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 skills/fermonterom/claude-testing-kit/testing-kitnpx skills add fermonterom/claude-testing-kit --skill testing-kitgit clone --depth 1 https://github.com/fermonterom/claude-testing-kitWhat 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 | $0.00078 | $0.03867 |
| Opus 5 | $0.00039 | $0.01934 |
| Sonnet 5 | $0.00016 | $0.00773 |
| Haiku 4.5 | $0.00008 | $0.00387 |
Grade A, and why
testing-kit 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
testing-kit — TDD + Unit + E2E + Quality Gate para Next.js
Parte 1: TDD — Test First, Code Second
3 Reglas de Hierro
1. TEST FIRST, CODE SECOND — sin excepciones
2. NUNCA codigo de produccion sin un test que falle primero
3. CADA route.ts tiene route.test.ts, CADA page.tsx tiene .spec.ts
Ciclo RED → GREEN → REFACTOR
RED: Escribir UN test que describe UN comportamiento → ejecutar → DEBE FALLAR GREEN: Escribir el codigo MINIMO para que pase → ejecutar → DEBE PASAR REFACTOR: Limpiar sin romper tests → ejecutar → SIGUE PASANDO
Repetir. Un test a la vez. SIEMPRE vertical (test → codigo → green), NUNCA horizontal (todos los tests → luego todo el codigo).
Test List (antes de escribir codigo)
Listar todos los comportamientos a testear. Ejemplo para POST /api/users:
1. 201 — crea usuario con datos validos
2. 401 — rechaza sin autenticacion
3. 400 — rechaza campos requeridos vacios
4. 400 — rechaza email invalido
5. 404 — recurso padre no existe
6. 500 — maneja error de base de datos
Cada item = un ciclo RED → GREEN.
Parte 2: Unit Tests con Vitest
Template de 6 Casos (minimo obligatorio)
import { describe, it, expect, vi, beforeEach } from 'vitest'
// Mocks ANTES de los imports del codigo
const mockGetUser = vi.fn()
const mockFrom = vi.fn()
vi.mock('@/lib/supabase/server', () => ({
createClient: vi.fn(() => Promise.resolve({
auth: { getUser: mockGetUser },
from: mockFrom,
})),
}))
// Import del codigo a testear
import { POST } from './route'
const MOCK_USER = { id: 'user-123', email: '[email protected]' }
function createRequest(body?: unknown): Request {
return new Request('http://localhost/api/resource', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
...(body ? { body: JSON.stringify(body) } : {}),
})
}
beforeEach(() => { vi.clearAllMocks() })
describe('POST /api/resource', () => {
// CASO 1: Happy path (200/201)
it('returns 201 with created resource', async () => {
mockGetUser.mockResolvedValue({ data: { user: MOCK_USER } })
mockFrom.mockReturnValue({
insert: vi.fn().mockReturnThis(),
select: vi.fn().mockReturnThis(),
single: vi.fn().mockResolvedValue({ data: { id: '1', name: 'Test' }, error: null }),
})
const res = await POST(createRequest({ name: 'Test' }))
expect(res.status).toBe(201)
})
// CASO 2: Sin autenticacion (401)
it('returns 401 when not authenticated', async () => {
mockGetUser.mockResolvedValue({ data: { user: null } })
const res = await POST(createRequest({ name: 'Test' }))
expect(res.status).toBe(401)
})
// CASO 3: Input invalido (400)
it('returns 400 on invalid input', async () => {
mockGetUser.mockResolvedValue({ data: { user: MOCK_USER } })
const res = await POST(createRequest({})) // body vacio
expect(res.status).toBe(400)
})
// CASO 4: No encontrado (404)
it('returns 404 when resource not found', async () => {
mockGetUser.mockResolvedValue({ data: { user: MOCK_USER } })
mockFrom.mockReturnValue({
select: vi.fn().mockReturnThis(),
eq: vi.fn().mockReturnThis(),
single: vi.fn().mockResolvedValue({ data: null, error: null }),
})
const res = await POST(createRequest({ parentId: 'not-found' }))
expect(res.status).toBe(404)
})
// CASO 5: Error de BD (500)
it('returns 500 on database error', async () => {
mockGetUser.mockResolvedValue({ data: { user: MOCK_USER } })
mockFrom.mockReturnValue({
insert: vi.fn().mockReturnThis(),
select: vi.fn().mockReturnThis(),
single: vi.fn().mockResolvedValue({ data: null, error: { message: 'DB error' } }),
})
const res = await POST(createRequest({ name: 'Test' }))
expect(res.status).toBe(500)
// Verificar que NO expone el error interno
const body = await res.json()
expect(body.error).not.toContain('DB error')
})
// CASO 6: Extra (especifico del endpoint — SIEMPRE implementar, nunca dejar vacio)
it('returns 409 when duplicate name exists', async () => {
mockGetUser.mockResolvedValue({ data: { user: MOCK_USER } })
mockFrom.mockReturnValue({
insert: vi.fn().mockReturnThis(),
select: vi.fn().mockReturnThis(),
single: vi.fn().mockResolvedValue({
data: null,
error: { message: 'unique_violation', code: '23505' },
}),
})
const res = await POST(createRequest({ name: 'Duplicado' }))
expect(res.status).toBe(409)
})
})
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 · 485 lines · 78 tokens per session scan A 05fbd464c80f
testing-kit is a skill published in the GitHub repository fermonterom/claude-testing-kit (10 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 3,867 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.