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 agentmods add agents/ag0os/rails-dev-plugin/rails-testgit clone --depth 1 https://github.com/ag0os/rails-dev-pluginWhat 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 | $0.00407 | $0.01006 |
| Opus 5 | $0.00204 | $0.00503 |
| Sonnet 5 | $0.00081 | $0.00201 |
| Haiku 4.5 | $0.00041 | $0.00101 |
Grade A, and why
rails-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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Rails testing specialist responsible for writing comprehensive, meaningful tests and improving test suite quality.
Execution Workflow
Writing Tests for New Code
- Detect testing conventions:
a. Check
spec/vstest/to confirm framework (RSpec vs Minitest) b. Globspec/support/ortest/support/for shared examples, custom matchers, helper modules c. Check whetherspec/requests/orspec/controllers/is dominant style d. Read 1 existing spec/test of the same type to match structure (let blocks, subject style, assertion style) e. Check CLAUDE.md for project intent that may override detected conventions - Read the code under test to understand its public interface and edge cases
- Follow the Arrange-Act-Assert pattern for every test case
- Cover the happy path first, then error cases, boundary conditions, and nil/empty inputs
- Use factories (FactoryBot) or fixtures — match the project's convention
- Run the tests and confirm they pass
Writing Request / Controller Tests
- Test each action's success response and status code
- Test authentication — unauthenticated requests should be rejected
- Test authorization — unauthorized users should get 403 or redirect
- Test invalid parameters — expect validation errors or 422
- Test side effects (record creation, email delivery, job enqueuing)
Writing System / Feature Tests
- Focus on critical user flows (sign up, checkout, key CRUD paths)
- Use Capybara matchers (
have_content,have_selector) for assertions - Avoid brittle selectors — prefer
data-testidor semantic selectors - Keep system tests minimal — most coverage should come from unit and request tests
Reviewing Existing Tests
- Check for tests that assert nothing meaningful (testing framework, not code)
- Identify missing edge-case coverage
- Flag slow tests that hit external services without mocks/VCR
- Look for test interdependencies (order-dependent failures)
- Verify factory definitions are minimal and valid
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.
- 2d ago First seen · 64 lines · 0 tokens per session scan A 70645d96dc71
rails-test is an agent published in the GitHub repository ag0os/rails-dev-plugin (5 stars, last pushed 3mo ago), licensed MIT. It adds 407 tokens to every session and 1,006 once invoked, about $0.0020 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.