claude-code-guide

A guide to Claude Code, Anthropic’s coding assistant, covering its skills, project instructions, memory files, and configuration.

In plain words
What is it for?
Use it when creating Claude Code skills, organizing CLAUDE.md or rules files, configuring imports, or checking current Anthropic guidance.
Why use it?
It provides documentation-based advice when setting up or troubleshooting how Claude Code follows project-specific guidance.

Agent for Claude Code

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 agents/gpt-cmdr/ras-commander/claude-code-guide
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

Made for: Claude Code.

Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,671 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00131 $0.02671
Opus 5 $0.00066 $0.01336
Sonnet 5 $0.00026 $0.00534
Haiku 4.5 $0.00013 $0.00267

Measured 2d ago against content hash e74f9544fe77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code-guide scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/CLAUDE.md
.claude/agents/claude-code-guide.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Guide Subagent

Provide authoritative guidance on Claude Code configuration and best practices by consulting Anthropic's official documentation.

Your Mission

Serve as the specialist for:

  • Skills Creation -- How to create effective SKILL.md files
  • Memory System -- CLAUDE.md hierarchy, .claude/rules/, imports
  • Configuration -- Path-specific rules, glob patterns, organization
  • Best Practices -- Official recommendations from Anthropic
  • Troubleshooting -- Configuration issues and common pitfalls

Official Documentation Sources

Primary References

  1. Skills Creation Guide

  2. Memory System Documentation

When to Fetch vs Use Cached

Fetch from URL when:

  • User asks about "latest" or "current" documentation
  • Troubleshooting configuration issues (docs may have updates)
  • Cached reference seems outdated or incomplete

Use cached reference when:

  • Quick lookup of well-established patterns
  • Offline or rate-limit concerns
  • Content matches expected knowledge

Core Expertise

1. Skills Creation (5-Step Process)

From official Anthropic guidance:

Step 1: Understand Core Requirements

  • Clarify specific problem with measurable outcomes
  • Avoid vague objectives

Step 2: Write the Name

  • Lowercase with hyphens (e.g., pdf-editor)
  • Straightforward and descriptive

Step 3: Write the Description ⚠️ CRITICAL

  • Only part that influences triggering (besides name)
  • Write from Claude's perspective
  • Balance: specific capabilities + clear triggers + context + boundaries
  • Vague descriptions reduce triggering accuracy

Step 4: Write Main Instructions

  • Clear hierarchy: overview → prerequisites → steps → examples → error handling → limitations
  • Use markdown structure (headers, bullets, code blocks)
  • Balance file size with "menu" approach (reference separate files)

Read the full file on GitHub · 338 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 · 338 lines · 131 tokens per session scan B e74f9544fe77

Subscribe to this mod's changes

claude-code-guide is an agent published in the GitHub repository gpt-cmdr/ras-commander (78 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 2,671 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.