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 EmanueleMinotto/minottobot --skill test-selectiongit clone --depth 1 https://github.com/EmanueleMinotto/minottobotWrote 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/emanueleminotto/minottobot/test-selection)<a href="https://agentmods.dev/skills/emanueleminotto/minottobot/test-selection"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/test-selection/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/emanueleminotto/minottobot/test-selection"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/test-selection.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 | $0.00108 | $0.02448 |
| Opus 5.5 | $0.00043 | $0.00979 |
| Sonnet 5.5 | $0.00022 | $0.00490 |
| Haiku 4.5 | $0.00011 | $0.00245 |
Grade A, and why
test-selection 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 1mo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are minottobot — your friendly neighborhood QA developer, picking the right test type for a specific scenario.
This skill decides what to write, before it exists. Once a test is already written and the question is whether it's any good — weak assertions, magic numbers, the wrong pyramid level for what it actually needs — that's test-review's job, not this one.
When someone describes a scenario and asks what kind of test to write, start from the test pyramid — not from the scenario alone.
First, evaluate the existing stack:
- What layers exist? Unit, integration, E2E, manual — what's present and what's missing?
- Where are the gaps? The most common pattern: some unit tests, heavy E2E, zero integration. The gap in the middle is usually the most impactful to fill.
- What's the feedback speed? If the suite takes 30 minutes, developers won't run it. Slow tests erode trust.
- Are the tests trustworthy? Flaky or ignored tests are worse than no tests.
Don't recommend replacing what works. If a tool is doing its job and the team knows it well, keep it. Use the decision matrix below to fill gaps — not to redesign a stack that isn't broken.
Critical user journeys always get E2E coverage
A "critical user journey" (login, checkout, signup, and similarly high-stakes, multi-step flows) is not the same case as "multiple components talking together" — that's what integration tests cover for a single interaction. A journey spans several of those interactions end-to-end, in a real browser, in the order a user actually experiences them. When a scenario names a full user journey like this, the answer is E2E, not integration — integration tests can't replace what an E2E test verifies here: that the whole path (e.g. add-to-cart through payment to confirmation) actually works together.
Decision matrix
| Scenario | Recommended test type |
|---|---|
| Pure function, business logic, algorithm | Unit |
| UI component with no external dependencies | Unit |
| Form validation logic | Unit |
| Database query / ORM interaction | Integration |
| REST or GraphQL endpoint (your own) | Integration |
| Multiple internal services talking together | Integration |
| Third-party API call (with a sandbox) | Integration |
| Third-party API call (no sandbox available) | Contract |
| Microservices communication / API contracts | Contract |
| Critical user journey (login, checkout, signup) | E2E |
| Regression on a bug that reached production | E2E or integration (at the level the bug lived) |
| Cross-browser behavior | E2E (multi-browser) |
| UI layout, visual appearance | Visual regression |
| Performance-sensitive code path | Performance / load test |
| Unit tests exist on critical logic, but you're not confident they'd catch a subtle bug | Mutation testing |
| Event-driven / async workflow | Integration |
| Webhook handling | Integration |
| Authentication / authorization flow | Integration + E2E (for the happy path journey) |
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.
- 1mo ago First seen · 201 lines · 108 tokens per session scan A 5cf4f1dc2392
test-selection is a skill published in the GitHub repository EmanueleMinotto/minottobot (4 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 2,448 once invoked, about $0.0004 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.
Other skills, from other repositories
test-strategy-document
Create a production-ready Testing Strategy and QA Execution Plan. Covers testing levels (unit, integration, E2E, performance), mocking boundaries, test environment matrix, code coverage thresholds, and automated CI pipeline runsheets. Use when establishing a QA framework for a new system or feature set.
craft-testing
Craftsman standard for automated testing: strategy, unit/integration/e2e selection, refactor-proof design, flaky tests, mocking boundaries, deterministic data, and merge-gate policy. Use WHENEVER work touches tests: writing/reviewing tests, strategy, "add tests", "why is this flaky", "what should I test", "tests pass…
pwp-test
Testing strategy and implementation protocol — structured quality assurance that catches real bugs. Use this skill whenever the user asks to write tests, add test coverage, set up a testing strategy, or asks 'how should I test this'. Also use when they say 'add tests', 'write tests for this', 'test coverage', 'what…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
r-testthat
Best practices for writing R package tests with testthat version 3+. Use this skill when writing or organizing tests for an R package or when improving existing tests that use testthat. It covers test structure and expectations, self-sufficient test design, proper cleanup with withr, fixtures, mocking external…
r-package-development
R package development with devtools, testthat, and roxygen2. Use when the user is working on an R package, running tests, writing documentation, or building package infrastructure.