setup-ci

A setup tool for configuring continuous integration and delivery (automated checks and release steps) in an ar-plugins repository.

In plain words
What is it for?
Use it to add GitHub workflows, configure commitlint and conventional commits, check version updates, and protect the master branch.
Why use it?
It adds consistent commit checks, version-bump checks where supported, and rules requiring pull requests and passing checks before changes reach the master branch.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kvothesson/ar-plugins/setup-ci
Any agent
npx skills add kvothesson/ar-plugins --skill setup-ci
Clone the repo
git clone --depth 1 https://github.com/kvothesson/ar-plugins

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.01849
Opus 5 $0.00022 $0.00924
Sonnet 5 $0.00009 $0.00370
Haiku 4.5 $0.00004 $0.00185

Measured 2d ago against content hash 7bc487582d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-ci 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.

skills/setup-ci/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /ar-plugins:setup-ci

Dado un repo plugin, agrega:

  • Workflow de conventional commits (commitlint)
  • Workflow de version bump (solo en repos con plugin.json)
  • .commitlintrc.json
  • Branch protection ruleset en master (PR obligatorio + checks requeridos)

Uso

/ar-plugins:setup-ci kvothesson/<nombre>

Si no se pasa repo, preguntar al usuario cuál quiere configurar.


Paso 1 — Verificar y obtener scope workflow

gh auth status 2>&1 | grep "Token scopes"

Si el output no contiene workflow, correrlo automáticamente:

gh auth refresh -s workflow

Este comando abre el browser para que el usuario apruebe el scope. Avisarle antes:

Necesito el scope `workflow` para crear los archivos en .github/workflows/.
Abriendo el browser para que lo apruebes — es un solo click en "Authorize".

Esperar a que el comando termine (el usuario aprueba en el browser y el CLI confirma). Luego verificar que el scope quedó:

gh auth status 2>&1 | grep "Token scopes"

Si sigue sin tener workflow, reportar el error y detener.


Paso 2 — Detectar tipo de repo

gh api repos/<owner>/<repo>/contents/.claude-plugin/plugin.json 2>&1 | grep -c '"content"'
  • Si retorna 1repo plugin → setup completo (version-bump + commitlint + ruleset)
  • Si retorna 0repo sin plugin.json → solo commitlint + ruleset (ej: ar-plugins)

Paso 3 — Clonar y crear branch

gh repo clone <owner>/<repo> /tmp/<repo>-setup-ci
cd /tmp/<repo>-setup-ci
git checkout -b ci/setup-ci

Paso 4 — Agregar archivos

.commitlintrc.json (siempre)

cat > /tmp/<repo>-setup-ci/.commitlintrc.json << 'EOF'
{
  "extends": ["@commitlint/config-conventional"],
  "rules": {
    "type-enum": [
      2,
      "always",
      ["feat", "fix", "chore", "docs", "refactor", "test", "ci"]
    ],
    "subject-case": [2, "never", ["start-case", "pascal-case", "upper-case"]],
    "header-max-length": [2, "always", 100]
  }
}
EOF

Read the full file on GitHub · 281 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.

  1. 2d ago First seen · 281 lines · 43 tokens per session scan A 7bc487582d5f

Subscribe to this mod's changes

setup-ci is a skill published in the GitHub repository kvothesson/ar-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,849 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

afip-constancia

Fetch the official ARCA (ex-AFIP) Constancia de Inscripción for an Argentine CUIT from the PUBLIC web form (no Clave Fiscal, no login). Returns the parsed fiscal situation — régimen (monotributo + categoría / responsable inscripto / exento), domicilio fiscal, actividades CLAE, impuestos, fecha de inscripción — AND the…

ar-agents/ar-agents · 228 tokens

eph

Diseño de registro y metodología de la Encuesta Permanente de Hogares (EPH) del INDEC. Lee automáticamente el archivo de diseño correcto y aplica orientación metodológica antes de generar scripts R o Python con microdatos EPH. Trigger: cuando el usuario pide un script R o Python para procesar microdatos de la EPH…

matias-denatale/eph-context · 104 tokens

correo-argentino

Integración de envíos con Correo Argentino (apiMiCorreo) para ecommerce. Cubre autenticación y alta de cliente (token Basic Auth + registro y obtención del customerId), cotización, sucursales, creación de envíos, tracking, sincronización por cron, mapeo de estados a la orden, y emails de "en camino"/"entregado".…

synerarg/claude-code-skills · 125 tokens

mercadopago

Skill UNICA y completa para todo Mercado Pago en aplicaciones web (Next.js, React, Vanilla JS). COBRAR: Checkout Pro (redireccion), Checkout Bricks (Payment, Card, Wallet, Status Screen), Orders API (nuevo modelo) y Suscripciones (preapproval / pagos recurrentes). ENVIAR dinero: Money Out (transferencias/retiros a…

synerarg/claude-code-skills · 457 tokens

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

ar-agents/ar-agents · 67 tokens

afip-arca

Implementar facturación electrónica de AFIP/ARCA (Argentina) de punta a punta desde código: obtener y asociar el certificado digital, autenticarse con el WSAA (TRA + CMS firmado + LoginCMS), y emitir comprobantes con WSFEv1 para conseguir el CAE. USAR SIEMPRE que el usuario mencione facturación electrónica, factura…

synerarg/claude-code-skills · 220 tokens