Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Hosted Browser Automation For Agents

ASecurity

Hosted browser automation API for agents. Screenshots, Playwright scripts, workflows — no local Chrome needed.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsrustgobashgitapisecurity

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill hosted-browser-automation-for-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hosted Browser Automation For Agents?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Hosted Browser Automation For Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-hosted-browser-automation-for-agents/badge)](https://www.skillsdirectory.com/skills/rondoflow-hosted-browser-automation-for-agents)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: hosted-browser-automation-for-agents
description: "Hosted browser automation API for agents. Screenshots, Playwright scripts, workflows — no local Chrome needed."
category: "AI & Agents"
author: community
version: "1.0.0"
icon: bot
---

# Riddle — Hosted Browser for AI Agents

Riddle gives your agent a browser without running Chrome locally. One API call: navigate, click, fill forms, take screenshots, capture network traffic. All execution happens on Riddle's servers — your agent stays lean.

> **Quick Start:** Sign up at [riddledc.com/register](https://riddledc.com/register) and get 5 minutes of free browser time — no credit card needed. After that, pricing is **$0.50/hour, billed per second**. A single screenshot costs roughly **$0.004**.

## Why Use This Instead of Local Chrome

- **No Chromium binary** — saves ~1.2 GB RAM and avoids the Lambda/container size headaches
- **No dependency hell** — no `@sparticuz/chromium`, no Puppeteer version conflicts, no `ENOENT` / `spawn` failures
- **Full Playwright** — not just screenshots. Run real Playwright scripts, multi-step workflows, form fills, authenticated sessions
- **Works everywhere** — Lambda, containers, T3 Micro instances, anywhere your agent runs

## Install

**Step 1: Sign up** — Create a free account at [riddledc.com/register](https://riddledc.com/register). No credit card required. You get 5 minutes of browser time free.

**Step 2: Get your API key** — After signing up, grab your API key from the [dashboard](https://riddledc.com/dashboard).

**Step 3: Install and configure the plugin:**

```bash
# Install the plugin
openclaw plugins install @riddledc/openclaw-riddledc

# Allow the tools
openclaw config set tools.alsoAllow --json '["openclaw-riddledc"]'

# Set your API key
openclaw config set plugins.entries.openclaw-riddledc.config.apiKey "YOUR_RIDDLE_API_KEY"
```

**One gotcha:** OpenClaw requires plugins in the `plugins.allow` list. The CLI doesn't have an append flag, so check your current list and add `openclaw-riddledc`:

```bash
# See what you have
openclaw config get plugins.allow

# Add openclaw-riddledc to the array (or edit ~/.openclaw/openclaw.json directly)
jq '.plugins.allow += ["openclaw-riddledc"]' ~/.openclaw/openclaw.json > tmp && mv tmp ~/.openclaw/openclaw.json

# Restart
openclaw gateway restart
```

## Tools

After install, you have five tools:

**`riddle_screenshot`** — Screenshot a URL. Simplest use case.
```
Take a screenshot of https://example.com
```

**`riddle_screenshots`** — Batch screenshots of multiple URLs in one job.
```
Screenshot these three pages: https://example.com, https://example.com/about, https://example.com/pricing
```

**`riddle_steps`** — Run a step-by-step workflow (goto, click, fill, screenshot at each step).
```
Go to https://example.com/login, fill the email field with "test@example.com", fill the password field, click the submit button, then screenshot the result.
```

**`riddle_script`** — Run full Playwright code for complex automation.
```
Run a Playwright script that navigates to https://example.com, waits for the dashboard to load, extracts all table rows, and screenshots the page.
```

**`riddle_run`** — Low-level API pass-through for custom payloads.

All tools return screenshots saved to `~/.openclaw/workspace/riddle/screenshots/` (not inline base64) with file paths in the response. Add `include: ["har"]` to also capture full network traffic.

## Authenticated Sessions

Need to interact with a page behind login? Pass cookies, localStorage, or custom headers:

```
Screenshot https://app.example.com/dashboard with these cookies: [session=abc123]
```

The plugin supports cookies, localStorage entries, and custom HTTP headers as auth parameters.

## Trust & Security

This plugin was built with the concerns raised by the Moltbook agent community in mind — specifically the discussion around skill provenance, capability manifests, and runtime boundaries.

**What this plugin declares (capability manifest in `openclaw.plugin.json`):**
- **Network**: Only talks to `api.riddledc.com` — hardcoded allowlist enforced at runtime, not just config time
- **Filesystem**: Only writes to `~/.openclaw/workspace/riddle/`
- **Agent context**: Zero access to conversation history, other tools' outputs, or user profile
- **Secrets**: Only requires `RIDDLE_API_KEY`, which is only sent to the declared endpoint

**What this means in practice:**
- Even if the config is manipulated, your API key cannot be sent to any non-Riddle domain (hardcoded check runs on every request)
- The plugin cannot read your conversations, memory, or other plugins' data
- Screenshots are saved as file references, not inline base64 — prevents context overflow and accidental data leakage in logs

**Verify it yourself:**
- Source: [github.com/riddledc/integrations](https://github.com/riddledc/integrations)
- npm provenance: `npm audit signatures @riddledc/openclaw-riddledc`
- Checksums: `CHECKSUMS.txt` in the package
- Full threat model: `SECURITY.md` in the package

This is a **plugin** (auditable code), not a skill (prompt text). You can read every line before installing.

## Pricing

Riddle uses transparent per-execution pricing. A simple screenshot costs fractions of a cent. See [riddledc.com](https://riddledc.com) for current pricing.

## Get Help

- Docs: [riddledc.com](https://riddledc.com)
- Security issues: security@riddledc.com
- Plugin source: [github.com/riddledc/integrations](https://github.com/riddledc/integrations)

## Links

- **Website:** [riddledc.com](https://riddledc.com)
- **Docs:** [riddledc.com/docs](https://riddledc.com/docs)
- **Pricing:** [riddledc.com/pricing](https://riddledc.com/pricing)
- **Dashboard:** [riddledc.com/dashboard](https://riddledc.com/dashboard)

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →