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/critical-pathgit 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/critical-path)<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/critical-path"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/critical-path.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 5.1 | $0.00026 | $0.02013 |
| Opus 5 | $0.00013 | $0.01007 |
| Sonnet 5 | $0.00005 | $0.00403 |
| Haiku 4.5 | $0.00003 | $0.00201 |
Grade A, and why
critical-path 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 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.
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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical Path Command
Test must-work user journeys. Critical paths are essential flows that must always work - if they fail, users can't accomplish core tasks.
Arguments
Parse the following from $ARGUMENTS:
--url <url>(required): Base URL for testing--path <name>(optional): Run specific path only (default: all paths)--persona <id>(optional): Override default persona for all paths--quiet(optional): Summary only output--fail-fast(optional): Stop on first failure--record(optional): Record sessions as Playwright Traces--record-path <path>(optional): Custom trace output path--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
Defining Critical Paths
Create .claude/critical-paths.json in your project:
{
"paths": [
{
"name": "purchase-flow",
"description": "Complete purchase from browse to confirmation",
"persona": "impulse-buyer",
"priority": "critical",
"steps": [
{ "action": "navigate", "to": "/" },
{ "action": "task", "do": "find and select a product" },
{ "action": "task", "do": "add to cart" },
{ "action": "task", "do": "proceed to checkout" },
{ "action": "task", "do": "complete guest checkout" },
{ "action": "verify", "element": "order confirmation number" }
]
},
{
"name": "account-creation",
"description": "New user registration flow",
"persona": "genz-digital-native",
"priority": "critical",
"steps": [
{ "action": "navigate", "to": "/signup" },
{ "action": "task", "do": "complete signup form" },
{ "action": "task", "do": "submit registration" },
{ "action": "verify", "element": "welcome message or dashboard" }
]
},
{
"name": "password-reset",
"description": "Password recovery flow",
"persona": "boomer-tech-averse",
"priority": "high",
"steps": [
{ "action": "navigate", "to": "/login" },
{ "action": "task", "do": "find forgot password link" },
{ "action": "task", "do": "enter email address" },
{ "action": "task", "do": "submit reset request" },
{ "action": "verify", "element": "confirmation message" }
]
}
]
}
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 · 304 lines · 26 tokens per session scan A 20ec995e7ac5
critical-path is a command published in the GitHub repository ncklrs/claude-chrome-user-testing (19 stars, last pushed 8mo ago), licensed MIT. It adds 26 tokens to every session and 2,013 once invoked, about $0.0001 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.
paul:verify
Guide manual user acceptance testing of recently built features.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
verify-pr
Verify a PR's frontend changes through browser automation.
harness-eval
执行 Harness 四级任务验证,覆盖编译、契约、E2E 与 Constitution 审查。.