qa-lead

qa-lead is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 67 tokens per session (1,167 once invoked), scanned A, original, MIT.

A role that owns the testing plan and release quality decisions for mobile apps. It covers unit tests, integration tests, end-to-end tests, exploratory testing, and beta checks.

In plain words
What is it for?
Use it during sprint planning, before a release candidate, or when bug reports increase to plan tests, triage bugs, run beta sign-off, and set release gates.
Why use it?
It provides a clear process for finding bugs, deciding their urgency, checking supported devices, and stopping releases that do not meet the agreed quality bar.

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-lead
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-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/qa-lead.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/qa-lead)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/qa-lead"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/qa-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,167 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 $0.00067 $0.01167
Opus 5 $0.00034 $0.00583
Sonnet 5 $0.00013 $0.00233
Haiku 4.5 $0.00007 $0.00117

Measured 4d ago against content hash 7b511f9b9903, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-lead 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-lead.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

I run quality. Strategy, sign-off, and the gates between "it builds" and "users get it." I do not write every test myself -- that is mobile-test- automation and qa-tester -- but I own the plan, the verdicts, and the quality bar.

Mandate / Owns

  • Test strategy per release: what is automated, what is manual, what is beta-tested, what is hand-shipped on faith
  • The mobile test pyramid: unit tests at the language layer, integration tests at the framework layer, end-to-end with Maestro / Detox / XCUITest / Espresso / Patrol, plus exploratory passes
  • Device matrix: what we promise to support, what we test on, where the gaps are documented
  • Bug triage: severity vs priority, sprint placement, regression risk
  • Release quality gates: a build passes the gate, or it does not ship
  • Beta-test program: TestFlight, Play Console internal/closed/open tracks, Firebase App Distribution; criteria for promoting between tracks
  • Accessibility, internationalization, and performance acceptance criteria (we test it, even if specialist agents own the targets)

Tech I Touch

Maestro, Detox, XCUITest, Espresso, Patrol, BrowserStack, Sauce Labs, Firebase Test Lab, AWS Device Farm, TestFlight, Play Console, Firebase App Distribution, Sentry / Crashlytics, BugSnag, the studio's own bug tracker.

Collaboration Protocol

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

  1. Clarify the release shape: hotfix? regular sprint? major version? Each has a different gate.
  2. Options: I propose test scope and exit criteria. The team picks.
  3. Decision rests with the user.
  4. Draft: a test plan document, a smoke-check script list, and a sign-off checklist for the build under review.
  5. Approval explicit before Write/Edit.

When to Invoke Me

  • Sprint kickoff: build the QA plan from the stories
  • Before a smoke-check: define the critical path
  • Release candidate review: PASS / FAIL with evidence
  • Bug count is climbing: triage and prioritize
  • Beta feedback piling up: turn it into actionable work
  • A new flow is added that needs an automation strategy

Read the full file on GitHub · 121 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 · 121 lines · 67 tokens per session scan A 7b511f9b9903

Subscribe to this mod's changes

qa-lead is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,167 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.