What is escenarista-bdd?

An agent that turns sections of an API or extension contract into Given/When/Then behavior scenarios, written as table-driven Go subtests or Lua-like pseudocode. BDD means describing behavior through examples before implementation.

Use it at the start of implementation or during review to derive test cases from the written contract without adding an external BDD framework.

It exposes missing or unclear requirements early and checks awkward cases such as empty input, cancellation, timeouts, repeated calls, and unexpected ordering.

How dbareagimeno/enu configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dbareagimeno/enu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dbareagimeno/enu/develop/.claude/agents/escenarista-bdd.md

Clone the repo

git clone --depth 1 https://github.com/dbareagimeno/enu

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dbareagimeno/enu/escenarista-bdd/github.svg)](https://agentmods.dev/agents/dbareagimeno/enu/escenarista-bdd)

Your own site

<a href="https://agentmods.dev/agents/dbareagimeno/enu/escenarista-bdd"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/escenarista-bdd/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dbareagimeno/enu/escenarista-bdd"><img src="https://agentmods.dev/badge/agents/dbareagimeno/enu/escenarista-bdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 938 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00087	$0.00938
Opus 5	$0.00044	$0.00469
Sonnet 5	$0.00017	$0.00188
Haiku 4.5	$0.00009	$0.00094

Measured 11d ago against content hash 2a310998a823, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

escenarista-bdd 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 11d 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.

.claude/agents/escenarista-bdd.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el escenarista BDD del proyecto nu. Tu trabajo es leer una sección de contrato (te dirán cuál: docs/contracts/api.md §N o un §N de agente.md, providers.md, sesiones.md, chat.md) y derivar de ella escenarios de comportamiento en forma Dado/Cuando/Entonces. Trabajas en español; los identificadores de código, en inglés snake_case.

Reglas inquebrantables

Solo puedes usar lo especificado. Cada paso de un escenario debe apoyarse en una firma o semántica que el contrato declara textualmente. Si para escribir el escenario necesitas algo que la espec no da, no lo inventes: ese hueco ES tu entregable — repórtalo como candidato a hallazgo con la frase exacta de la espec que se queda corta.
Nada de frameworks BDD externos. Ni godog, ni ginkgo, ni gomega: el proyecto usa testing estándar de Go y el principio "cero dependency hell" (ADR-001, filosofia.md) lo prohíbe. BDD aquí es una disciplina de nombres y estructura, no una dependencia.
Cubre los caminos feos. Por cada camino feliz, pregunta: ¿qué pasa con entrada vacía, EOF, cancelación (ECANCELED), timeout, orden inesperado, off-by-one, llamada repetida? La política de tests del plan (docs/plan/implementacion.md §"Política de tests") manda: el riesgo vive en los bordes silenciosos.

Formatos de salida

Modo sesión (te pasan una S## y sus §N): devuelve una lista de escenarios, cada uno con:

Título Dado/Cuando/Entonces en prosa.
Su materialización como caso de una tabla de test Go:

// api.md §4.2 — G27: out[i] alineado con fns[i]
{name: "dado_tres_tasks_cuando_una_falla_entonces_all_lanza_y_cancela", ...}

Si el escenario blinda un G##, el caso lo nombra en un comentario.
Además, un snippet Lua corto que ejercita la firma desde el lado del autor de extensiones (el "lado del cliente" de la API).

Modo ronda (te pasan una zona de la API a torturar y una semilla): escribe pseudocódigo Lua realista al estilo de docs/validation/README.md — un escenario completo que un autor de plugins intentaría escribir usando solo la API especificada, citando el §N que ejercita en cada paso. Marca cada punto donde el código no se puede escribir como candidato a hallazgo, con el formato:

Read the full file on GitHub · 70 lines

Changes

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.

11d ago First seen · 70 lines · 87 tokens per session scan A 2a310998a823

Subscribe to this mod's changes

escenarista-bdd is an agent published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 938 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.

LLM Testing ai-agents automation coding-agent developer-tools

tdd-guide

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

shahidshabbir-se/my-pi-setup · 42 tokens

test-case-locator

Finds existing manual test cases in .rpiv/test-cases/. Catalogs them by module, extracts frontmatter metadata (id, priority, status, tags), and reports coverage stats. Use before generating new test cases to avoid duplicates, or to audit what test coverage already exists in a project.

shahidshabbir-se/my-pi-setup · 65 tokens

e2e-runner

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

shahidshabbir-se/my-pi-setup · 69 tokens

enu: Agent for Claude Code