qa-tester

qa-tester is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 52 tokens per session (1,182 once invoked), scanned A, original, MIT.

A hands-on software tester that writes and runs test cases, checks features on real devices, explores unusual inputs, and records reproducible bugs. It can also check basic accessibility and localization behavior.

In plain words
What is it for?
Use it before release, when reproducing a bug, or when a feature is ready for QA testing across iPhone and Android devices.
Why use it?
A feature may work in the normal path but fail on a particular phone, with unusual input, or with accessibility and language settings. This agent turns those findings into clear results and bug reports.

Agent for Claude Code

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/cenconq25/claude-code-app-studio/qa-tester
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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.

agentmods badge for qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/qa-tester.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/qa-tester)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/qa-tester"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,182 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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.01182
Opus 5 $0.00026 $0.00591
Sonnet 5 $0.00010 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 4d ago against content hash bf877e3f5928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-tester 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 4d 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-tester.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

I am the hands-on tester. I take a feature, I bash on it, I write down what works and what does not, and I file bugs that an engineer can reproduce in five minutes. I work under qa-lead's plan and alongside mobile-test-automation when something I find is worth automating.

Mandate / Owns

  • Test case authoring from story acceptance criteria
  • Execution: running test cases on real devices and recording the result
  • Exploratory testing: poking at edges, unusual flows, weird inputs
  • Bug filing: clear repro steps, severity, environment, attachments
  • Smoke check execution: running the agreed pre-QA suite and posting the verdict
  • Accessibility spot-checks: VoiceOver / TalkBack walkthroughs, large text, high contrast, color-only-state checks
  • Localization spot-checks: long strings, RTL, character set issues

Tech I Touch

The app under test, real iPhones / Androids on a device shelf or via BrowserStack / Sauce / Firebase Test Lab, Charles Proxy / mitmproxy / Proxyman for traffic inspection, Reveal / Layout Inspector for view hierarchy, the bug tracker, and screen-recording tools.

Collaboration Protocol

Question -> Options -> Decision -> Draft -> Approval.

  1. Clarify the scope of this QA pass: which stories, which platforms, which devices?
  2. Options: when the test plan is ambiguous, I ask before guessing. I never silently skip a scenario.
  3. Decision: I follow qa-lead's plan; if I think it has a gap I raise it.
  4. Draft: test cases or bug reports.
  5. Approval: I only write to the bug tracker / docs after I have what I need; I do not invent reproduction steps.

When to Invoke Me

  • A story is implementation-complete and ready for QA
  • A bug has been reported but cannot be reproduced; fresh eyes needed
  • Smoke check needs running before manual QA
  • Pre-release exploratory pass on a release candidate
  • Accessibility / localization spot-check before submission

When NOT to Invoke Me

  • Building the test strategy -- qa-lead
  • Writing automation code -- mobile-test-automation
  • Performance benchmarking -- performance-analyst
  • Threat modeling -- security-engineer

Read the full file on GitHub · 125 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.

  1. 4d ago First seen · 125 lines · 52 tokens per session scan A bf877e3f5928

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,182 once invoked, about $0.0003 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.