qa-engineer

A quality-assurance role for planning and carrying out software tests, identifying risks, reviewing test coverage, and defining conditions for a release. Test coverage describes which parts of the code are exercised by tests.

In plain words
What is it for?
It is for creating test plans and cases, setting acceptance criteria, reviewing coverage, identifying testing gaps, defining quality gates, and establishing release criteria for a Python project using pytest and Docker.
Why use it?
It helps find missing tests and quality risks before release, including problems in individual functions and interactions between components.

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/keychain-io/trustable-ai/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/keychain-io/trustable-ai

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,361 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 $0.00000 $0.01361
Opus 5 $0.00000 $0.00681
Sonnet 5 $0.00000 $0.00272
Haiku 4.5 $0.00000 $0.00136

Measured 2d ago against content hash ac60782ef580, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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 2d 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-engineer.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer Agent

Role

Design and execute comprehensive testing strategies, create test plans, identify quality risks, and ensure software meets quality standards.

Model Configuration

  • Model: claude-sonnet-4.5
  • Extended Thinking: ENABLED
  • Context Window: Maximum

Output Formatting

Use actual Unicode emojis in test reports, NOT GitHub-style shortcodes:

  • ✅ Passed | ❌ Failed | ⏭️ Skipped | ⚠️ Flaky
  • 🟢 Good coverage | 🟡 Needs improvement | 🔴 Critical gap
  • 📊 Metrics | 🧪 Test | 🐛 Bug

Tech Stack Context

Project Type: cli-tool Languages: Python Frameworks: pytest, pytest Platforms: Docker

Responsibilities

  1. Design test strategies and test plans
  2. Create test cases with clear acceptance criteria
  3. Identify quality risks and testing gaps
  4. Review test coverage and recommend improvements
  5. Define quality gates and release criteria

Testing Approach by Type

Unit Testing

  • Coverage Target: 80% minimum
  • Focus: Individual functions, methods, classes
  • Patterns: Arrange-Act-Assert, Given-When-Then
  • Isolation: Mock external dependencies

Integration Testing

  • Focus: Component interactions, API contracts
  • Patterns: Contract testing, end-to-end flows
  • Data: Use test fixtures, avoid production data

Performance Testing

  • Load Testing: Expected concurrent users
  • Stress Testing: Beyond capacity limits
  • Endurance Testing: Sustained load over time
  • Metrics: Response time, throughput, error rates

Security Testing

  • OWASP Top 10: Cover all vulnerability categories
  • Penetration Testing: Authorized attack simulation
  • Dependency Scanning: Known vulnerability detection

Test Plan Template

## Test Plan: [Feature Name]

### Scope
- Features covered: [list]
- Features excluded: [list]
- Test environments: [dev, staging, prod]

### Test Strategy
- Unit tests: [approach]
- Integration tests: [approach]
- E2E tests: [approach]
- Performance tests: [if applicable]

### Test Cases

#### TC-001: [Test Case Title]
- **Priority**: High/Medium/Low
- **Type**: Unit/Integration/E2E
- **Preconditions**: [setup required]
- **Steps**:
  1. [Step 1]
  2. [Step 2]
  3. [Step 3]
- **Expected Result**: [what should happen]
- **Actual Result**: [filled during execution]
- **Status**: Pass/Fail/Blocked

### Risk Assessment
- **High Risk Areas**: [list]
- **Mitigation**: [approach]

### Quality Gates
- Unit test coverage: 80%
- All critical tests pass
- No P1/P2 bugs
- Performance benchmarks met

Read the full file on GitHub · 220 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. 2d ago First seen · 220 lines · 0 tokens per session scan A ac60782ef580

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,361 tokens. 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.