A systematic quality-assurance command for testing a web app and checking its overall health. It can inspect pages, forms, accessibility, responsiveness, performance, links, and browser errors.

Use it to smoke-test key routes, run deeper page and accessibility checks, calculate a health score, fix reported bugs when enabled, and retest known issues.

It helps find problems that a quick manual check may miss and supports repeated testing after fixes.

qa — Command for Claude Code by ShaheerKhawaja

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.

Clone the repo

git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

Made for: Claude Code.

Or install productionos, the plugin that ships this one along with the rest of its 4 skills, 41 commands, 11 agents.

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/commands/shaheerkhawaja/productionos/qa.svg)](https://agentmods.dev/commands/shaheerkhawaja/productionos/qa)

Your own site

<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/qa"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 592 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00030	$0.00592
Opus 5	$0.00015	$0.00296
Sonnet 5	$0.00006	$0.00118
Haiku 4.5	$0.00003	$0.00059

Measured 6d ago against content hash c155dccdb5d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3000 > /dev/null 2>&1 && echo "Dev server: http://localhost:3000"

.claude/commands/qa.md · 78 lines

What it actually says

/qa — Systematic QA Testing

Test the web app systematically. Find bugs. Fix them. Re-test. Score health 0-100.

Step 0: Preamble

Run templates/PREAMBLE.md. Detect dev server URL.

Step 1: Discover

# Detect dev server
curl -s http://localhost:3000 > /dev/null 2>&1 && echo "Dev server: http://localhost:3000"
curl -s http://localhost:8000 > /dev/null 2>&1 && echo "Dev server: http://localhost:8000"

Step 2: Smoke Test

Dispatch browser-controller to navigate key pages:

Home/landing
Auth (login/signup)
Dashboard/main
Settings
Any page with forms

Report: loads? errors? missing elements?

Step 3: Deep QA (if mode = full)

Dispatch parallel agents:

browser-controller: Navigate every route, screenshot each
ux-auditor: Full WCAG + interaction audit on each page
self-evaluator: Score each page's quality

Step 4: Health Score

Calculate 0-100 score:

Pages load without error: 20 pts
No console errors: 15 pts
Forms work: 15 pts
Accessibility passes: 15 pts
Responsive: 15 pts
Performance (< 3s load): 10 pts
No broken links: 10 pts

Step 5: Fix Loop (if fix = on)

For each bug found:

Read the source file causing the issue
Fix with minimal change
Re-test to verify fix
Self-eval the fix quality

Step 6: Report

Write to .productionos/QA-REPORT-{timestamp}.md:

# QA Report
**Health Score:** X/100
**Pages Tested:** N
**Bugs Found:** N
**Bugs Fixed:** N
**Regressions:** N (if regression mode)

Self-Eval

Run templates/SELF-EVAL-PROTOCOL.md on QA thoroughness.

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.

6d ago First seen · 78 lines · 30 tokens per session scan A c155dccdb5d9

Subscribe to this mod's changes

qa is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 592 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.

Browser automation Claude Code E2E testing Multi-Agent Testing agentic-development claude-code-plugin llm-judge prompt-engineering

qa