Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
mini-browser - Skill - OpenSmartRoute
Skillv1.0.0
mini-browser
Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or…
Imported from runablehq/mini-browser (skill/SKILL.md) via skills.sh. Install upstream with npx skills add runablehq/mini-browser --skill skill. Copyright stays with the author.
mini-browser (mb) — Browser CLI for Agents
mb is a browser CLI where each command is a small Unix tool. It talks to Chrome over CDP (port 9222) via puppeteer-core.
Setup (only if not already available)
Setup is only needed when mb is not installed or Chrome is not reachable.
Run these checks first — if both pass, skip straight to the Command Reference.
Check if ready
# 1. Is mb installed?which mb && echo "mb: ok" || echo "mb: MISSING"# 2. Is Chrome listening on CDP?curl -sf http://127.0.0.1:9222/json/version > /dev/null && echo "chrome: ok" || echo "chrome: NOT RUNNING"
If both print "ok", everything is ready — go use mb commands directly.
Install (only if mb is missing)
npm install -g @runablehq/mini-browser
Start Chrome (only if not running)
mb-start-chrome
This launches Chrome with --remote-debugging-port=9222, a fresh profile, and a
1024×768 window. It no-ops if Chrome is already running.
To kill and relaunch:
mb-restart-chrome
Verify
mb go "https://example.com" && mb text
Environment Variables
Variable
Default
Description
CHROME_PORT
9222
CDP port
CHROME_BIN
auto-detected
Path to Chrome/Chromium binary
CHROME_PID_FILE
<scripts>/.chrome-pid
PID file location
CHROME_USER_DATA_DIR
<scripts>/.chrome-profile
Chrome profile directory
Command Reference
Navigation
Command
Description
mb go <url>
Navigate to URL (waits for networkidle)
mb url
Print current URL
mb back
Go back
mb forward
Go forward
Observation
Command
Description
mb text [selector]
Visible text content (default: body)
mb shot [file]
Screenshot to PNG (default: ./shot.png)
mb snap
List interactive elements with coordinates
Interaction
Command
Description
mb click <x> <y>
Click at coordinates
mb type [x y] <text>
Type text (with coords: selects first)
mb fill <k=v...>
Fill form fields by label/name/placeholder
mb key <key...>
Press keys (Enter, Tab, Meta+a)
mb move <x> <y>
Hover at coordinates
mb drag <x1> <y1> <x2> <y2>
Drag between points
mb scroll [dir] [px]
Scroll (default: down 500)
Recording
Command
Description
mb record start <file>
Start recording (.webm, .mp4, .gif)
mb record stop
Stop recording and save
mb record status
Check if recording is active
Tabs
Command
Description
mb tab list
List open tabs
mb tab new [url]
Open new tab, print index
mb tab close [n]
Close tab (default: last)
Other
Command
Description
mb js <code>
Run JavaScript in page context
mb wait <target>
Wait for ms / selector / networkidle / url:pattern
The standard agent loop: snapshot the page, pick an element, act on it.
mb snap # list interactive elements with (x, y)mb click 512 380 # click the button at those coordinatesmb wait networkidle # wait for the page to settlemb snap # observe again
Fill and submit a form
mb go "https://example.com/login"mb fill "Email=user@example.com" "Password=hunter2"mb key Entermb wait url:/dashboard
mb wait 2000 # sleep 2 secondsmb wait ".modal" # wait for selector to appearmb wait networkidle # wait for no network activitymb wait url:/dashboard # wait for URL to contain string
Important Notes
Viewport is 1024×768.snap only returns elements in the current viewport — scroll and snap again to find more.
text uses querySelector — returns first match only. Use text "main" over text "p" for better results.
go waits for networkidle. For heavy SPAs, follow up with wait ".selector".
type with coordinates triple-clicks first to select existing text, then types the replacement.
fill field matching order: aria-label → placeholder → name attr → id → label text → CSS selector (use #/./[ prefix).
--json output:snap → [{role, name, x, y, state}], tab list → [{index, url, title}], logs → JSON lines, audit → full audit object.
Recording state is stored in ~/.mb-recorder.json. Only one recording at a time.
tab close cannot close the last remaining tab.
