Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/igmarin/rails-agent-skillsnpx agentmods add skills/igmarin/rails-agent-skills/test-engineWrote 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/igmarin/rails-agent-skills/test-engine)<a href="https://agentmods.dev/skills/igmarin/rails-agent-skills/test-engine"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/test-engine.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00838 |
| Opus 5 | $0.00014 | $0.00419 |
| Sonnet 5 | $0.00005 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
test-engine 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Engine
HARD-GATE
EVERY engine MUST have a dummy app for testing.
If it doesn't exist, generate it:
cd my_engine && bundle exec rails plugin new . --dummy-path=spec/dummy --skip-git
Validate the dummy app boots before proceeding:
cd spec/dummy && bundle exec rails runner "puts 'Boot OK'"
If this fails, check the engine's `engine.rb` initializer order and ensure the engine is correctly mounted in `spec/dummy/config/routes.rb` before writing any specs.
Core Process
- Identify the engine type and public behaviors.
- Add the smallest integration test that proves mounting and boot work. Verify it passes before continuing — if it fails, check
engine.rbinitializer order and mount configuration. - Add request, routing, configuration, and generator coverage as needed.
- Add regression tests for coupling bugs before refactoring.
- Run the full test suite (
bundle exec rspec) to verify all specs pass.
Minimal request spec to prove the engine mounts:
# spec/requests/my_engine/root_spec.rb
require 'rails_helper'
RSpec.describe 'MyEngine mount', type: :request do
it 'returns ok for the engine root' do
get my_engine.root_path
expect(response).to have_http_status(:ok)
end
end
Configuration spec (engine respects host config):
# spec/my_engine/configuration_spec.rb
RSpec.describe MyEngine::Configuration do
around do |example|
original = MyEngine.config.widget_count
MyEngine.config.widget_count = 3
example.run
MyEngine.config.widget_count = original
end
it 'uses configured value' do
expect(MyEngine.config.widget_count).to eq(3)
end
end
Advanced Coverage Patterns
Namespace-scoped routing spec:
# spec/routing/my_engine/widgets_routing_spec.rb
require 'rails_helper'
RSpec.describe MyEngine::WidgetsController, type: :routing do
routes { MyEngine::Engine.routes }
it 'routes GET /widgets to widgets#index' do
expect(get: '/widgets').to route_to('my_engine/widgets#index')
end
end
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 128 lines · 27 tokens per session scan A e52a1d447df5
test-engine is a skill published in the GitHub repository igmarin/rails-agent-skills (24 stars, last pushed 17d ago), licensed MIT. It adds 27 tokens to every session and 838 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…