Skip to main content
ClaudeWave
Skill125 estrellas del repoactualizado today

using-webctl

Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/oaustegard/claude-skills /tmp/using-webctl && cp -r /tmp/using-webctl/using-webctl ~/.claude/skills/using-webctl
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Using webctl in Claude.ai Containers

Browser automation using webctl CLI with automatic proxy authentication handling for Claude.ai's egress-controlled environment.

## When This Skill Applies

- User requests browser automation, web scraping, or page interaction
- webctl commands fail with `ERR_TUNNEL_CONNECTION_FAILED`
- Playwright/Chromium needs to work through authenticated HTTP proxy

## Core Problem

Claude.ai containers route traffic through an authenticated egress proxy (`HTTP_PROXY` env var with JWT credentials). Chromium doesn't properly handle proxy authentication for HTTPS CONNECT tunnels, causing all HTTPS navigation to fail even though curl works.

## Solution

A local forwarding proxy (port 18080) intercepts Chromium connections and injects `Proxy-Authorization` headers before forwarding to the real egress proxy.

## Setup Procedure

### 1. Install webctl

```bash
pip install webctl --break-system-packages
webctl setup  # Downloads Chromium if needed
```

### 2. Deploy Auth Proxy Module

Copy `scripts/auth_proxy.py` to webctl's daemon directory:

```bash
cp /mnt/skills/user/using-webctl/scripts/auth_proxy.py \
   /usr/local/lib/python3.12/dist-packages/webctl/daemon/
```

### 3. Patch Session Manager

Apply this patch to `/usr/local/lib/python3.12/dist-packages/webctl/daemon/session_manager.py`.

Recent webctl versions split context creation into two branches (mobile emulation vs desktop). Both must receive the proxy config. Find the block (search for `cfg = WebctlConfig.load()` followed by the `if mode == "unattended" and cfg.mobile_emulation:` branch — around line 190):

```python
cfg = WebctlConfig.load()
if mode == "unattended" and cfg.mobile_emulation:
    # Mobile emulation: cleaner pages, fewer ads, simpler layouts
    device = self._playwright.devices["Pixel 7"]
    context = await browser.new_context(
        storage_state=storage_state,
        **device,
    )
else:
    context = await browser.new_context(
        storage_state=storage_state, viewport={"width": 1280, "height": 720}
    )
```

Replace with:
```python
cfg = WebctlConfig.load()
from .auth_proxy import get_local_proxy_url
proxy_url = get_local_proxy_url()
proxy_config = {"server": proxy_url} if proxy_url else None
if mode == "unattended" and cfg.mobile_emulation:
    # Mobile emulation: cleaner pages, fewer ads, simpler layouts
    device = self._playwright.devices["Pixel 7"]
    context = await browser.new_context(
        storage_state=storage_state,
        proxy=proxy_config,
        **device,
    )
else:
    context = await browser.new_context(
        storage_state=storage_state, viewport={"width": 1280, "height": 720},
        proxy=proxy_config
    )
```

If the file only has a single `new_context` call (older webctl), inject `proxy=proxy_config` into that one and place the three `proxy_url` lines just above it.

### 4. Verify

```bash
webctl start --mode unattended
webctl --quiet navigate "https://github.com"
webctl snapshot --interactive-only --limit 10
webctl stop
```

## Quick Reference

### Session Management
```bash
webctl start --mode unattended    # Headless browser
webctl stop                       # Full shutdown (use --keep-daemon to leave daemon running)
webctl status                     # Current state + console error counts
```

### Navigation
```bash
webctl navigate "https://..."
webctl back / webctl forward / webctl reload
```

### Observation
```bash
webctl snapshot --interactive-only --limit 30   # Buttons, links, inputs
webctl snapshot --within "role=main"            # Scope to container
webctl query "role=button name~=Submit"         # Debug queries
webctl screenshot --path shot.png
```

### Interaction
```bash
webctl click 'role=button name~="Submit"'
webctl type 'role=textbox name~="Email"' "user@example.com"
webctl type 'role=textbox name~="Search"' "query" --submit
webctl select 'role=combobox name~="Country"' --label "Germany"
```

### Query Syntax
- `role=button` — By ARIA role
- `name~="partial"` — Contains (preferred, more robust)
- `name="exact"` — Exact match
- `nth=0` — Select first when multiple matches

### Wait Conditions
```bash
webctl wait network-idle
webctl wait 'exists:role=button name~="Continue"'
webctl wait 'url-contains:"/dashboard"'
```

## Troubleshooting

### ERR_TUNNEL_CONNECTION_FAILED
Auth proxy not loaded. Verify:
1. `auth_proxy.py` exists in webctl daemon directory
2. Session manager is patched
3. Restart daemon: `webctl stop && webctl start --mode unattended`

### Multiple matches error
Add specificity or use `nth=0`:
```bash
webctl click 'role=link name="Sign in" nth=0'
```

### Verify proxy is running
```bash
netstat -tlnp | grep 18080
```

## Limitations

- Patch is session-local (container resets clear it)
- Only allowed domains in network config are accessible
- No Firefox support (download blocked by egress policy)

## Domain Restrictions

Check `<network_configuration>` in system prompt for allowed domains. Common allowed: `*.github.com`, `*.bsky.app`, allowed API endpoints.

## Output Filtering

Reduce context consumption:
```bash
webctl snapshot --interactive-only --limit 30    # Cap elements
webctl snapshot | grep -i "submit"               # Unix filtering
webctl --quiet navigate "..."                    # Suppress events
```
accessing-github-reposSkill

GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.

api-credentialsSkill

Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need to access stored API keys for external service invocations.

asking-questionsSkill

Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical decisions. Use when implementation choices exist that could significantly affect outcomes.

assessing-impactSkill

>-

bm25Skill

>-

browsing-blueskySkill

Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for personalized feeds. Use for Bluesky research, user monitoring, trend analysis, feed reading, firehose sampling, account categorization.

building-github-indexSkill

Generate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when user mentions "index", "github repo", "project knowledge", or "documentation reference".

categorizing-bsky-accountsSkill

Analyze and categorize Bluesky accounts by topic using keyword extraction. Use when users mention Bluesky account analysis, following/follower lists, topic discovery, account curation, or network analysis.