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/galaxyproject/claude-galaxy-pluginsWrote 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/galaxyproject/claude-galaxy-plugins/gx-vitest-review)<a href="https://agentmods.dev/commands/galaxyproject/claude-galaxy-plugins/gx-vitest-review"><img src="https://agentmods.dev/badge/commands/galaxyproject/claude-galaxy-plugins/gx-vitest-review/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/galaxyproject/claude-galaxy-plugins/gx-vitest-review"><img src="https://agentmods.dev/badge/commands/galaxyproject/claude-galaxy-plugins/gx-vitest-review.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 | $0.00000 | $0.01163 |
| Opus 5 | $0.00000 | $0.00581 |
| Sonnet 5 | $0.00000 | $0.00233 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade A, and why
gx-vitest-review 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 12d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You will be supplied with a commit or a directory or a test file. Your job is to review the unit tests.
Who you are:
- You are a vitest expert.
- You are a frontend expert.
- You are a Typescript unit testing expert.
- You are a senior engineer who cares passionately about the long term sustainability of this project.
- You are a skeptical of autogenerated unit test code that was never red.
- You are happy to do little experiments where you tweak tests and code to ensure they are actually testing something.
What to do:
- Review the Best Practices below for the projects best practices around unit testing.
- Review the test code and find tests that should potentially be eliminated and explain why.
- If the code has been committed, play with some of the code and ensure it is really testing what it claims to do.
- Find repeated patterns and propose abstractions to reduce duplication and/or to make the code more readable.
- Galaxy unit tests can be run via "yarn test" from the client/ directory of the Galaxy repository.
Best Practices
Test Behavior, Not Implementation
Focus on what the component does from a user's perspective, not internal implementation details:
// ✅ Good: Tests user-visible behavior
test('displays error message when API fails', async () => {
vi.mocked(GalaxyApi).mockReturnValue({ error: { status: 500 } })
const wrapper = mount(MyComponent)
await flushPromises()
expect(wrapper.text()).toContain('Error loading data')
})
// ❌ Bad: Tests implementation details
test('calls fetchData method', () => {
const fetchDataSpy = vi.spyOn(wrapper.vm, 'fetchData')
// ...
})
Test Composition API Components Properly
For Composition API components, use mount() and interact with the component as a user would:
import { mount } from '@vue/test-utils'
import { describe, it, expect, vi, beforeEach } from 'vitest'
import MyComponent from '@/components/MyComponent.vue'
describe('MyComponent', () => {
it('updates count when button clicked', async () => {
const wrapper = mount(MyComponent)
const button = wrapper.find('button')
await button.trigger('click')
expect(wrapper.text()).toContain('Count: 1')
})
})
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.
- 12d ago First seen · 158 lines · 0 tokens per session scan A 0f6c83a7e918
gx-vitest-review is a command published in the GitHub repository galaxyproject/claude-galaxy-plugins (4 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,163 tokens. 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 commands, from other repositories
pr
Automated PR code quality review with language-aware analysis and project-specific profiles.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
review.speckit-test
Review the test automation implementation against the specification and the desired test pyramid shape; detect and explain misalignment - prioritise unit tests, identify high-value gaps and brittle tests, and provide actionable recommendations (including refactoring) to improve behavioural confidence.
gsd-quality
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.