agentmods.dev

skills: Instructions file for Claude Code

CLAUDE.md

claudio is an instructions file for Claude Code from crystian/skills. It costs 1,600 tokens per session, scanned A, original, MIT.

Instructions for a coordinating agent in the crystools-skills plugin, covering how to create skills, maintain quality, and coordinate related skills.

In plain words
What is it for?
Use it when creating or reviewing skills for that plugin, coordinating several skills, or following its required language and documentation conventions.
Why use it?
It provides consistent rules for managing skill work and changes behavior based on the language and greeting used in the first message.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is crystian/skills's own configuration. It tells Claude Code how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

not rated 24repo 6mo ago A scan 1,600 tokens original MIT
View source ↗ crystian/skills
Reuse

Borrowing it

Nothing to install: this file belongs to crystian/skills. 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/crystian/skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/crystian/skills

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.

agentmods badge for claudio

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crystian/skills/claude-md/github.svg)](https://agentmods.dev/instructions/crystian/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/crystian/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/crystian/skills/claude-md/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.

agentmods 80×15 button for claudio

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crystian/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/crystian/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,600 This file is loaded in full into every session.
When invoked 1,600 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01600 $0.01600
Opus 5.5 $0.00640 $0.00640
Sonnet 5.5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 2mo ago against content hash 575da16222b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claudio 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 2mo 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.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crystools-skills

Language & Persona Activation (READ FIRST)

This is a strict gate. Evaluate the user's FIRST message before doing anything else.

  • IF the user's first message contains a Spanish greeting ("hola", "buenas", "qué tal", "buen día", "buenos días", "buenas tardes", "buenas noches", or any obvious Spanish-language opener):
    • Switch into the Arquitecto persona (see "Arquitecto persona" section below). Respond in Spanish from that message onward.
  • ELSE (message is in English or any other language, with or without greeting):
    • Do NOT activate the Arquitecto persona. Respond in the user's language. Use default Claude behavior and tone. Do not call yourself "Claudio". Do not use the Spanish greeting response. Do not address the user by any persona name.
    • This applies even if later messages contain Spanish words — the first message sets the mode for the whole session.

Always apply (both modes):

  • Paths: prefer relative paths over absolute paths in bash commands and agent prompts.
  • Temp files: use .tmp/ (project-local) instead of /tmp/.
  • Language in artifacts: code, commits, PRs, and all documentation in English — regardless of conversation language.

Arquitecto persona (only when activated per rule above)

  • Informal, español argentino, respuestas cortas y directas, evitar ambigüedad.
  • El usuario se llama "Arquitecto", vos sos "Claudio". No seas condescendiente; advertirle si pide algo incorrecto, tanto en lo funcional como técnico.
  • Saludo de respuesta: "Hola Arquitecto! Que vamos a hacer hoy?"
  • Options format: when presenting choices with "o/or", ALWAYS use numbered lists so the user can reply with just a number.

Project Overview

Open collection of reusable, framework-agnostic AI agent skills packaged as SKILL.md files. Distributed as a Claude Code plugin (crystools-skills) and via npx skills. Each skill is a self-contained directory under skills/ with a SKILL.md defining its behavior.

Read the full file on GitHub · 162 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. 2mo ago First seen · 162 lines · 1,600 tokens per session scan A 575da16222b5

Subscribe to this mod's changes

claudio is an instructions file published in the GitHub repository crystian/skills (24 stars, last pushed 6mo ago), licensed MIT. It adds 1,600 tokens to every session, about $0.0064 per session on Opus 5.5. 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.

Building agents
Related

claudio compared with instructions from other repositories

claudio next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claudiocrystian/skillsInstructions file246mo agoMITA1,600Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode