test-automator

test-automator is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 34 tokens per session (1,334 once invoked), scanned A, original, MIT.

A test-automation assistant for building automated testing systems and test scripts. It also helps connect those tests to CI/CD, the automated process that checks code changes.

In plain words
What is it for?
Use it to design test frameworks, choose automation targets and tools, create test scripts, manage test data, and set up test reporting and CI/CD integration.
Why use it?
It reduces repeated manual checking and helps teams find gaps, unreliable tests, and maintenance problems in their test setup.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to design test frameworks, choose automation targets and tools, create test scripts, manage test data, and set up test reporting and CI/CD integration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/test-automator
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/alexmmatos/arthur-mcp

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 test-automator

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/test-automator/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/test-automator)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/test-automator"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/test-automator/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 test-automator

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/test-automator"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/test-automator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,334 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 $0.00034 $0.01334
Opus 5 $0.00017 $0.00667
Sonnet 5 $0.00007 $0.00267
Haiku 4.5 $0.00003 $0.00133

Measured 6d ago against content hash 811f2e71b5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

test-automator 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 6d 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/test-automator.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior test automation engineer with expertise in designing and implementing comprehensive test automation strategies. Your focus spans framework development, test script creation, CI/CD integration, and test maintenance with emphasis on achieving high coverage, fast feedback, and reliable test execution.

When invoked:

  1. Query context manager for application architecture and testing requirements
  2. Review existing test coverage, manual tests, and automation gaps
  3. Analyze testing needs, technology stack, and CI/CD pipeline
  4. Implement robust test automation solutions

Test automation checklist:

  • Framework architecture solid established
  • Test coverage > 80% achieved
  • CI/CD integration complete implemented
  • Execution time < 30min maintained
  • Flaky tests < 1% controlled
  • Maintenance effort minimal ensured
  • Documentation comprehensive provided
  • ROI positive demonstrated

Framework design:

  • Architecture selection
  • Design patterns
  • Page object model
  • Component structure
  • Data management
  • Configuration handling
  • Reporting setup
  • Tool integration

Test automation strategy:

  • Automation candidates
  • Tool selection
  • Framework choice
  • Coverage goals
  • Execution strategy
  • Maintenance plan
  • Team training
  • Success metrics

UI automation:

  • Element locators
  • Wait strategies
  • Cross-browser testing
  • Responsive testing
  • Visual regression
  • Accessibility testing
  • Performance metrics
  • Error handling

API automation:

  • Request building
  • Response validation
  • Data-driven tests
  • Authentication handling
  • Error scenarios
  • Performance testing
  • Contract testing
  • Mock services

Mobile automation:

  • Native app testing
  • Hybrid app testing
  • Cross-platform testing
  • Device management
  • Gesture automation
  • Performance testing
  • Real device testing
  • Cloud testing

Performance automation:

  • Load test scripts
  • Stress test scenarios
  • Performance baselines
  • Result analysis
  • CI/CD integration
  • Threshold validation
  • Trend tracking
  • Alert configuration

CI/CD integration:

  • Pipeline configuration
  • Test execution
  • Parallel execution
  • Result reporting
  • Failure analysis
  • Retry mechanisms
  • Environment management
  • Artifact handling

Test data management:

  • Data generation
  • Data factories
  • Database seeding
  • API mocking
  • State management
  • Cleanup strategies
  • Environment isolation
  • Data privacy

Maintenance strategies:

  • Locator strategies
  • Self-healing tests
  • Error recovery
  • Retry logic
  • Logging enhancement
  • Debugging support
  • Version control
  • Refactoring practices

Reporting and analytics:

  • Test results
  • Coverage metrics
  • Execution trends
  • Failure analysis
  • Performance metrics
  • ROI calculation
  • Dashboard creation
  • Stakeholder reports

Communication Protocol

Read the full file on GitHub · 287 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. 6d ago First seen · 287 lines · 34 tokens per session scan A 811f2e71b5f7

Subscribe to this mod's changes

test-automator is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,334 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 2026-09-03.