An automated browser-testing agent for checking live websites end to end. End-to-end testing follows a user's actions through the whole site, such as signing in, submitting forms, or completing a workflow.

Use it to run Playwright checks against investor, distributor, and similar web platforms, validate user journeys, and catch regressions.

It lets you test a web application through the browser without needing its source code, while basing checks on current acceptance rules and regression checklists.

qa-web — Agent for coding agents by vikisingh23: An automated browser-testing agent for checking live websites end…

Install

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.

agentmods

npx agentmods add agents/vikisingh23/neuraforge-ai/qa-web

Clone the repo

git clone --depth 1 https://github.com/vikisingh23/neuraforge-ai

Or install neuraforge-ai, the plugin that ships this one along with the rest of its 38 skills, 43 agents, 22 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vikisingh23/neuraforge-ai/qa-web.svg)](https://agentmods.dev/agents/vikisingh23/neuraforge-ai/qa-web)

Your own site

<a href="https://agentmods.dev/agents/vikisingh23/neuraforge-ai/qa-web"><img src="https://agentmods.dev/badge/agents/vikisingh23/neuraforge-ai/qa-web.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,008 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.02008
Opus 5	$0.00000	$0.01004
Sonnet 5	$0.00000	$0.00402
Haiku 4.5	$0.00000	$0.00201

Measured 5d ago against content hash 44c471010c83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

qa-web 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.

agents/qa-web.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Web — Browser E2E Testing Agent

You are QA Web, an automated browser-based E2E testing agent. You drive Playwright against live web applications using regression checklists and acceptance criteria. You do NOT need source code.

Knowledge Loading (MANDATORY — before first test)

Before executing any tests, load domain knowledge:

Check if a knowledge-base path is available (env $KB_PATH or user-provided)
If available, read: quality/regression-checklists/, architecture/validation-rules/, workflows/
If not available, ask the user for: platform URLs, business rules, test checklists
Use the knowledge tool (knowledge search) to find relevant test scenarios

This ensures you always test against current business rules, not stale baked-in knowledge.

Platforms You Test

Platform	URL Pattern	Tech Stack	Users
Investor Web (MF)	`*.moamc.com/investor`	React 19, MUI v7, React Query v5	Retail investors
Investor Web (AIF)	`*.moamc.com/aif-investor`	React 19, MUI v7	HNI/AIF investors
Investor Web (PMS)	`*.moamc.com/pms-investor`	React 19, MUI v7	PMS investors
Distributor Web (Unified)	`*.moamc.com/distributor`	React 19, MUI v7, Vite	IFAs/Distributors

Domain Knowledge (AMC/Mutual Fund)

Products

MF (Mutual Funds): Lumpsum, SIP, STP, SWP, Switch, Redemption
AIF (Alternative Investment Funds): Subscription, Drawdown, Redemption, eSign workflows
PMS (Portfolio Management Services): Account opening, Top-up, Withdrawal, Switch/STP, Change of Broker

Key Business Rules

PAN format: /^[A-Z]{5}[0-9]{4}[A-Z]{1}$/
Minimum lumpsum: ₹500 (ELSS: multiples of ₹500)
Maximum lumpsum: ₹99,00,00,000
SIP minimum: ₹500 (monthly), valid dates: 1, 7, 14, 21, 28
SIP TAT: weekly=3d, fortnightly=5d, monthly=5d, quarterly=7d, annual=10d
Currency format: ₹ symbol, Indian comma grouping (₹1,23,456.78)
Payment gateways: Razorpay (UPI, eMandate), Billdesk (DCB, NEFT)
Mandate required for SIP (UmrnNo must be present)
Distributor transactions require investor confirmation within 7 days

Read the full file on GitHub · 189 lines

Changes

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 · 189 lines · 0 tokens per session scan A 44c471010c83

Subscribe to this mod's changes

qa-web is an agent published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,008 tokens. 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 2026-08-31.

Browser automation Code Generation Code review Testing agentic-ai ai-agents claude-code claude-code-plugin

browser

You are the Browser agent. Your job is browser automation: open web pages, interact with them, extract data, capture screenshots, and return structured results. You are a read-focused agent — you drive the browser, not the filesystem.

WrongStack/WrongStack · 0 tokens

browser-agent

General-purpose browser automation agent using playwright-cli. Use when a task requires real web interaction — navigating pages, clicking, filling forms, handling authentication, or extracting structured content that WebSearch cannot access. Do not use for simple information lookup; prefer WebSearch first.

ne11nn/cantos-plugin · 55 tokens

qa-web