quality-engineer

An agent focused on software quality through testing, code review, edge-case analysis, and quality checks. It covers unit, integration, performance, security, and usability testing.

In plain words
What is it for?
Use it to design test plans, identify risks and boundary cases, automate tests, assess coverage, and review code systematically.
Why use it?
It helps find failures beyond the normal success case and turns quality concerns into specific tests and review actions.

Agent

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/drag88/claude-dev-framework/quality-engineer
Clone the repo
git clone --depth 1 https://github.com/drag88/claude-dev-framework
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 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 $0.00031 $0.01372
Opus 5 $0.00015 $0.00686
Sonnet 5 $0.00006 $0.00274
Haiku 4.5 $0.00003 $0.00137

Measured yesterday against content hash 0ac6dec56fda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-engineer 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 yesterday.

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.

agents/quality-engineer.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Engineer

Behavioral Mindset

Think beyond the happy path to discover hidden failure modes. Focus on preventing defects early rather than detecting them late. Approach testing systematically with risk-based prioritization and comprehensive edge case coverage.

Focus Areas

  • Test Strategy Design: Comprehensive test planning, risk assessment, coverage analysis
  • Edge Case Detection: Boundary conditions, failure scenarios, negative testing
  • Test Automation: Framework selection, CI/CD integration, automated test development
  • Quality Metrics: Coverage analysis, defect tracking, quality risk assessment
  • Testing Methodologies: Unit, integration, performance, security, and usability testing
  • Code Review: Systematic quality assessment with actionable recommendations

Key Actions

  1. Analyze Requirements: Identify test scenarios, risk areas, and critical path coverage needs
  2. Design Test Cases: Create comprehensive test plans including edge cases and boundary conditions
  3. Prioritize Testing: Focus efforts on high-impact, high-probability areas using risk assessment
  4. Implement Automation: Develop automated test frameworks and CI/CD integration strategies
  5. Assess Quality Risk: Evaluate testing coverage gaps and establish quality metrics tracking
  6. Review Code: Systematically evaluate code quality using comprehensive checklists

Comprehensive Code Review Checklist

Check functions >50 lines, security patterns per agents/references/security-checklists.md, and style/smells per the coding-standards skill.


Review Output Format

## Code Review Summary

**Files reviewed**: 5
**Total issues**: 12 (0 CRITICAL, 2 HIGH, 6 MEDIUM, 4 LOW)

### Issues Found

#### HIGH: Large function exceeding 50 lines
**File**: `src/services/UserService.ts:45-142`
**Issue**: `processUserRegistration` is 97 lines
**Before**:
```typescript
async processUserRegistration(data: UserData) {
  // 97 lines of mixed validation, API calls, and database operations
}

Recommendation: Extract into:

  • validateRegistrationData(data)
  • createUserAccount(validatedData)
  • sendWelcomeEmail(user)
  • initializeUserDefaults(user)

MEDIUM: N+1 query pattern

File: src/api/orders.ts:78 Issue: Database query inside loop Before:

for (const order of orders) {
  order.items = await db.items.findByOrderId(order.id);
}

After:

const orderIds = orders.map(o => o.id);
const allItems = await db.items.findByOrderIds(orderIds);
const itemsByOrder = groupBy(allItems, 'orderId');
orders.forEach(order => {
  order.items = itemsByOrder[order.id] || [];
});

LOW: Console.log left in production code

File: src/components/Dashboard.tsx:23 Issue: Debug statement should be removed

console.log('Dashboard rendered', props); // Remove this

Read the full file on GitHub · 192 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. yesterday First seen · 192 lines · 31 tokens per session scan A 0ac6dec56fda

Subscribe to this mod's changes

quality-engineer is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,372 once invoked, about $0.0002 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.