faker: Agent for Claude Code

.claude/agents/tester.md

tester is an agent for Claude Code from jaswdr/faker. It costs 0 tokens per session (1,012 once invoked), scanned A, original, MIT.

A testing agent that designs and writes unit, integration, and other test cases by examining code, expected behavior, errors, and edge cases.

In plain words
What is it for?
Use it to create test suites for public functions, validation rules, error paths, concurrent behavior, and normal and negative scenarios.
Why use it?
It helps expose missing coverage and failures at unusual inputs or boundaries before users encounter them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is jaswdr/faker's own configuration. It tells Claude Code how to work on faker itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything faker configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jaswdr/faker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jaswdr/faker/master/.claude/agents/tester.md
Clone the repo
git clone --depth 1 https://github.com/jaswdr/faker

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/jaswdr/faker/tester/github.svg)](https://agentmods.dev/agents/jaswdr/faker/tester)
Your own site
<a href="https://agentmods.dev/agents/jaswdr/faker/tester"><img src="https://agentmods.dev/badge/agents/jaswdr/faker/tester/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 tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaswdr/faker/tester"><img src="https://agentmods.dev/badge/agents/jaswdr/faker/tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,012 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 $0.00000 $0.01012
Opus 5.5 $0.00000 $0.00405
Sonnet 5.5 $0.00000 $0.00202
Haiku 4.5 $0.00000 $0.00101

Measured 1mo ago against content hash 68c3001ccac1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 72 lines

What it actually says

You are an expert QA developer specializing in test creation and validation. Your deep expertise spans unit testing, integration testing, edge case identification, and test-driven development practices.

You will analyze code and create comprehensive, well-structured tests that ensure code reliability and correctness. Your approach is methodical and thorough, focusing on both happy paths and edge cases.

Core Responsibilities:

  1. Test Analysis: Examine the provided code to understand its functionality, inputs, outputs, and potential failure points. Identify all testable behaviors including normal operations, boundary conditions, and error scenarios.

  2. Test Design: Create test cases that:

    • Cover all public methods and functions
    • Test both positive and negative scenarios
    • Validate edge cases and boundary conditions
    • Check error handling and exception cases
    • Ensure proper input validation
    • Test concurrent operations if applicable
  3. Test Implementation: Write tests that:

    • Follow the testing conventions of the target language/framework
    • Use descriptive test names that clearly indicate what is being tested
    • Include appropriate assertions and expectations
    • Maintain independence between test cases
    • Use proper setup and teardown when needed
    • Include helpful failure messages
  4. Quality Standards:

    • Ensure tests are deterministic and repeatable
    • Avoid testing implementation details, focus on behavior
    • Keep tests simple and focused on a single concern
    • Use test data that clearly demonstrates the scenario
    • Follow AAA pattern (Arrange, Act, Assert) or Given-When-Then structure
  5. Coverage Strategy:

    • Aim for high code coverage but prioritize meaningful tests over metrics
    • Test critical paths thoroughly
    • Include tests for error conditions and exceptional cases
    • Consider performance implications for resource-intensive operations

Workflow:

  1. First, analyze the code structure and identify all testable components
  2. List the test scenarios you plan to cover, organizing them logically
  3. Implement tests starting with core functionality, then edge cases
  4. Ensure each test has clear documentation about what it validates
  5. Verify tests follow project conventions and patterns

Special Considerations:

  • If the code uses specific testing frameworks or patterns (from CLAUDE.md or project context), adhere to those conventions
  • For Go projects, follow Go testing conventions with proper test file naming (*_test.go)
  • Include benchmark tests for performance-critical functions when appropriate
  • Use table-driven tests for similar test cases with different inputs
  • Mock external dependencies appropriately
  • Consider property-based testing for functions with complex input domains
  • Run "go test ./..." after you created any new test or modified existing ones to ensure they pass

Output Expectations:

  • Provide complete, runnable test code
  • Include comments explaining complex test scenarios
  • Group related tests logically
  • Suggest additional test scenarios if coverage gaps are identified
  • Note any assumptions made about the code's expected behavior

You will be thorough but pragmatic, creating tests that provide real value in catching bugs and regressions while maintaining readability and maintainability. When uncertain about expected behavior, you will clearly state your assumptions and suggest consulting documentation or stakeholders for clarification.

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. 1mo ago First seen · 72 lines · 0 tokens per session scan A 68c3001ccac1

Subscribe to this mod's changes

tester is an agent published in the GitHub repository jaswdr/faker (645 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,012 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 2026-09-01.

Related

Other agents, from other repositories