the path to the eyebrowse repo (e.g. /Users/evan/memory/eyebrowse).
- Present and correct → MCP is configured
- Missing → add the config (see "Configure MCP" below)
- Wrong path → update the path to match the actual repo location
4. End-to-End Test
If checks 1-3 pass, run a live test:
- Call
mcp__eyebrowse__open_browserwith urlhttps://example.com - Call
mcp__eyebrowse__screenshot - Verify the screenshot shows the Example Domain page
- Call
mcp__eyebrowse__close_window
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.
- 6d ago First seen · 162 lines · 17 tokens per session scan A 31a7ca52b668
eyebrowse-setup is a skill published in the GitHub repository evan108108/eyebrowse (2 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,427 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
signed-in-browser
Drive the browser the user is already signed into, instead of a cold automation profile. Use when a task lives behind a login — a dashboard, an admin console, an internal tool, a ticket queue, a bank or billing page, webmail, a social account — or when a scripted login is failing on SSO, MFA, CAPTCHA or bot detection.…
post-to-hacker-news
Submit to Hacker News, including Show HN, by driving a signed-in browser. Use when launching a product, tool or MCP server, or when a submission needs its customary author comment. Covers the title rules, when a Show HN is allowed, the url-or-text choice, and how to tell a real submission from a silent failure.
qa-runner
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
browse
Use when asked to interact with a web browser — navigate, click, fill forms, take screenshots, run JavaScript, or read page content. Requires the browser-bridge MCP server and Chrome extension.
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…