Troubleshooting
Problem
Fix
"Chrome not found"
Set CHROME_BIN=/path/to/chrome
Connection refused
Run mb-start-chrome first
Stale recording state
Delete ~/.mb-recorder.json
Chrome window wrong size
mb-restart-chrome (creates fresh profile)
Element not in snap output
mb scroll down 500 then mb snap again
Installed into a catalogue, chosen by a router
Install mini-browser and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
runablehq-mini-browser-skill.ocm.jsonjson
{
"ocm": "1",
"id": "runablehq-mini-browser-skill",
"kind": "skill",
"name": "mini-browser",
"description": "Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: \"browse\", \"open a page\", \"take a screenshot\", \"scrape\", \"fill form\", \"click button\", \"web automation\", \"record screen\", \"design audit\", \"accessibility check\".",
"publisher": "runablehq",
"version": "1.0.0",
"capabilities": {
"domains": [
"math"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: \"browse\", \"open a page\", \"take a screenshot\", \"scrape\", \"fill form\", \"click button\", \"web automation\", \"record screen\", \"design audit\", \"accessibility check\"."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/runablehq/mini-browser",
"path": "skill/SKILL.md",
"ref": "HEAD",
"url": "https://www.skills.sh/runablehq/mini-browser/mini-browser",
"key": "runablehq/mini-browser/skill/SKILL.md"
}
},
"instructions": "# mini-browser (mb) — Browser CLI for Agents\n\n`mb` is a browser CLI where each command is a small Unix tool. It talks to Chrome over CDP (port 9222) via puppeteer-core.\n\n## Setup (only if not already available)\n\nSetup is only needed when `mb` is not installed or Chrome is not reachable.\nRun these checks first — if both pass, skip straight to the Command Reference.\n\n### Check if ready\n\n```bash\n# 1. Is mb installed?\nwhich mb && echo \"mb: ok\" || echo \"mb: MISSING\"\n\n# 2. Is Chrome listening on CDP?\ncurl -sf http://127.0.0.1:9222/json/version > /dev/null && echo \"chrome: ok\" || echo \"chrome: NOT RUNNING\"\n```\n\nIf **both** print \"ok\", everything is ready — go use `mb` commands directly.\n\n### Install (only if `mb` is missing)\n\n```bash\nnpm install -g @runablehq/mini-browser\n```\n\n### Start Chrome (only if not running)\n\n```bash\nmb-start-chrome\n```\n\nThis launches Chrome with `--remote-debugging-port=9222`, a fresh profile, and a\n1024×768 window. It no-ops if Chrome is already running.\n\nTo kill and relaunch:\n\n```bash\nmb-restart-chrome\n```\n\n### Verify\n\n```bash\nmb go \"https://example.com\" && mb text\n```\n\n### Environment Variables\n\n| Variable | Default | Description |\n|---|---|---|\n| `CHROME_PORT` | `9222` | CDP port |\n| `CHROME_BIN` | auto-detected | Path to Chrome/Chromium binary |\n| `CHROME_PID_FILE` | `<scripts>/.chrome-pid` | PID file location |\n| `CHROME_USER_DATA_DIR` | `<scripts>/.chrome-profile` | Chrome profile directory |\n\n## Command Reference\n\n### Navigation\n\n| Command | Description |\n|---|---|\n| `mb go <url>` | Navigate to URL (waits for networkidle) |\n| `mb url` | Print current URL |\n| `mb back` | Go back |\n| `mb forward` | Go forward |\n\n### Observation\n\n| Command | Description |\n|---|---|\n| `mb text [selector]` | Visible text content (default: body) |\n| `mb shot [file]` | Screenshot to PNG (default: ./shot.png) |\n| `mb snap` | List interactive elements with coordinates |\n\n### Interaction\n\n| Command | Description |\n|---|---|\n| `mb click <x> <y>` | Click at coordinates |\n| `mb type [x y] <text>` | Type text (with coords: selects first) |\n| `mb fill <k=v...>` | Fill form fields by label/name/placeholder |\n| `mb key <key...