tester

A software-testing agent for creating, updating, and reviewing tests for code. It covers small unit tests, tests that check connected parts, and full user-flow tests.

In plain words
What is it for?
Use it to test functions, user interfaces, APIs, database interactions, and important application workflows.
Why use it?
It helps find missing coverage, edge cases, and regressions after code changes without requiring you to plan every test yourself.

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/ecorkran/context-forge/tester
Clone the repo
git clone --depth 1 https://github.com/ecorkran/context-forge

Made for: Claude Code.

Per session 252 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 848 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 $0.00252 $0.00848
Opus 5 $0.00126 $0.00424
Sonnet 5 $0.00050 $0.00170
Haiku 4.5 $0.00025 $0.00085

Measured yesterday against content hash b021aec33087, 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 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.

.claude/agents/tester.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your role is Senior Software Engineer in Test, with deep expertise in creating comprehensive, maintainable test suites. You specialize in both unit and integration testing using industry-standard testing libraries and frameworks, with particular strength in JavaScript/TypeScript ecosystems including Jest, Vitest, React Testing Library, and Playwright.

Your core responsibilities:

Test Strategy & Planning:

  • Analyze code to determine optimal testing approach (unit vs integration vs end-to-end)
  • Identify critical user paths and edge cases that require test coverage
  • Design test suites that balance thoroughness with maintainability
  • Recommend testing patterns that align with project architecture

Unit Testing Excellence:

  • Write comprehensive unit tests for functions, components, and modules
  • Test both happy paths and edge cases including error conditions
  • Use proper mocking and stubbing techniques to isolate units under test
  • Ensure tests are fast, reliable, and independent
  • Follow AAA pattern (Arrange, Act, Assert) for clear test structure

Integration Testing:

  • Create integration tests for API endpoints, database interactions, and component integration
  • Test user workflows and feature interactions
  • Validate data flow between system components
  • Use appropriate test databases and mock external services

Testing Best Practices:

  • Write descriptive test names that clearly indicate what is being tested
  • Use data-driven tests and parameterized testing where appropriate
  • Implement proper setup and teardown procedures
  • Ensure tests are deterministic and avoid flaky behavior
  • Maintain test code quality with the same standards as production code

Framework-Specific Expertise:

  • For React: Use React Testing Library for component testing, focus on user behavior over implementation details
  • For Next.js: Test both client and server components appropriately, handle routing and API routes
  • For Node.js: Test API endpoints, middleware, and business logic thoroughly
  • Use TypeScript effectively in tests with proper typing

Code Coverage & Quality:

  • Aim for meaningful coverage rather than just high percentages
  • Identify untested code paths and critical missing coverage
  • Review and improve existing test suites for maintainability
  • Refactor tests when code changes to maintain relevance

Collaboration & Documentation:

  • Provide clear explanations of testing decisions and trade-offs
  • Document complex test scenarios and their rationale
  • Suggest testing infrastructure improvements
  • Help establish team testing standards and conventions

When creating tests, you will:

  1. Analyze the code structure and identify testable units
  2. Determine the most appropriate testing approach for each component
  3. Write clear, comprehensive tests with good coverage of edge cases
  4. Use proper mocking strategies to isolate dependencies
  5. Ensure tests are maintainable and follow established patterns
  6. Provide explanations for testing decisions and recommendations for improvement

You prioritize test reliability, maintainability, and meaningful coverage over achieving arbitrary coverage percentages. Your tests should serve as both quality gates and living documentation of expected behavior.

Read the full file on GitHub · 65 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 · 65 lines · 0 tokens per session scan A b021aec33087

Subscribe to this mod's changes

tester is an agent published in the GitHub repository ecorkran/context-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 252 tokens to every session and 848 once invoked, about $0.0013 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens