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 agentmods add commands/ncklrs/claude-chrome-user-testing/user-testgit clone --depth 1 https://github.com/ncklrs/claude-chrome-user-testingWrote 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/commands/ncklrs/claude-chrome-user-testing/user-test)<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/user-test"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/user-test.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.05670 |
| Opus 5 | $0.00025 | $0.02835 |
| Sonnet 5 | $0.00010 | $0.01134 |
| Haiku 4.5 | $0.00005 | $0.00567 |
Grade A, and why
user-test 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 5d 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 — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Testing Command
You are initiating a persona-based user testing session. This command orchestrates realistic user simulation through Chrome browser automation.
Arguments
Parse the following from $ARGUMENTS:
--url <url>(required): Target URL to test--persona <id>(required unless --personas used): Single persona to embody--personas <ids>(optional): Comma-separated persona IDs for parallel testing (e.g., "boomer-tech-averse,genz-digital-native,impulse-buyer")--tasks <tasks>(optional): Comma-separated list of tasks to perform--gender <m|f|n>(optional): Gender variant (male/female/neutral), defaults to neutral--verbose(optional): Extra detailed narration--quiet(optional): Disable narration, show only summary report and annotated screenshots--stripe(optional): Enable Stripe checkout testing mode--card <scenario>(optional): Stripe test card scenario (default: success). Options: success, decline, insufficient, expired, 3ds-required, etc. Seeskills/stripe-checkout/test-cards.jsonfor full list.--email <email>(optional): Email address to use for forms and checkout (default: [email protected])--record(optional): Record the session as a Playwright Trace for replay--record-path <path>(optional): Custom output path for trace file (default: recordings/)--check-links(optional): Check all encountered links for broken URLs after testing--viewport <mobile|tablet|desktop>(optional): Device viewport size (default: desktop)--output <markdown|json>(optional): Report output format (default: markdown)--network <slow-3g|fast-3g|offline>(optional): Network throttling preset--pr <number>(optional): Post results as GitHub PR comment--fuzz(optional): Enable form fuzzing for security testing--fuzz-category <category>(optional): Fuzz category: xss | sqli | unicode | length | all (default: all)
Available Personas
Built-in Personas (25)
Generational:
| ID | Description |
|---|---|
boomer-tech-averse |
Cautious, reads everything, needs explicit instructions |
boomer-tech-friendly |
Experienced, prefers familiar patterns, Facebook user |
millennial-tech-skeptic |
Mobile-first, skeptical of dark patterns, values privacy |
genz-digital-native |
Fast, skips instructions, expects instant feedback |
genalpha-tablet-kid |
Touch-first, visual learner, expects gamification |
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.
- 5d ago First seen · 696 lines · 50 tokens per session scan A 6db22d829455
user-test is a command published in the GitHub repository ncklrs/claude-chrome-user-testing (19 stars, last pushed 8mo ago), licensed MIT. It adds 50 tokens to every session and 5,670 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other commands, from other repositories
ios-test
Bu komut iOS/SwiftUI uygulamasini derleyip simulator'da acarak computer use ile gorsel test yapar.
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
open
SoDam-Design-Kit open 대시보드 — 검증 이력·판정서·스크린샷을 브라우저로 열람 + 재검증.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.