Borrowing it
Nothing to install: this file belongs to dundas/thinkrun. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dundas/thinkrun/main/.claude/skills/web-browse/SKILL.mdgit clone --depth 1 https://github.com/dundas/thinkrunWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dundas/thinkrun/web-browse)<a href="https://agentmods.dev/skills/dundas/thinkrun/web-browse"><img src="https://agentmods.dev/badge/skills/dundas/thinkrun/web-browse/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dundas/thinkrun/web-browse"><img src="https://agentmods.dev/badge/skills/dundas/thinkrun/web-browse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.01205 |
| Opus 5.5 | $0.00042 | $0.00482 |
| Sonnet 5.5 | $0.00021 | $0.00241 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
web-browse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browse
Drive a browser programmatically with ThinkRun. Two interfaces, same capabilities:
thinkrunCLI — for shell scripts and terminal use.npm install -g @thinkrun/cli(bin:thinkrun).@thinkrun/mcp— for MCP clients (Claude Code, Cursor, Cline, Windsurf).npx @thinkrun/mcp.
Both support two execution modes:
- Local mode — controls your real Chrome via the ThinkRun extension + native host. Best for sites needing your login/cookies, or visual work on the browser you already have open.
- Cloud mode — provisions an isolated Playwright browser on Fly.io. Best for headless/autonomous scraping, multi-agent work, and anti-detection (stealth).
Mode is auto-detected; override per-command with --mode local|cloud (CLI) or the set_mode tool (MCP).
When to use which
| Scenario | Mode | Why |
|---|---|---|
| Site needs your login cookies | Local | Uses your real Chrome session |
| Visual/interactive work on an open tab | Local | Attach to the tab you're looking at |
| Headless autonomous scraping | Cloud | No Chrome needed, runs detached |
| Multi-agent / parallel sessions | Cloud | Isolated browser per session |
| Anti-detection needed | Cloud | Built-in stealth (no navigator.webdriver) |
See references/details.md for the full CLI command + MCP tool reference, common patterns, and error codes.
Setup
Install
# CLI (shell use)
npm install -g @thinkrun/cli # provides the `thinkrun` command
# MCP (Claude Code / Cursor / Cline / Windsurf)
npx @thinkrun/mcp # or add to your MCP config (see below)
MCP config:
{ "mcpServers": { "thinkrun": { "command": "npx", "args": ["@thinkrun/mcp"] } } }
Cloud mode
Set an API key (get one at thinkrun.ai):
thinkrun config set-key <api-key> # or: export THINKRUN_API_KEY=<api-key>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +9 tokens per session d3f8b1d5c9f4
- 2mo ago First seen · 125 lines · 96 tokens per session scan A 4802e1b0d050
web-browse is a skill published in the GitHub repository dundas/thinkrun (2 stars, last pushed 18d ago), licensed MIT. It adds 105 tokens to every session and 1,205 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Console Error Hunter
Systematically detect, capture, and categorize browser console errors, warnings, and unhandled exceptions during automated test execution.
Dead Link Detector
Automated detection and reporting of broken links, missing resources, and orphaned pages across web applications using crawl-based and DOM-based strategies.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
Geb Testing
Browser automation testing with Geb framework for Groovy/JVM using jQuery-like content DSL, Page Object pattern, Spock integration, and WebDriver abstraction.
Karma Testing
Comprehensive Karma test runner skill for browser-based JavaScript unit testing with Jasmine, Mocha, or QUnit frameworks, real browser execution, coverage reporting, and CI/CD pipeline integration.
playwright-e2e
Comprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors, assertions, waits, fixtures, and test organization.