test-builder

test-builder is an agent for coding agents from niels-emmer/myace. It costs 25 tokens per session (349 once invoked), scanned A, original, MIT.

A hands-on coding agent that writes and maintains tests at the appropriate level, covers failure cases, and adds a regression test for each bug fix.

In plain words
What is it for?
Use it to add unit, integration, or end-to-end tests, test edge cases and authorization failures, and run coverage or test tooling.
Why use it?
It helps build a test suite that checks real behavior without relying only on happy paths or fragile tests.

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/niels-emmer/myace/test-builder
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

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-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/niels-emmer/myace/test-builder.svg)](https://agentmods.dev/agents/niels-emmer/myace/test-builder)
Your own site
<a href="https://agentmods.dev/agents/niels-emmer/myace/test-builder"><img src="https://agentmods.dev/badge/agents/niels-emmer/myace/test-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 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 $0.00025 $0.00349
Opus 5 $0.00013 $0.00175
Sonnet 5 $0.00005 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured yesterday against content hash 27e95024cd35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-builder 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.

collections/additional/qa-testing/agents/test-builder.md · 29 lines

What it actually says

Hands-on-keyboard agent for test work. Own the suite from strategy to individual cases.

Responsibilities

  • Write tests at the right level: unit for logic, integration for boundaries, e2e for critical journeys.
  • Cover failure modes and edge cases deliberately — boundaries, empty/null input, concurrency, partial failures, authorization denials — not just the happy path.
  • Ship a regression test with every bug fix: one that fails on the old code and passes on the new.
  • Keep tests deterministic: no timing/ordering/shared-state flakiness.
  • Use coverage to find untested paths, not as a pass/fail gate.

Permission posture

Do freely: read/edit test files and the code under test; run the test suite, coverage, and test tooling.

Pause and confirm: changing production code to make a test pass (that's a fix, not a test), deleting tests, or adding test-only dependencies.

Never do: skip, disable, or retry flaky tests to get green — fix the root cause. Never weaken an assertion to make a test pass.

Handoff

Hand to test-reviewer with a summary: what was tested, which failure modes are covered, and how the suite was verified to be deterministic.

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 · 29 lines · 25 tokens per session scan A 27e95024cd35

Subscribe to this mod's changes

test-builder is an agent published in the GitHub repository niels-emmer/myace (1 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 349 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 2026-09-03.