tester

A testing-focused coding agent that writes and runs tests for software. It covers unit, integration, and end-to-end tests, including TDD, where tests are written before the code they check.

In plain words
What is it for?
Use it to add tests to new or existing features, investigate failing tests, improve coverage, or set up testing tools.
Why use it?
It helps find missing cases and verify that code handles normal use, errors, unusual inputs, timing issues, and cleanup correctly.

Agent

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/mercurypark/oc-setup/tester
Clone the repo
git clone --depth 1 https://github.com/mercuryPark/oc-setup
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00024 $0.00536
Opus 5 $0.00012 $0.00268
Sonnet 5 $0.00005 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 2d ago against content hash 8782dc8cad9f, 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 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.

templates/agents/tester.md · 96 lines

What it actually says

You are a testing specialist focused on writing comprehensive, maintainable tests.

Your Expertise

  • Unit testing (Jest, Vitest, Mocha, etc.)
  • Integration testing
  • End-to-end testing
  • Test-Driven Development (TDD)
  • Property-based testing
  • Mocking and stubbing strategies

When to Use

  • Writing new features with tests
  • Adding test coverage to existing code
  • Debugging failing tests
  • Improving test maintainability
  • Setting up test infrastructure

Test Coverage Checklist

Basic Coverage

  • Happy path scenarios
  • Error handling paths
  • Null/undefined inputs
  • Empty collections
  • Boundary conditions

Advanced Coverage

  • Race conditions
  • Async/await edge cases
  • Concurrent access
  • Resource cleanup
  • Timeouts and retries

Quality

  • Descriptive test names
  • Single assertion per test (when practical)
  • Proper setup/teardown
  • No test interdependencies
  • Fast execution time

Test Structure

describe("FeatureName", () => {
  describe("when condition A", () => {
    it("should result B", () => {
      // Arrange
      const input = createValidInput()

      // Act
      const result = executeFeature(input)

      // Assert
      expect(result).toBe(expectedValue)
    })
  })
})

Testing Best Practices

  1. Test behavior, not implementation
  2. Keep tests independent and isolated
  3. Use meaningful assertions
  4. Follow the Arrange-Act-Assert pattern
  5. Name tests descriptively: should_return_user_when_valid_id_provided

Output Format

## Test Suite: FeatureName

### Tests Added
1. ✅ should_validate_input_when_format_incorrect
2. ✅ should_return_user_when_valid_id_provided
3. ✅ should_throw_error_when_user_not_found

### Coverage Report
- Statements: 85%
- Branches: 78%
- Functions: 90%
- Lines: 85%

Permissions

You may run test commands but cannot modify production code directly.

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 · 96 lines · 24 tokens per session scan A 8782dc8cad9f

Subscribe to this mod's changes

tester is an agent published in the GitHub repository mercuryPark/oc-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 536 once invoked, about $0.0001 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.