agentmods.dev

ajustes

ajustes is a command for coding agents from 686f6c61/alfred-dev. It costs 23 tokens per session (1,860 once invoked), scanned A, original, MIT.

A configuration command for Alfred Dev. It loads or creates the project’s local settings, detects the technology stack, and prepares the sections used by the assistant.

In plain words
What is it for?
Use it when setting up or updating Alfred Dev for a project. It helps configure autonomy, project details, Lucius, memory, and the assistant’s behavior.
Why use it?
It keeps project settings in one canonical file and normalizes older setting names when needed. Its headless mode also prepares a usable menu for automated sessions.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the alfred-dev plugin — 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server shipped together

not rated 119 19d ago A scan 23 tokens original MIT
View the source file 686f6c61/alfred-dev
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 commands/686f6c61/alfred-dev/ajustes
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev

Or install alfred-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server.

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.

agentmods badge for ajustes

README.md
[![agentmods](https://agentmods.dev/badge/commands/686f6c61/alfred-dev/ajustes.svg)](https://agentmods.dev/commands/686f6c61/alfred-dev/ajustes)
Your own site
<a href="https://agentmods.dev/commands/686f6c61/alfred-dev/ajustes"><img src="https://agentmods.dev/badge/commands/686f6c61/alfred-dev/ajustes.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,860 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 $0.00023 $0.01860
Opus 5 $0.00012 $0.00930
Sonnet 5 $0.00005 $0.00372
Haiku 4.5 $0.00002 $0.00186

Measured 4d ago against content hash 2f099bb74893, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ajustes 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 4d 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.

commands/ajustes.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/alfred-dev:ajustes

Lee el fichero .claude/alfred-dev.local.md si existe. Si no existe, créalo con la configuración canónica actual del plugin.

Escribe siempre la clave canónica autonomia en el frontmatter, aunque encuentres variantes legacy como autonomía. El runtime las entiende por retrocompatibilidad, pero la escritura nueva debe quedar normalizada.

Paso 0: helper determinista

Antes de razonar o preguntar, ejecuta este Bash inmediatamente para cargar o crear la configuración, detectar stack, construir las 7 secciones y generar el menú canónico:

python3 "${CLAUDE_PLUGIN_ROOT}/core/config_cli.py" "$PWD" --headless

Conserva ese stdout como CONFIG_SUMMARY. Si el comando falla porque CLAUDE_PLUGIN_ROOT no existe en desarrollo local, reintenta una sola vez con python3 core/config_cli.py "$PWD" --headless solo si estás en el repo del plugin. En modo headless, CONFIG_SUMMARY debe contener el marcador literal CONFIG_HEADLESS_MENU.

Modo no interactivo / claude -p

Si esta invocación se está ejecutando en modo no interactivo/headless (claude -p, SDK sin callback canUseTool, auditoría automatizada o cualquier contexto donde no puedas recibir una selección del usuario en esta misma llamada), no llames AskUserQuestion. En ese modo:

  1. devuelve CONFIG_SUMMARY tal cual, sin reescribirlo con otra tabla;
  2. no abras submenús;
  3. no termines con una pregunta abierta.

No esperes indefinidamente una respuesta humana en modo headless y no abras los submenús de agentes opcionales ni memoria sin una selección real del usuario. Si llamas a AskUserQuestion y la herramienta vuelve cancelada, sin selección, sin respuesta utilizable o con cualquier señal de que el usuario no pudo elegir, trátalo igual que modo headless: devuelve CONFIG_SUMMARY tal cual. No conviertas esa cancelación en una pregunta abierta tipo "¿sobre qué sección actúo?".

Presenta al usuario la configuración actual organizada en secciones:

  1. Autonomía por fase (interactivo / semi-autonomo / autonomo): producto, arquitectura, desarrollo, calidad, documentacion, entrega
  2. Proyecto (detectado o manual): runtime, lenguaje, framework, ORM, test runner, bundler
  3. Agentes opcionales: solo Lucius
  4. Memoria persistente: enabled, sync_to_native, sync_commits_limit, capture_decisions, capture_commits, retention_days
  5. Compliance: estilo, lint, format_on_save
  6. Integraciones: git, ci, deploy
  7. Personalidad: nivel_sarcasmo (1-5), verbosidad, idioma, celebrar_victorias, insultar_malas_practicas

Read the full file on GitHub · 166 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. 4d ago First seen · 166 lines · 23 tokens per session scan A 2f099bb74893

Subscribe to this mod's changes

ajustes is a command published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 1,860 once invoked, about $0.0001 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 2026-08-30.

ai-agentsautomationclaude-codeclaude-code-pluginsdlc
Related

Other commands, from other repositories

e2e-test

Generate end-to-end tests using Playwright (web) and Detox (mobile). Covers user flows, visual regression, and cross-browser testing. Usage: /e2e-test [flow-name|--all] [--visual].

alphaaiservice/cortex · 46 tokens

gen-brand

Generate complete brand identity with SVG logos, color system, typography, and design tokens. Claude writes SVG code directly — no API key needed. Usage: /gen-brand 'ProductName — description' or /gen-brand ./PRD.md.

alphaaiservice/cortex · 47 tokens

init-project

Initialize a new or upgrade existing project with Alpha AI's standard architecture. Supports Python/FastAPI, Node.js/NestJS, Java/Spring Boot. Usage: /init-project [--lang=python|nestjs|springboot] [--with-frontend] [--with-mobile] [--with-ai] [--existing].

alphaaiservice/cortex · 71 tokens

accessibility

Audit frontend for WCAG 2.1 AA compliance: check semantic HTML, ARIA labels, color contrast, keyboard navigation, screen reader support. Usage: /accessibility [page-or-component] [--fix] [--level=AA|AAA].

alphaaiservice/cortex · 52 tokens

gen-ci

Generate CI/CD pipelines for GitHub Actions, GitLab CI, or Bitbucket Pipelines. Auto-detects stack from project. Usage: /gen-ci [github-actions|gitlab-ci|bitbucket] [--full].

alphaaiservice/cortex · 47 tokens

gen-prd

Generate a detailed PRD from a brief idea, pre-configured for Alpha AI's tech stack. Supports Python/FastAPI, Node.js/NestJS, Java/Spring Boot backends. Usage: /gen-prd 'brief product idea' [--lang=python|nestjs|springboot].

alphaaiservice/cortex · 61 tokens