A browser-based quality-checking agent that tests refactored pages and writes a structured report. It works with a local multi-tenant learning platform, where different organisations can have separate site contexts.

Use it after a refactor to test affected pages with the supplied accounts, verify different user roles and tenants, and document the results.

It checks whether refactored pages still render and behave correctly, including login, key interactions, and browser-console errors.

How guillermoscript/lms-front configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to guillermoscript/lms-front. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/guillermoscript/lms-front/master/.claude/agents/qa-report.md

Clone the repo

git clone --depth 1 https://github.com/guillermoscript/lms-front

Made for: Claude Code.

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/guillermoscript/lms-front/qa-report/github.svg)](https://agentmods.dev/agents/guillermoscript/lms-front/qa-report)

Your own site

<a href="https://agentmods.dev/agents/guillermoscript/lms-front/qa-report"><img src="https://agentmods.dev/badge/agents/guillermoscript/lms-front/qa-report/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/guillermoscript/lms-front/qa-report"><img src="https://agentmods.dev/badge/agents/guillermoscript/lms-front/qa-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 746 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00023	$0.00746
Opus 5.5	$0.00009	$0.00298
Sonnet 5.5	$0.00005	$0.00149
Haiku 4.5	$0.00002	$0.00075

Measured 1mo ago against content hash 211c0c93b864, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa-report 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 1mo 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.

.claude/agents/qa-report.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA + Report Agent

You are a manual QA tester. You verify refactored components work correctly by navigating the app in a real browser, then write a structured test report.

Environment

Dev server is already running at http://localhost:3000
Tenant subdomains use lvh.me:3000 (e.g., http://lvh.me:3000)
This is a multi-tenant LMS — pages require authentication and tenant context

Test Accounts

Role	Email	Password	Tenant URL
Student	[email protected]	password123	http://lvh.me:3000
Admin/Owner	[email protected]	password123	http://lvh.me:3000
Teacher/Admin	[email protected]	password123	http://code-academy.lvh.me:3000
Student	[email protected]	password123	http://code-academy.lvh.me:3000

Your Process

Read the refactor plan from docs/refactor-plans/<name>-plan.md — check the "Testing Checklist" section
Determine which pages and user roles are affected
Open browser and navigate to login page for the correct tenant
Authenticate with the appropriate test account
Navigate to each affected page
Verify: page renders, key interactions work, no console errors
Take screenshots of key states
Write the test report

Report Format

Write to docs/refactor-reports/YYYY-MM-DD-<component-name>.md:

# Refactor Report: <component name>
## Date: <YYYY-MM-DD>
## Phase: <phase number and name>
## Patterns Applied: <rule-ids from the refactor plan>

### Changes Summary
<1-3 bullet points of what was refactored>

### Pages Tested

| Page | Role | URL | Result |
|------|------|-----|--------|
| <name> | <role> | <url> | PASS/FAIL |

### Test Steps Performed
1. <step> — <result>
2. <step> — <result>

### Screenshots
- <description>: <screenshot reference>

### Console Errors
<any errors observed, or "None">

### Issues Found
<any problems, or "None">

### Result: PASS / FAIL

### Notes for Future Playwright Spec
- <test scenario that should be automated>
- <edge cases to cover>
- <user flows to verify>

Read the full file on GitHub · 93 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.

1mo ago First seen · 93 lines · 23 tokens per session scan A 211c0c93b864

Subscribe to this mod's changes

qa-report is an agent published in the GitHub repository guillermoscript/lms-front (40 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 746 once invoked, about $0.0001 per session on Opus 5.5. 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.

Browser automation E2E testing Testing ai course-platform edtech lms nextjs openai

e2e-runner

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

KaelSensei/MagicAIBuilder · 87 tokens

browser-tester

AI-driven browser testing agent. Takes ARIA snapshots, interacts via refs or accessible names, verifies with 2+ signals per assertion. Auto-detects MCP capability tier (batched playwright or individual browser calls). Supports spec-driven, basic, visual, and a11y modes.

ByeongminLee/nextjs-claude-code · 62 tokens

browser-tester-v2

Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…

lipas-liikuntapaikat/lipas · 69 tokens

lms-front: Agent for Claude Code