Opencli Browser
Apps & Automationopencli-browserOpencli Browser is an Agent Skill for apps & automation published in the zxfccmm4/Obsidian-OpenCode-Knowledge repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/zxfccmm4/Obsidian-OpenCode-Knowledge/blob/HEAD/vault-template/.opencode/skill/opencli-browser/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/opencli-browser, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
OpenCLI Browser — Browser Automation for AI Agents
Control Chrome step-by-step via CLI. Reuses existing login sessions — no passwords needed.
Prerequisites
opencli doctor # Verify extension + daemon connectivity
Requires: Chrome running + OpenCLI Browser Bridge extension installed.
Critical Rules
- ALWAYS use
stateto inspect the page, NEVER usescreenshot—statereturns structured DOM with[N]element indices, is instant and costs zero tokens. - ALWAYS use
click/type/selectfor interaction, NEVER useevalto click or type —eval "el.click()"bypasses scrollIntoView and CDP click pipeline. - Verify inputs with
get value, not screenshots — aftertype, runget value <index>to confirm. - Run
stateafter every page change — afteropen,click(on links),scroll, always runstate. - Chain commands aggressively with
&&— combine commands to reduce overhead. evalis read-only — useevalONLY for data extraction, never for clicking, typing, or navigating.- Minimize total tool calls — plan your sequence before acting.
- Prefer
networkto discover APIs — most sites have JSON APIs. API-based adapters are more reliable than DOM scraping.
Core Workflow
- Navigate:
opencli browser open <url> - Inspect:
opencli browser state→ elements with[N]indices - Interact: use indices —
click,type,select,keys - Wait (if needed):
opencli browser wait selector ".loaded"orwait text "Success" - Verify:
opencli browser stateoropencli browser get value <N> - Repeat: browser stays open between commands
- Save: write a JS adapter to
~/.opencli/clis/<site>/<command>.js
Commands
Navigation
opencli browser open <url> # Open URL (page-changing)
opencli browser back # Go back (page-changing)
opencli browser scroll down # Scroll (up/down, --amount N)
Inspect (free & instant)
opencli browser state # Structured DOM with [N] indices — PRIMARY tool
opencli browser screenshot [path.png] # Save visual to file — ONLY for user deliverables
Get (free & instant)
opencli browser get title # Page title
opencli browser get url # Current URL
opencli browser get text <index> # Element text content
opencli browser get value <index> # Input/textarea value (use to verify after type)
opencli browser get html # Full page HTML
opencli browser get html --selector "h1" # Scoped HTML
opencli browser get attributes <index> # Element attributes
Interact
opencli browser click <index> # Click element [N]
opencli browser type <index> "text" # Type into element [N]
opencli browser select <index> "option" # Select dropdown
opencli browser keys "Enter" # Press key (Enter, Escape, Tab, Control+a)
Wait
opencli browser wait time 3 # Wait N seconds
opencli browser wait selector ".loaded" # Wait until element appears
opencli browser wait selector ".spinner" --timeout 5000 # With timeout
opencli browser wait text "Success" # Wait until text appears
Extract (free & instant, read-only)
opencli browser eval "document.title"
opencli browser eval "JSON.stringify([...document.querySelectorAll('h2')].map(e => e.textContent))"
Network (API Discovery)
opencli browser network # Show captured API requests
opencli browser network --detail 3 # Show full response body of request #3
opencli browser network --all # Include static resources
Session
opencli browser close # Close automation window
Action Chaining
Always chain when possible — fewer tool calls = faster completion:
# GOOD: open + inspect in one call
opencli browser open https://example.com && opencli browser state
# GOOD: fill form in one call
opencli browser type 3 "hello" && opencli browser type 4 "world" && opencli browser click 7
# GOOD: click + wait + state in one call
opencli browser click 12 && opencli browser wait time 1 && opencli browser state
Tips
- Always
statefirst — never guess element indices - Sessions persist — browser stays open between commands
- Use
evalfor data extraction —eval "JSON.stringify(...)"is faster than multiplegetcalls - Use
networkto find APIs — JSON APIs are more reliable than DOM scraping - Alias:
opencli opis shorthand foropencli browser
Troubleshooting
| Error | Fix |
|---|---|
| "Browser not connected" | Run opencli doctor |
| "attach failed: chrome-extension://" | Disable 1Password temporarily |
| Element not found | opencli browser scroll down && opencli browser state |
| Stale indices after page change | Run opencli browser state again |