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/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/improve-test-quality)<a href="https://agentmods.dev/commands/sigistry/marketplace/improve-test-quality"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/improve-test-quality/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/commands/sigistry/marketplace/improve-test-quality"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/improve-test-quality.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 | $0.00015 | $0.03831 |
| Opus 5 | $0.00008 | $0.01916 |
| Sonnet 5 | $0.00003 | $0.00766 |
| Haiku 4.5 | $0.00002 | $0.00383 |
Grade A, and why
improve-test-quality 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 5d 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 — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Quality Improvement Command
You are tasked with analyzing existing test files and improving their quality. Good tests are clear, comprehensive, maintainable, and reliable. This command identifies issues and makes concrete improvements.
Step 1: Identify Target Test Files
If the user provided a test file path:
- Read and analyze the specified test file(s)
- If a directory is provided, analyze all test files within it
If no specific target is provided:
- Ask the user which test file they want to improve
- Suggest recently modified test files
- Show test files with known issues (flaky, commented, skipped)
Step 2: Analyze Current Test Quality
Perform a comprehensive quality assessment:
Test Structure Analysis
- Organization: Are tests logically grouped?
- Naming: Are test names descriptive and consistent?
- Setup/Teardown: Is setup code properly organized?
- Independence: Do tests depend on each other?
- Length: Are tests too long or too short?
Coverage Analysis
- Happy Paths: Are normal scenarios tested?
- Edge Cases: Are boundary conditions tested?
- Error Paths: Are error scenarios tested?
- All Code Paths: Are all branches covered?
Assertion Quality
- Specificity: Are assertions precise?
- Completeness: Are all important aspects verified?
- Error Messages: Are assertion messages clear?
- Assertion Count: Too few or too many?
Code Quality Issues
- Duplication: Repeated setup or test code
- Magic Values: Hardcoded values without context
- Unclear Intent: Tests that are hard to understand
- Flakiness: Tests with timing issues or randomness
- Commented Code: Disabled or commented tests
Mock/Stub Quality
- Proper Isolation: Are dependencies properly mocked?
- Realistic Mocks: Do mocks represent real behavior?
- Mock Verification: Are mock calls verified?
- Mock Cleanup: Are mocks reset between tests?
Step 3: Identify Specific Issues
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.
- 5d ago First seen · 652 lines · 15 tokens per session scan A 739cbe3ca215
improve-test-quality is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 3,831 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.
Other commands, from other repositories
octo-loop
Your first output line MUST be: 🐙 Octopus Loop Mode.
octo-debug
Debug a symptom through reproducible, bounded evidence.
cloudflare-workers:test-setup
Interactive Vitest setup wizard for Cloudflare Workers testing. Configures @cloudflare/vitest-pool-workers, mocks bindings, and creates example tests.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
verify
Verify a repository in fast or full mode with runner-first execution, deterministic stage order, and explicit PASS/FAIL/SKIP output.