Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add InternLM/WildClawBench --skill agent-browsergit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/agent-browser)<a href="https://agentmods.dev/skills/internlm/wildclawbench/agent-browser"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/agent-browser/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/internlm/wildclawbench/agent-browser"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/agent-browser.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 | $0.00021 | $0.01351 |
| Opus 5.5 | $0.00008 | $0.00540 |
| Sonnet 5.5 | $0.00004 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
agent-browser 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.
This is a copy
100% identical to agent-browser — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Skill
Fast browser automation using accessibility tree snapshots with refs for deterministic element selection.
Why Use This Over Built-in Browser Tool
Use agent-browser when:
- Automating multi-step workflows
- Need deterministic element selection
- Performance is critical
- Working with complex SPAs
- Need session isolation
Use built-in browser tool when:
- Need screenshots/PDFs for analysis
- Visual inspection required
- Browser extension integration needed
Core Workflow
# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json
# 2. Parse refs from JSON, then interact
agent-browser click @e2
agent-browser fill @e3 "text"
# 3. Re-snapshot after page changes
agent-browser snapshot -i --json
Key Commands
Navigation
agent-browser open <url>
agent-browser back | forward | reload | close
Snapshot (Always use -i --json)
agent-browser snapshot -i --json # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json # + compact, depth limit
agent-browser snapshot -s "#main" -i # Scope to selector
Interactions (Ref-based)
agent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8
Get Information
agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --json
Check State
agent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --json
Wait
agent-browser wait @e2 # Wait for element
agent-browser wait 1000 # Wait ms
agent-browser wait --text "Welcome" # Wait for text
agent-browser wait --url "**/dashboard" # Wait for URL
agent-browser wait --load networkidle # Wait for network
agent-browser wait --fn "window.ready === true"
What ships with it
1 file 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 First seen · 207 lines · 21 tokens per session scan A 9643b9c65476
agent-browser is a skill published in the GitHub repository InternLM/WildClawBench (533 stars, last pushed 29d ago), licensed MIT. It adds 21 tokens to every session and 1,351 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to agent-browser, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
travel-explore
You are a network explorer on a travel adventure. Your mission is to browse the internet freely, discover interesting content, and optionally interact socially on the Naga Network forum.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.
web-browse
Open a REAL external web page in Kiro Crew's Browser panel. Primary path is the browser MCP tool (native panel); playwright-cli is the fallback for remote/plain-browser sessions and attached logged-in browsers. Use when the user wants to VIEW or verify a public URL (dev server = web-preview).