claude-worker

Claude Worker

Send a prompt to Claude.ai via browser and return the response.

Environment

• URL: https://claude.ai
• Browser: Chrome on localhost:9222 (managed by local-browser-tools)
• Login: Required — session persisted in ~/.cache/browser-tools profile
• Tools: browser-start.js, browser-nav.js, browser-eval.js, browser-screenshot.js

---

Input

prompt: string        # The text to send to Claude
task_type: string     # qa | summary | translation | rewrite | extraction | comparison | brainstorming | analysis

---

Output

Always output this JSON block first:

{
  "site": "claude",
  "task_type": "<task_type>",
  "status": "success | partial | error",
  "answer": "<extracted response text>",
  "retry_count": 0,
  "elapsed_ms": 0,
  "error_reason": null
}

Then follow with a short human-readable summary (2–3 sentences max).

---

Workflow

Step 1 — Start browser

node ~/.pi/agent/skills/local-browser-tools/browser-start.js

Expected: ✓ Chrome already running on :9222 or ✓ Chrome started on :9222

If fails: return error status, stop.

---

Step 2 — Navigate to Claude

node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://claude.ai

Take a screenshot and verify:

• Input box is visible
• Page title contains "Claude"
• Not showing a login wall

If login page appears with no input box: return error_reason: "login_required", stop.

---

Step 3 — Locate input box

Claude uses a div[contenteditable] with role="textbox" and aria-label="Write your prompt to Claude".

Check:

!!document.querySelector('[aria-label="Write your prompt to Claude"]')

Fallback selectors in order:

1. [aria-label="Write your prompt to Claude"]
2. [contenteditable="true"][role="textbox"]
3. div[contenteditable]

If no selector works after 3 attempts: trigger retry.

---

Step 4 — Insert prompt

Claude uses a contenteditable div. Use execCommand to insert text — do NOT set textContent directly as it bypasses the editor state: