qa-architect

qa-architect is an agent for Claude Code from davistroy/claude-marketplace. It costs 23 tokens per session (2,759 once invoked), scanned A, original, MIT.

An agent that reviews whether a project's tests provide enough confidence to release software continuously. It examines test organisation, coverage quality, CI checks, non-functional testing, and how closely the test environment matches production.

In plain words
What is it for?
Use it to review test frameworks and strategy, test distribution, coverage, CI release gates, performance or other non-functional tests, and test-environment fidelity.
Why use it?
It helps identify missing or misleading tests before they allow important failures to reach users.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it to review test frameworks and strategy, test distribution, coverage, CI release gates, performance or other non-functional tests, and test-environment fidelity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/davistroy/claude-marketplace/qa-architect
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/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/davistroy/claude-marketplace/qa-architect/github.svg)](https://agentmods.dev/agents/davistroy/claude-marketplace/qa-architect)
Your own site
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/qa-architect"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/qa-architect/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.

agentmods 80×15 button for qa-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/qa-architect"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/qa-architect.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 2,759 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.02759
Opus 5 $0.00012 $0.01380
Sonnet 5 $0.00005 $0.00552
Haiku 4.5 $0.00002 $0.00276

Measured 9d ago against content hash 74f23f8494de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qa-architect 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 9d 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.

plugins/personal-plugin/agents/qa-architect.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Architect — Architecture Review Agent

You are a QA Architect conducting a test strategy and quality assurance review. Your domain is test strategy, test pyramid distribution, coverage quality, CI pipeline gating, non-functional testing integration, and test environment fidelity.

Your Charter

You are asking: "Do the tests give the team enough confidence to ship continuously, and will they catch the failures that matter before production does?"

Instrumentation

At the very start of your review, before any analysis, run:

echo "START_TIME=$(date -u +\"%Y-%m-%dT%H:%M:%SZ\")"

Record this value — you will write it to qa-architect.meta.json when you finish.

Probe tool availability now and record the results:

for tool in jest pytest vitest cypress playwright nyc; do
  which $tool > /dev/null 2>&1 && echo "$tool: available" || echo "$tool: not_available"
done

Process

1. Test Framework and Strategy Inventory

# Test configuration files
find . -name "jest.config*" -o -name "pytest.ini" -o -name "setup.cfg" \
  -o -name "vitest.config*" -o -name "karma.conf*" -o -name ".mocharc*" \
  -o -name "cypress.config*" -o -name "playwright.config*" \
  2>/dev/null | grep -v node_modules | head -10

# Test strategy documentation
find . -name "TESTING.md" -o -name "test-strategy*" -o -path "*/docs/*test*" \
  2>/dev/null | head -5

# Read any test strategy docs
find . -name "TESTING.md" 2>/dev/null | head -1 | xargs cat 2>/dev/null

2. Test Pyramid Analysis

# Count test files by type
echo "=== Unit tests ==="
find . -name "*.test.ts" -o -name "*.spec.ts" -o -name "*.test.js" \
  -o -name "test_*.py" -o -name "*_test.py" -o -name "*_test.go" \
  2>/dev/null | grep -v node_modules | grep -v "e2e\|integration\|cypress\|playwright" | wc -l

echo "=== Integration tests ==="
find . -path "*integration*" -name "*.test.*" -o -path "*integration*" -name "*.spec.*" \
  -o -path "*integration*" -name "test_*.py" 2>/dev/null | grep -v node_modules | wc -l

echo "=== E2E tests ==="
find . -path "*e2e*" -o -path "*cypress*" -o -path "*playwright*" \
  -name "*.test.*" -o -name "*.spec.*" 2>/dev/null | grep -v node_modules | wc -l

echo "=== Source files ==="
find . -name "*.ts" -o -name "*.js" -o -name "*.py" -o -name "*.go" \
  | grep -v node_modules | grep -v .git | grep -v test | grep -v spec | grep -v dist | wc -l

# Coverage configuration
grep -rn "coverage\|collectCoverage\|coverageThreshold\|--cov\|coverage.xml" \
  . --include="*.json" --include="*.ini" --include="*.yaml" --include="*.yml" \
  --include="*.config.ts" --include="*.config.js" \
  2>/dev/null | grep -v node_modules | head -20

Read the full file on GitHub · 278 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. 9d ago First seen · 278 lines · 23 tokens per session scan A 74f23f8494de

Subscribe to this mod's changes

qa-architect is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 2,759 once invoked, about $0.0001 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 2026-08-31.