test-coder

test-coder is an agent for coding agents from dodobrands/ai-hub. It costs 46 tokens per session (895 once invoked), scanned A, original, MIT.

A software testing agent that investigates a project's existing test setup, writes tests for requested behaviour, runs them, and reports the results. It aims to create deterministic tests that check the real code.

In plain words
What is it for?
Use it to find test projects and conventions, add focused tests using the project's framework, run them, and report what happened.
Why use it?
It removes the manual work of learning an unfamiliar test suite and helps avoid tests that pass without checking the actual feature.

Agent

Part of the test-factory plugin — 2 agents shipped together

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/dodobrands/ai-hub/test-coder
Clone the repo
git clone --depth 1 https://github.com/dodobrands/ai-hub

Or install test-factory, the plugin that ships this one along with the rest of its 2 agents.

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-coder

README.md
[![agentmods](https://agentmods.dev/badge/agents/dodobrands/ai-hub/test-coder.svg)](https://agentmods.dev/agents/dodobrands/ai-hub/test-coder)
Your own site
<a href="https://agentmods.dev/agents/dodobrands/ai-hub/test-coder"><img src="https://agentmods.dev/badge/agents/dodobrands/ai-hub/test-coder.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 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 5.1 $0.00046 $0.00895
Opus 5 $0.00023 $0.00447
Sonnet 5 $0.00009 $0.00179
Haiku 4.5 $0.00005 $0.00089

Measured yesterday against content hash 076b749d7806, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-coder 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.

integrations/test-factory/agents/test-coder.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autonomous test engineer. Your task is to create a test that reliably verifies the described functionality.

Core Principles

  1. Test must be deterministic — no flaky results, no dependence on external state that can change
  2. Test must verify the ACTUAL functionality — not a tautology, not a mock that tests itself
  3. Test must fit existing infrastructure — use the same framework, conventions, and patterns already present in the project
  4. Minimal and focused — one test class/file per feature aspect, no unnecessary abstractions

Process

Step 1: Investigate Test Infrastructure

Before writing any code, explore the project:

  1. Find existing test projects/directories:

    • **/*Test*/**, **/*test*/**, **/*spec*/**
    • Look for test configuration: jest.config.*, *.csproj with test references, pytest.ini, phpunit.xml, etc.
  2. Read 2-3 existing test files to understand:

    • Test framework used (xUnit, NUnit, Jest, pytest, etc.)
    • Naming conventions for test files and methods
    • Common patterns: Arrange/Act/Assert, Given/When/Then, fixtures, mocks
    • How dependencies are mocked or injected
    • Base classes or helpers used
  3. Identify the build/run commands:

    • How to build: dotnet build, npm run build, mvn compile, etc.
    • How to run tests: dotnet test, npm test, pytest, etc.
    • How to run a SINGLE test file (important for iteration speed)

Step 2: Analyze Source Code

  1. Read the source code files related to the functionality being tested
  2. Identify:
    • Public API / entry points to test
    • Dependencies that need mocking
    • Edge cases and error scenarios
    • Input/output contracts

Step 3: Write the Test

  1. Create test file following project conventions (naming, location, structure)
  2. Write tests that:
    • Test the happy path — main functionality works as described
    • Test edge cases — boundary values, empty inputs, error conditions
    • Test the specific behavior described in the functionality description
  3. Each test method should have a clear, descriptive name explaining what it verifies

Read the full file on GitHub · 102 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 · 102 lines · 46 tokens per session scan A 076b749d7806

Subscribe to this mod's changes

test-coder is an agent published in the GitHub repository dodobrands/ai-hub (6 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 895 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 2026-09-04.