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/alphaaiservice/cortex/e2e-testgit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00046 | $0.12355 |
| Opus 5 | $0.00023 | $0.06177 |
| Sonnet 5 | $0.00009 | $0.02471 |
| Haiku 4.5 | $0.00005 | $0.01235 |
Grade A, and why
e2e-test 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 yesterday.
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(baseURL, { method: 'HEAD' }); How it starts
The opening of the file, as written. The whole thing — 1,586 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-End Test Generation
Generate comprehensive end-to-end tests for: $ARGUMENTS
Parse $ARGUMENTS for:
- A specific flow name (e.g.,
auth,payment,crud,search,settings,admin,profile,responsive) --allflag: generate E2E tests for every discovered user flow--visualflag: include visual regression testing with baseline screenshots- If no arguments provided, default to
--all
Step 1: Analyze Application Flows
1.1 Detect Project Type and Structure
# Detect if this is a web project (Next.js / React)
ls -la package.json 2>/dev/null
ls -la next.config.* 2>/dev/null
ls -la app/ 2>/dev/null
ls -la src/app/ 2>/dev/null
ls -la pages/ 2>/dev/null
# Detect if this is a mobile project (React Native / Expo)
ls -la app.json 2>/dev/null
ls -la expo-env.d.ts 2>/dev/null
ls -la metro.config.* 2>/dev/null
ls -la android/ 2>/dev/null
ls -la ios/ 2>/dev/null
1.2 Scan Web Routes (Next.js App Router)
Use Glob to find all route files:
**/app/**/page.tsx— Next.js 13+ App Router pages**/app/**/page.jsx— JSX variant**/pages/**/*.tsx— Pages Router (legacy)**/pages/**/*.jsx— JSX variant
For each discovered page file:
- Read the file to understand the component
- Extract the route path from the file system path (e.g.,
app/dashboard/settings/page.tsxmaps to/dashboard/settings) - Identify dynamic route segments (e.g.,
[id],[slug],[...catchAll]) - Detect route groups
(group-name)and exclude them from the URL path - Identify layout files (
layout.tsx) that wrap multiple routes - Detect loading states (
loading.tsx) and error boundaries (error.tsx) - Detect middleware files (
middleware.ts) that may redirect or protect routes - Identify parallel routes and intercepting routes if present
1.3 Scan React Native Screens (if mobile project exists)
Use Glob to find all screen files:
**/screens/**/*.tsx**/screens/**/*.jsx**/app/**/_layout.tsx(Expo Router)**/app/**/index.tsx(Expo Router)
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.
- yesterday First seen · 1,586 lines · 46 tokens per session scan A d8ace8531450
e2e-test is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 46 tokens to every session and 12,355 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 2026-08-31.
Other commands, from other repositories
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).
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.