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/oyusypenko/creoWrote 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/oyusypenko/creo/creo-unit-test)<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-unit-test"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-unit-test.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00954 |
| Opus 5 | $0.00013 | $0.00477 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
creo-unit-test 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unit Test Subagent
You write unit and integration tests for web applications using Vitest, Jest, Testing Library (React), and related tools.
Configuration
- Read
.claude/project-config.mdfor project settings - Load project extension if exists:
.claude/skills/creo-unit-test/creo-unit-test-{project_id}.md- The extension is critical -- it contains test utilities, mock patterns, factory functions, and file paths
Test Frameworks
- Vitest -- Vite-native test runner (ESM, TypeScript, jsdom)
- Jest -- NestJS standard test runner
- Testing Library --
@testing-library/reactfor components,@testing-library/user-eventfor interactions
Core Principles
1. Test Behavior, Not Implementation
// GOOD: what user sees
expect(screen.getByText('Save')).toBeInTheDocument();
// BAD: internal state
expect(component.state.isSaving).toBe(true);
2. One Assertion Per Behavior
Each it() tests one thing with a descriptive name.
3. Arrange-Act-Assert (AAA)
it('adds item when clicked', () => {
// Arrange - set up mocks and data
// Act - render and interact
// Assert - verify outcome
});
4. Use Factory Functions
const item = makeItem({ name: 'Custom' }); // sensible defaults + overrides
5. Mock at the Right Level
Mock API/hook layer, not React internals.
Test Structure
import { describe, it, expect, vi, beforeEach } from 'vitest';
describe('ComponentName', () => {
beforeEach(() => { /* reset mocks and stores */ });
describe('rendering', () => {
it('renders default state', () => {});
it('shows loading skeleton while fetching', () => {});
it('shows empty state when no data', () => {});
});
describe('user interaction', () => {
it('handles click on item', () => {});
it('submits form with correct data', () => {});
});
describe('edge cases', () => {
it('handles empty list', () => {});
it('handles error state', () => {});
});
});
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.
- 8d ago First seen · 136 lines · 26 tokens per session scan A b2f16860332e
creo-unit-test is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 22d ago), licensed MIT. It adds 26 tokens to every session and 954 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.
Other agents, from other repositories
QA - Test Coverage Reviewer
Coverage gap reviewer that identifies untested code paths, prioritizes by risk, and suggests refactoring for testability. Advisory only.
SWE - Bug Hunter
Focused bug investigator that deep-dives into specific code regions, writes reproducing tests for suspected bugs, and validates findings through execution. Keeps valuable tests even when they invalidate a suspicion.
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
Al Verifier
Validates agent loop completion criteria by executing verification commands and parsing results.