SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill browser-testinggit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/browser-testing)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/browser-testing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/browser-testing/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/benchflow-ai/skillsbench/browser-testing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/browser-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01578 |
| Opus 5 | $0.00024 | $0.00789 |
| Sonnet 5 | $0.00010 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
browser-testing scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url); Copies of this mod
1 near-identical copy found in the catalogue:
- browser-testing — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Measurement with Playwright CDP
Diagnose performance issues by measuring actual load times and network activity.
Playwright is pre-installed. Just use the measurement script.
Quick Start
A measure.ts script is included in this skill's directory. Find it and run:
# Measure a page (outputs JSON with waterfall data)
npx ts-node <path-to-this-skill>/measure.ts http://localhost:3000
# Measure an API endpoint
npx ts-node <path-to-this-skill>/measure.ts http://localhost:3000/api/products
The script is in the same directory as this SKILL.md file.
Understanding the Output
The script outputs JSON with:
{
"url": "http://localhost:3000",
"totalMs": 1523,
"requests": [
{ "url": "http://localhost:3000/", "ms": 45.2 },
{ "url": "http://localhost:3000/api/products", "ms": 512.3 },
{ "url": "http://localhost:3000/api/featured", "ms": 301.1 }
],
"metrics": {
"JSHeapUsedSize": 4521984,
"LayoutCount": 12,
"ScriptDuration": 0.234
}
}
Reading the Waterfall
The requests array shows network timing. Look for sequential patterns:
BAD (sequential - each waits for previous):
/api/products |████████| 512ms
/api/featured |██████| 301ms (starts AFTER products)
/api/categories |████| 201ms (starts AFTER featured)
Total: 1014ms
GOOD (parallel - all start together):
/api/products |████████| 512ms
/api/featured |██████| 301ms (starts SAME TIME)
/api/categories |████| 201ms (starts SAME TIME)
Total: 512ms (just the slowest one)
Key Metrics
| Metric | What it means | Red flag |
|---|---|---|
totalMs |
Total page load time | > 1000ms |
JSHeapUsedSize |
Memory used by JS | Growing over time |
LayoutCount |
Layout recalculations | > 50 per page |
ScriptDuration |
Time in JS execution | > 0.5s |
What ships with it
3 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.
- 6d ago First seen · 200 lines · 49 tokens per session scan A cb1a9611c3d0
browser-testing is a skill published in the GitHub repository benchflow-ai/skillsbench (1,757 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,578 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Browser Smoke Testing
Open a local web target and verify that the main page renders and core controls respond.
web-ui-test
Test the IronClaw web UI using the Claude for Chrome browser extension.
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".