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/Cratis/AInpx agentmods add skills/cratis/ai/cratis-application-react-specificationsWrote 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-application-react-specifications)<a href="https://agentmods.dev/skills/cratis/ai/cratis-application-react-specifications"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-application-react-specifications.svg" alt="Measured on agentmods" 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 | $0.01784 |
| Opus 5 | $0.00044 | $0.00892 |
| Sonnet 5 | $0.00018 | $0.00357 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
cratis-application-react-specifications 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 today.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cratis application React specifications
Frontend specifications are specifications, not tests. The for_ / when_ / and_
shape is deliberately the same BDD language as the backend, so one subject, one
context, clear setup, and small assertions read as sentences.
This is the application frontend peer of the backend slice specification
skill. Specifications for a Cratis framework package (@cratis/*) follow that
repository's own TypeScript specification conventions instead.
Stack
- Vitest for the runner, with Mocha-style
describe/beforeEach/it. - Sinon for stubs and fakes (
sinon.stub(),sinon.createStubInstance()). - Chai with the
.shouldfluent interface — neverexpect().result.should.equal(expected)reads as a sentence.
Placement and naming
Specifications live next to the unit they specify, in snake_case so the path reads as a scenario sentence:
<Slice>/
<Subject>.ts
for_<Subject>/
when_<context>/
and_<extra_context>.ts
| Shape | Use for |
|---|---|
for_<Subject>/when_<context>/and_<extra>.ts |
the default — view models, branching helpers, component specs |
for_<Subject>/when_<context>.ts |
a tiny pure helper with no useful extra context |
describe('when ...') names the scenario, not the class. it('should ...')
uses spaces, not underscores, and asserts one observable outcome. Do not add
.test.ts or .spec.ts files unless the project's configuration changes
deliberately.
What to specify
Behavior that can regress without TypeScript catching it:
- View models — the primary target. State transitions, computed getters, filtering, sorting, selection, wizard steps, validation state, and command-value derivation.
- Command orchestration outside a command dialog — the unauthorized, invalid, exception, and success branches.
- Pure helpers — parsing, formatting, grouping, boundary cases.
- Component rendering only when the markup, a disabled state, or wrapper behavior is genuinely the point.
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.
- today First seen · 193 lines · 89 tokens per session scan A 208144f172d6
cratis-application-react-specifications 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 1,784 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 2026-09-06.
Other skills, from other repositories
angular-testing
Write Angular component tests using TestBed, ComponentHarness, and HttpTestingController with proper signal input handling. Use when writing component tests, mocking HTTP calls, or testing signal inputs.
appbuilder-testing
Generate and run tests for Adobe App Builder actions and UI components. Scaffolds Jest unit tests, integration tests against deployed actions, contract tests for Adobe API interactions, and React component tests using Testing Library. Provides mock helpers for State, Files, Events SDKs, @adobe/aio-lib- clients, ExC…
sfnext-testing
Write tests for Storefront Next using Vitest unit tests, Storybook stories, interaction tests, snapshot tests, and accessibility tests. Use when writing component tests, creating Storybook stories, running test coverage, or setting up test utilities. Covers testing-library patterns, play functions, and coverage…
testing
Skill "testing" from udecode/plate-playground-template, covering testing goal, core rules, seam selection, fixtures and assertions and quick reference.
react-testing-library
React Testing Library best practices for writing maintainable, user-centric tests. Use when writing, reviewing, or refactoring RTL tests. Triggers on test files, testing patterns, getBy/queryBy queries, userEvent, waitFor, and component testing.
react-vitest
Use when adding or improving tests in a React project that uses Vitest — covers component testing with Testing Library, mocking hooks, and coverage configuration.