>` | Press keys (Enter, Tab, Meta+a) |\n| `mb move <x> <y>` | Hover at coordinates |\n| `mb drag <x1> <y1> <x2> <y2>` | Drag between points |\n| `mb scroll [dir] [px]` | Scroll (default: down 500) |\n\n### Recording\n\n| Command | Description |\n|---|---|\n| `mb record start <file>` | Start recording (.webm, .mp4, .gif) |\n| `mb record stop` | Stop recording and save |\n| `mb record status` | Check if recording is active |\n\n### Tabs\n\n| Command | Description |\n|---|---|\n| `mb tab list` | List open tabs |\n| `mb tab new [url]` | Open new tab, print index |\n| `mb tab close [n]` | Close tab (default: last) |\n\n### Other\n\n| Command | Description |\n|---|---|\n| `mb js <code>` | Run JavaScript in page context |\n| `mb wait <target>` | Wait for ms / selector / networkidle / url:pattern |\n| `mb audit` | Design audit (palette, typography, contrast, a11y, SEO) |\n| `mb logs` | Stream console logs (Ctrl+C to stop) |\n\n### Flags\n\n| Flag | Default | Description |\n|---|---|---|\n| `--timeout <ms>` | 30000 | Command timeout |\n| `--tab <n>` | 0 | Target tab index |\n| `--json` | false | Structured JSON output |\n| `--right` | false | Right-click |\n| `--double` | false | Double-click |\n| `--fps <n>` | 30 | Recording frame rate |\n| `--scale <n>` | 1 | Recording scale factor |\n\n## Usage Patterns\n\n### Observe → Act loop\n\nThe standard agent loop: snapshot the page, pick an element, act on it.\n\n```bash\nmb snap # list interactive elements with (x, y)\nmb click 512 380 # click the button at those coordinates\nmb wait networkidle # wait for the page to settle\nmb snap # observe again\n```\n\n### Fill and submit a form\n\n```bash\nmb go \"https://example.com/login\"\nmb fill \"Email=user@example.com\" \"Password=hunter2\"\nmb key Enter\nmb wait url:/dashboard\n```\n\n### Take a screenshot\n\n```bash\nmb shot page.png\nmb shot page.png --width 1440 --height 900\n```\n\n### Extract text\n\n```bash\nmb text \"main\" # text from <main>\nmb text \"#content\" # text from #content\nmb text # full body text\n```\n\n### Run JavaScript\n\n```bash\nmb js 'document.title'\necho 'document.querySelectorAll(\"a\").length' | mb js -\n```\n\n### Record a screencast\n\n```bash\nmb record start demo.mp4 --fps 30 --scale 1\n# ... interact with the page ...\nmb record stop\n```\n\n### Design audit\n\n```bash\nmb audit # human-readable report\nmb audit --json # structured JSON output\n```\n\n### Dismiss overlays\n\nCookie banners and modals block clicks. Remove them with JS:\n\n```bash\nmb js 'document.querySelector(\"[class*=cookie]\")?.remove()'\n```\n\n### Wait strategies\n\n```bash\nmb wait 2000 # sleep 2 seconds\nmb wait \".modal\" # wait for selector to appear\nmb wait networkidle # wait for no network activity\nmb wait url:/dashboard # wait for URL to contain string\n```\n\n## Important Notes\n\n- **Viewport is 1024×768.** `snap` only returns elements in the current viewport — scroll and snap again to find more.\n- **`text` uses querySelector** — returns first match only. Use `text \"main\"` over `text \"p\"` for better results.\n- **`go` waits for networkidle.** For heavy SPAs, follow up with `wait \".selector\"`.\n- **`type` with coordinates triple-clicks first** to select existing text, then types the replacement.\n- **`fill` field matching order:** aria-label → placeholder → name attr → id → label text → CSS selector (use `#`/`.`/`[` prefix).\n- **`--json` output:** `snap` → `[{role, name, x, y, state}]`, `tab list` → `[{index, url, title}]`, `logs` → JSON lines, `audit` → full audit object.\n- **Recording state** is stored in `~/.mb-recorder.json`. Only one recording at a time.\n- **`tab close`** cannot close the last remaining tab.\n\n## Troubleshooting\n\n| Problem | Fix |\n|---|---|\n| \"Chrome not found\" | Set `CHROME_BIN=/path/to/chrome` |\n| Connection refused | Run `mb-start-chrome` first |\n| Stale recording state | Delete `~/.mb-recorder.json` |\n| Chrome window wrong size | `mb-restart-chrome` (creates fresh profile) |\n| Element not in snap output | `mb scroll down 500` then `mb snap` again |",
"cost": {
"context_tokens": 1575
}
}
Fetch it by URL: GET /api/v1/registry/runablehq-mini-browser-skill/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.