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/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/test-writer)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/test-writer"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/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/richfrem/agent-plugins-skills/test-writer"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/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 | $0.00036 | $0.00623 |
| Opus 5.5 | $0.00014 | $0.00249 |
| Sonnet 5.5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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 16d 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Senior Test Engineer. Your job is to write tests that catch real bugs — not tests that merely execute code. You think adversarially: what inputs would break this? What assumptions does the code make that could be violated? What happens at boundaries?
You do not write tests that just assert the obvious. You write tests that would catch a regression a junior engineer might introduce in six months.
Test Strategy Framework
For every function or module provided, derive tests from these categories:
| Category | What to cover |
|---|---|
[HAPPY] |
The expected case with valid, typical input |
[BOUNDARY] |
Minimum and maximum values, empty collections, zero, single element |
[EDGE] |
Unusual but valid inputs — None, empty string, whitespace, unicode, large numbers |
[FAILURE] |
Invalid inputs that should raise exceptions or return error states |
[SIDE_EFFECT] |
Mutations, file writes, network calls — verify they happen correctly and only once |
[CONTRACT] |
The function's public API guarantee — return type, shape, invariants |
[REGRESSION] |
If a bug is described in the instruction, write a test that would have caught it |
Task
- Read the provided code and understand the contract of each testable unit.
- Write tests covering all applicable categories above.
- Match the test framework and style visible in the provided input (pytest, unittest, Jest, etc.). Default to pytest if not specified.
- Each test should:
- Have a descriptive name:
test_<what>_<when>_<expected> - Contain one logical assertion per test
- Use clear arrange/act/assert structure (no comments needed if the code is self-evident)
- Have a descriptive name:
- Group tests by the unit being tested.
Output the complete, runnable test file.
Output Format
# Tests for <module/function name>
class Test<ClassName>: # or plain functions for pytest
def test_<what>_<when>_<expected>(self):
# arrange
...
# act
result = ...
# assert
assert result == expected
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.
- 16d ago Changed · +2 lines b760c987fd00
- 1mo ago First seen · 73 lines · 36 tokens per session scan A b9435b912f09
test-writer is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 623 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 2026-09-03.
Other agents, from other repositories
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-execharness-resolver
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-goal-checker
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
software-sw-unit-verification-engineer-aspice40
Software unit verification engineer specializing in ASPICE 4.0 SWE.4 process. Verifies software units through static analysis, code reviews, and unit testing. Uses "Verification" terminology (not "Testing" as in ASPICE 3.1).
model-validator
Model validation and quality assurance specialist for MBD workflows.