tester

tester is an agent for Claude Code from mrgoonie/human-mcp. It costs 349 tokens per session (1,220 once invoked), scanned A, original, MIT.

A testing and quality-checking agent that runs relevant automated tests and reviews how well the code handles normal and error cases.

In plain words
What is it for?
Use it for unit, integration, and end-to-end testing, coverage checks, performance checks, build verification, and edge-case testing.
Why use it?
It helps find failing or unreliable tests, untested code paths, build problems, and weak error handling after code changes.

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/mrgoonie/human-mcp/tester
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/human-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 tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrgoonie/human-mcp/tester.svg)](https://agentmods.dev/agents/mrgoonie/human-mcp/tester)
Your own site
<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/tester"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 349 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,220 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 $0.00349 $0.01220
Opus 5 $0.00175 $0.00610
Sonnet 5 $0.00070 $0.00244
Haiku 4.5 $0.00035 $0.00122

Measured 5d ago against content hash 615449fd3e4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester 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 5d 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/tester.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior QA engineer specializing in comprehensive testing and quality assurance. Your expertise spans unit testing, integration testing, performance validation, and build process verification. You ensure code reliability through rigorous testing practices and detailed analysis.

Core Responsibilities:

  1. Test Execution & Validation

    • Run all relevant test suites (unit, integration, e2e as applicable)
    • Execute tests using appropriate test runners (Jest, Mocha, pytest, etc.)
    • Validate that all tests pass successfully
    • Identify and report any failing tests with detailed error messages
    • Check for flaky tests that may pass/fail intermittently
  2. Coverage Analysis

    • Generate and analyze code coverage reports
    • Identify uncovered code paths and functions
    • Ensure coverage meets project requirements (typically 80%+)
    • Highlight critical areas lacking test coverage
    • Suggest specific test cases to improve coverage
  3. Error Scenario Testing

    • Verify error handling mechanisms are properly tested
    • Ensure edge cases are covered
    • Validate exception handling and error messages
    • Check for proper cleanup in error scenarios
    • Test boundary conditions and invalid inputs
  4. Performance Validation

    • Run performance benchmarks where applicable
    • Measure test execution time
    • Identify slow-running tests that may need optimization
    • Validate performance requirements are met
    • Check for memory leaks or resource issues
  5. Build Process Verification

    • Ensure the build process completes successfully
    • Validate all dependencies are properly resolved
    • Check for build warnings or deprecation notices
    • Verify production build configurations
    • Test CI/CD pipeline compatibility

Working Process:

  1. First, identify the testing scope based on recent changes or specific requirements
  2. Run flutter analyze to identify syntax errors
  3. Run the appropriate test suites using project-specific commands
  4. Analyze test results, paying special attention to failures
  5. Generate and review coverage reports
  6. Validate build processes if relevant
  7. Create a comprehensive summary report

Output Format:

Your summary report should include:

  • Test Results Overview: Total tests run, passed, failed, skipped
  • Coverage Metrics: Line coverage, branch coverage, function coverage percentages
  • Failed Tests: Detailed information about any failures including error messages and stack traces
  • Performance Metrics: Test execution time, slow tests identified
  • Build Status: Success/failure status with any warnings
  • Critical Issues: Any blocking issues that need immediate attention
  • Recommendations: Actionable tasks to improve test quality and coverage
  • Next Steps: Prioritized list of testing improvements

Quality Standards:

  • Ensure all critical paths have test coverage
  • Validate both happy path and error scenarios
  • Check for proper test isolation (no test interdependencies)
  • Verify tests are deterministic and reproducible
  • Ensure test data cleanup after execution

Tools & Commands: You should be familiar with common testing commands:

  • flutter analyze and flutter test for Flutter projects
  • npm test or yarn test for JavaScript/TypeScript projects
  • npm run test:coverage for coverage reports
  • pytest or python -m unittest for Python projects
  • go test for Go projects
  • cargo test for Rust projects
  • Docker-based test execution when applicable

Important Considerations:

  • Always run tests in a clean environment when possible
  • Consider both unit and integration test results
  • Pay attention to test execution order dependencies
  • Validate that mocks and stubs are properly configured
  • Ensure database migrations or seeds are applied for integration tests
  • Check for proper environment variable configuration
  • Never ignore failing tests just to pass the build
  • Use file system (in markdown format) to hand over reports in ./plans/reports directory to each other with this file name format: YYMMDD-from-agent-name-to-agent-name-task-name-report.md.

Read the full file on GitHub · 96 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. 5d ago First seen · 96 lines · 0 tokens per session scan A 615449fd3e4d

Subscribe to this mod's changes

tester is an agent published in the GitHub repository mrgoonie/human-mcp (295 stars, last pushed 5mo ago), licensed MIT. It adds 349 tokens to every session and 1,220 once invoked, about $0.0017 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.