A structured exercise for testing an API design by writing pseudocode against its documented contracts. API means the rules that define how software components can be used; each place where the pseudocode cannot be written becomes a finding.

Use it to examine a particular API area, contract combination, plugin author type, or stressful situation such as mass cancellation or overloaded workers.

It exposes missing or unclear parts of an API before the design is finalized. Several scenarios are tested in parallel, and proposed findings are checked to avoid inventing problems.

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/skills/ronda/SKILL.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/skills/dbareagimeno/enu/ronda/github.svg)](https://agentmods.dev/skills/dbareagimeno/enu/ronda)

Your own site

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

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 913 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	$0.00089	$0.00913
Opus 5	$0.00044	$0.00456
Sonnet 5	$0.00018	$0.00183
Haiku 4.5	$0.00009	$0.00091

Measured 11d ago against content hash ff0dfb3509c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ronda 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/skills/ronda/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ronda de pseudocódigo (torturar la API)

La API se valida escribiendo pseudocódigo contra ella: escenarios reales usando solo lo especificado en los contratos. Cada punto donde el código no se puede escribir es un hallazgo. Esta skill paraleliza el ejercicio y le añade el filtro que evita su modo de fallo clásico: inventar API para tapar lo que ya se componía.

Pasos

Elegir la zona. Lee el índice de rondas previas en docs/validation/README.md (y el estado de docs/findings/README.md) para ver qué zonas ya fueron torturadas (caminos feos, orquestación por un tercero...). Propón al usuario la zona y el ángulo de esta ronda: una extensión concreta, una combinación de primitivas, un tipo de autor de plugin (novato, hostil, con prisa), un régimen (cancelación masiva, reload en caliente, worker saturado).
Fan-out. Lanza en paralelo N agentes escenarista-bdd en modo ronda (N = 3-5 según amplitud de la zona), cada uno con una semilla distinta: un escenario-objetivo concreto y diferente que intentar escribir. Las semillas deben forzar caminos distintos (no tres variantes del mismo happy path). Cada escenarista devuelve su pseudocódigo con los §N citados y sus candidatos a hallazgo.
Consolidar. Reúne los candidatos y deduplica (dos escenaristas suelen chocar con la misma grieta por caminos distintos — eso es señal de que es real, consérvala como evidencia).
Verificación adversarial. Por cada candidato, lanza un verificador fresco (solo el candidato + la espec; nunca el razonamiento del escenarista). Su mandato: demostrar que el escenario ya es expresable componiendo la API existente.
Triaje con el usuario, candidato a candidato:
- REAL y la v1 lo necesita → G## vía /hallazgo.
- REAL pero puede esperar → P## en docs/postponed/ (un fichero pNN-<slug>.md), siempre con su disparador (la señal concreta que indica reabrirlo).
- FALSO POSITIVO → demostrado-expresable: la composición del verificador se documenta en la ronda (es tan valiosa como un hallazgo: enseña el patrón).

Read the full file on GitHub · 60 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 · 60 lines · 89 tokens per session scan A ff0dfb3509c9

Subscribe to this mod's changes

ronda is a skill published in the GitHub repository dbareagimeno/enu (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 913 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

colony-dogfood

Conduz um experimento de dogfood onde a colônia Pi executa uma task do .project/tasks.json em dois tempos (research → código) com gates do operador. Use quando o operador quiser ativar um experimento colony-experiment-phase1 ou colony-experiment-phase2.

aretw0/agents-lab · 64 tokens

create-pi-web-extension

Como criar/extender extensões web no pi com arquitetura determinística, segurança mínima e testes automatizados (smoke + e2e via pi-test-harness).

aretw0/agents-lab · 39 tokens

test-pi-extension

Como testar extensões pi com @marcfargas/pi-test-harness. Use quando o usuário quiser testar uma extensão, criar testes automatizados, ou validar que um pacote pi funciona após publish.

aretw0/agents-lab · 44 tokens

taiyi-dev

A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.

Dong90/oh-my-taiyiforge · 21 tokens

taiyi-test

A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.

Dong90/oh-my-taiyiforge · 24 tokens

codex-claude-worker

Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…

zhuzai-2007/claude-code-mcp-harness · 86 tokens

enu: Skill for Claude Code