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 Cratis/AI --skill cratis-specification-by-examplegit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-specification-by-example)<a href="https://agentmods.dev/skills/cratis/ai/cratis-specification-by-example"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-specification-by-example/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/cratis/ai/cratis-specification-by-example"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-specification-by-example.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 | $0.00089 | $0.02036 |
| Opus 5 | $0.00044 | $0.01018 |
| Sonnet 5 | $0.00018 | $0.00407 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
cratis-specification-by-example 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cratis specification by example
Cratis calls automated tests specifications. That is not a vocabulary preference — it changes what you write. A test asks "does this code still do what it did yesterday?". A specification states what the software promises, in the language of the domain, in a form a machine can check. The folder tree is the table of contents; the file names are the sentences; the assertions are the promises.
This skill is the language-agnostic layer. It settles the questions that are the same in C#, TypeScript, and anything else: what to specify, how to name it, where to put it, and when to stop.
Verified product sources
| Source | Version | What it grounds |
|---|---|---|
Cratis.Specifications analyzers |
CRSPEC0001–CRSPEC0007 |
The naming and structure rules below are machine-enforced in C#, not taste |
The seven diagnostics are declared in Cratis.Specifications.CodeAnalysis.DiagnosticIds:
| Id | Rule |
|---|---|
CRSPEC0001 |
A test method inside a specification must be named should_* |
CRSPEC0002 |
A file declares at most one specification |
CRSPEC0003 |
A test method must not sit on a reusable given/ context |
CRSPEC0004 |
A should_* method without a test attribute never runs |
CRSPEC0005 |
A lifecycle method must not call its base implementation |
CRSPEC0006 |
A specification declaring test methods must be public so the runner finds it |
CRSPEC0007 |
The action under test must not sit on a reusable given/ context |
In a language without those analyzers the same rules hold; the reviewer enforces them instead of the compiler. Reverify against the owning product repository before claiming behavior for another version.
Route near misses
- Writing the C# mechanics — the
Specificationbase,Establish/Because, substitutes, assertions: usecratis-specifications-csharp. - Writing the TypeScript mechanics —
describe/it, Sinon, the Chaishouldinterface: usecratis-specifications-typescript. - Specifying an event-sourced application slice with the in-process scenario
family: use
cratis-application-slice-specifications. - Deciding what a command, projection, reducer, or reactor should do: that is a modeling question. Settle the behavior first; a specification records a decision, it does not make one.
What ships with it
1 file 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.
- yesterday First seen · 189 lines · 89 tokens per session scan A d1da304d4923
cratis-specification-by-example is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,036 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
Event Sourcing Testing
Testing event sourcing patterns including event store validation, projection testing, saga orchestration, and event versioning compatibility.
author-test
Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.
crap-score
Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities…
nunit
Write, run, or repair .NET tests that use NUnit. Use when a repo uses NUnit, [Test], [TestCase], [TestFixture], or NUnit3TestAdapter for VSTest or Microsoft.Testing.Platform execution. USE FOR: writing or reviewing NUnit tests; using [Test], [TestCase], [TestFixture], [SetUp], [TearDown] attributes; configuring…
coverlet
Use the open-source free coverlet toolchain for .NET code coverage. Use when a repo needs line and branch coverage, collector versus MSBuild driver selection, or CI-safe coverage commands. USE FOR: coverlet setup; CI line or branch coverage; choosing between collector and MSBuild drivers. DO NOT USE FOR: coverage…
archunitnet
Use the open-source free ArchUnitNET library for architecture rules in .NET tests. Use when a repo needs richer architecture assertions than lightweight fluent rule libraries usually provide. USE FOR: the repo uses or wants ArchUnitNET; architecture testing needs richer modeling than simple dependency checks. DO NOT…