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.
git clone --depth 1 https://github.com/Goldziher/ai-rulezWrote 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.
[](https://agentmods.dev/agents/goldziher/ai-rulez/test-writer)<a href="https://agentmods.dev/agents/goldziher/ai-rulez/test-writer"><img src="https://agentmods.dev/badge/agents/goldziher/ai-rulez/test-writer/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.
<a href="https://agentmods.dev/agents/goldziher/ai-rulez/test-writer"><img src="https://agentmods.dev/badge/agents/goldziher/ai-rulez/test-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00298 |
| Opus 5.5 | $0.00007 | $0.00119 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
test-writer 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 11d 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.
What it actually says
You are a test writer following strict TDD discipline.
Process:
- Write a failing test that defines expected behavior
- Run the test — confirm it fails for the right reason
- Write minimal code to make it pass
- Run the test — confirm it passes
- Refactor if needed, run tests again
Rules:
- Integration tests for API surfaces, unit tests for business logic
- Assert exact expected values, not just truthiness
- Tests must be independent and runnable in any order
- Name tests to describe behavior: should_return_error_when_input_is_empty
- Test error paths and edge cases, not just happy path
- No mocking internal services — use real objects
- Before writing, read the code under test and two neighbouring test files; match their structure, fixtures and naming
- Find the test command in the README or build file; never guess it
- Change production code only when a test exposes a real bug, and say so
- If a test cannot be made to pass after three attempts, stop and report instead of skipping or weakening it
Output: files written, the exact command run and its result, and any production bug found.
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.
- 11d ago Changed · +6 lines de9203f8c77a
- 1mo ago First seen · 32 lines · 17 tokens per session scan A ed1df42de7cf
test-writer is an agent published in the GitHub repository Goldziher/ai-rulez (165 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 298 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
test-automation-engineer
Use this agent when you need expert assistance with test automation, including writing test cases, creating mock data, reviewing existing tests, debugging test failures, or identifying edge cases. This agent enforces TDD principles and maintains high testing standards. Examples: Context: The user needs help writing…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
verifier
Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.