Instrucciones de origen · Vista previa de solo lectura
name
browser-harness
description
Self-healing browser automation framework that connects LLM agents directly to Chrome via CDP. Use when the user needs autonomous browser tasks, clean browser verification, Codex or Antigravity browser control, Claude-safe screenshots, adaptive helper code in `agent_helpers.py`, domain skills, or Browser Use Cloud escalation. Triggers on: browser-harness, self-healing browser, llm browser automation, cdp agent, chrome devtools agent, codex browser automation, antigravity browser automation, claude screenshot error, claude image error, agent browser task, browser-use harness, domain skills browser.
allowed-tools
Bash Read Write Edit Glob Grep WebFetch
compatibility
Requires Python 3.10+ and Chrome/Chromium with remote debugging enabled. Works from Claude Code, Codex CLI, Antigravity (`agy`), Gemini CLI, and OpenCode when the agent can edit/run the local Python workspace. Includes a Claude-safe screenshot patch for PIL file-handle and image-size issues.
Direct WebSocket connection between an LLM agent and Chrome via Chrome DevTools Protocol. The agent can inspect the page, write helper code, reuse domain skills, and verify the task without an extra browser abstraction layer.
Browser Harness is the canonical replacement for the removed agent-browser skill in this catalog. Use it for clean browser verification, autonomous browser tasks, and platform-portable CDP control across Claude Code, Codex, Antigravity, Gemini CLI, and OpenCode.
When to use this skill
The user needs an LLM agent to complete a multi-step browser workflow: login, navigation, form fill, data extraction, download, or verification.
The workflow needs a clean browser profile or repeatable CDP verification instead of the user's already-open browser state.
The user is running from Codex CLI or Antigravity and needs a local browser harness the agent can operate with shell/Python commands.
Claude reports image/screenshot/tool errors when browser screenshots are written, resized, or re-opened.
The target DOM changes and the agent should add or repair helpers in agent-workspace/agent_helpers.py.
The task benefits from site-specific domain skills in agent-workspace/domain-skills/.
Browser Use Cloud is justified for concurrent browsers, proxies, or captcha solving on allowed targets.
Do not use this skill when
The task is simple HTML extraction without browser state or JS interaction -> route to scrapling.
The task is exact human UI annotation or pointing at a rendered issue -> route to agentation.
The task must reuse the user's already-open authenticated Chrome profile -> route to playwriter.
The task is React component source capture -> route to react-grab.
The task is ordinary Playwright/Puppeteer script authoring without agent autonomy -> use that stack directly.
Instructions
Step 1: Choose the execution packet
Pick one primary packet before writing commands:
local-cdp: local Chrome/Chromium with --remote-debugging-port=9222.
codex-cdp: Codex CLI controls the same local checkout and CDP endpoint.
antigravity-cdp: Antigravity (agy) uses the same workspace and Chrome debugging endpoint.
claude-vision-safe: screenshot capture must use the safe image pipeline below.
domain-skill: add or repair a site-specific helper in agent-workspace/domain-skills/.
cloud-browser: Browser Use Cloud is needed and allowed.
Step 2: Install browser-harness
Browser Harness can be set up by an agent from any platform that can run shell commands:
If Claude throws image recognition, image upload, PNG read, or tool errors around screenshots, patch src/browser_harness/helpers.py so screenshots are decoded and resized in memory, and PIL file handles are closed before saving overlays.
Required changes:
diff --git a/src/browser_harness/helpers.py b/src/browser_harness/helpers.py--- a/src/browser_harness/helpers.py+++ b/src/browser_harness/helpers.py
@@
-import base64, importlib.util, json, math, os, sys, time, urllib.request+import base64, importlib.util, io, json, math, os, sys, time, urllib.request
@@
- img = Image.open(path)+ with Image.open(path) as src:+ img = src.copy()
@@
- open(path, "wb").write(base64.b64decode(r["data"]))+ data = base64.b64decode(r["data"])
if max_dim:
from PIL import Image
- img = Image.open(path)+ img = Image.open(io.BytesIO(data))
if max(img.size) > max_dim:
img.thumbnail((max_dim, max_dim))
- img.save(path)+ buf = io.BytesIO()+ img.save(buf, format="PNG")+ data = buf.getvalue()+ with open(path, "wb") as f:+ f.write(data)
Why this matters:
Image.open(path) keeps a lazy file handle unless copied or closed.
Claude image/tool pipelines are more likely to fail when a PNG is opened, rewritten, then reopened by the agent in quick succession.
In-memory resize via io.BytesIO avoids the write-read-write cycle.
Writing once with with open(path, "wb") produces a stable file for Claude vision upload.
Recommended screenshot call for Claude:
path = capture_screenshot(max_dim=1800)
Use max_dim=1800 on high-DPI displays to stay under common 2000px-per-side image limits.
Step 6: Run browser tasks
Give the agent a natural-language task:
Open the local app, complete the signup form, and verify that the dashboard appears.
Navigate to GitHub, open the first open issue, and summarize the acceptance criteria.
Fill in the contact form at example.com and confirm the success message.
The agent should:
Connect to Chrome via CDP.
Inspect tabs and page state.
Reuse existing helpers in agent-workspace/agent_helpers.py.
Add missing helpers in agent-workspace/agent_helpers.py or agent-workspace/domain-skills/.
Verify completion with text, URL, DOM state, screenshot, or downloaded artifact evidence.
Step 7: Extend with domain skills
Domain skills are site-specific playbooks. Keep them small and reusable:
Use Browser Use Cloud only when local Chrome is insufficient and the target permits automation:
from browser_harness import BrowserUseCloud
client = BrowserUseCloud(api_key="YOUR_API_KEY")
result = client.run("Extract the dashboard data and return a CSV summary")
print(result)
Best practices
Start with local-cdp; escalate only when the local CDP endpoint cannot satisfy the job.
Keep core package edits minimal. Put ordinary workflow logic in agent_helpers.py or domain skills.
Apply the Claude-safe screenshot patch before image-heavy Claude Code runs.
For Codex and Antigravity, prefer explicit shell/Python commands over Claude-only plugin instructions.
Treat every browser task as incomplete until the agent records final evidence.
Use scrapling for stateless scraping and playwriter for already-open authenticated browser reuse.
Do not bypass site terms, robots, rate limits, or authorization boundaries.
