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.
npx skills add shwilliamson/automatasaurus --skill testing-standardsgit clone --depth 1 https://github.com/shwilliamson/automatasaurusWrote 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/skills/shwilliamson/automatasaurus/testing-standards)<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/testing-standards"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/testing-standards/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/skills/shwilliamson/automatasaurus/testing-standards"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/testing-standards.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 | $0.00029 | $0.01409 |
| Opus 5.5 | $0.00012 | $0.00564 |
| Sonnet 5.5 | $0.00006 | $0.00282 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
testing-standards 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 2mo 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Standards
Guidelines for writing effective tests that catch bugs, enable refactoring, and document behavior.
Testing Pyramid
Prefer more tests at the bottom, fewer at the top:
/ E2E \ Few, slow, high confidence
/----------\
/ Integration \ Some, medium speed
/----------------\
/ Unit Tests \ Many, fast, focused
What to Test
Always Test
- Business logic and calculations
- Edge cases and boundary conditions
- Error handling paths
- Public API contracts
- Security-sensitive code
- Complex conditionals
Usually Skip
- Simple getters/setters
- Framework code (React renders, Express routing)
- Third-party library internals
- Private implementation details
- Logging statements
Unit Tests
Structure: Arrange-Act-Assert
test('calculates total with discount', () => {
// Arrange
const cart = new Cart([{ price: 100 }, { price: 50 }]);
const discount = 0.1;
// Act
const total = cart.calculateTotal(discount);
// Assert
expect(total).toBe(135);
});
Naming Convention
test('[unit] [action] [expected result] [condition]')
Examples:
test('User.validate rejects empty email')test('calculateTax returns 0 for tax-exempt items')test('login redirects to dashboard on success')
Keep Tests Focused
// Bad: Testing multiple behaviors
test('user registration', () => {
expect(validate(user)).toBe(true);
expect(hash(password)).toMatch(/^\$2b\$/);
expect(sendEmail).toHaveBeenCalled();
expect(db.save).toHaveBeenCalled();
});
// Good: One behavior per test
test('validates user email format', () => { ... });
test('hashes password with bcrypt', () => { ... });
test('sends welcome email after registration', () => { ... });
test('persists user to database', () => { ... });
Integration Tests
Test how components work together:
describe('User Registration Flow', () => {
test('creates user and sends welcome email', async () => {
const response = await request(app)
.post('/api/users')
.send({ email: '[email protected]', password: 'secure123' });
expect(response.status).toBe(201);
expect(await User.findByEmail('[email protected]')).toBeTruthy();
expect(emailService.sent).toContainEqual(
expect.objectContaining({ to: '[email protected]' })
);
});
});
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.
- 2mo ago First seen · 245 lines · 29 tokens per session scan A 649663726c8d
testing-standards is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 8mo ago), licensed MIT. It adds 29 tokens to every session and 1,409 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 2026-08-31.
testing-standards compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| testing-standardsshwilliamson/automatasaurus | Skill | 5 | 8mo ago | MIT | A | 29 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 104 | Claude Code |
| axiom-testingCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 38 | Claude Code |
| test-generatorrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 33 | Claude Code |
| testing-blocksadobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 61 | Claude Code |
| designing-testsCloudAI-X/claude-workflow-v2 | Skill | 1.4k | 1mo ago | MIT | A | 48 | Claude Code |
| test-automation-expertcuriositech/some_claude_skills | Skill | 263 | yesterday | MIT | A | 133 | Claude Code |