claude-code-toolkit CLAUDE.md

A project guide for Claude Code, with instructions about the repository’s custom skills, build commands, and required file structure.

In plain words
What is it for?
Use it to understand the repository, build one skill or all skills into .skill ZIP files, and check which skills pass validation.
Why use it?
It gives Claude Code the project context needed to work consistently and explains how to validate and package skills for Claude.ai.

Instructions file

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 instructions/robertguss/claude-code-toolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/robertguss/claude-code-toolkit
Per session 617 This file is loaded in full into every session.
When invoked 617 The same file — it is already loaded in full.
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 $0.00617 $0.00617
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00062 $0.00062

Measured 3d ago against content hash cdbb889043a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-toolkit CLAUDE.md 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 3d 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This repository contains custom Claude skills—modular packages that extend Claude's capabilities with specialized workflows and domain knowledge. Skills are used with both Claude Code (CLI) and Claude.ai (web/mobile/desktop).

Build Commands

# Package a single skill for Claude.ai upload
python build.py <skill-name>

# Package all skills
python build.py --all

# List available skills with validation status
python build.py --list

Output: .skill files in dist/ (ZIP archives with skill contents)

Architecture

Skill Structure

Each skill is a top-level folder containing:

<skill-name>/
├── SKILL.md              # Required: instructions + YAML frontmatter
├── references/           # Optional: documentation loaded on-demand
└── assets/               # Optional: templates, examples

SKILL.md Requirements

Must start with YAML frontmatter:

  • name (required): skill identifier
  • description (required, min 20 chars): determines when the skill activates

Build System

build.py validates skills and packages them as ZIP archives:

  • Validates YAML frontmatter presence and required fields
  • Excludes hidden files, .DS_Store, __pycache__
  • Creates <skill-name>.skill in dist/

Requires: pyyaml (for frontmatter parsing)

Usage Modes

Claude Code: Reference skills directly via filesystem paths in project CLAUDE.md or global ~/.claude/CLAUDE.md

Claude.ai: Upload packaged .skill files via Settings → Skills

Templates

The templates/ directory contains document templates and guides for configuring Claude Code:

Document Purpose
CLAUDE-MD-template.md Project or global instructions for Claude
HUMAN-MD-template.md Relationship document — helps Claude know who you are
SKILL-MD-template.md Create custom skills (slash commands)
SESSION-HANDOFF-template.md Preserve context when sessions end
CORRECTION-template.md Give Claude structured feedback it can learn from
compaction-strategy.md What to preserve when context is compressed
CLAUDE-MD-GUIDE.md Deep dive into why each CLAUDE.md section matters
PROMPT-GUIDE.md How to write prompts that get better results
INTERACTION-PATTERNS.md How different phrases affect Claude's processing
CLAUDE_DNA.md Understanding who Claude is — values, preferences, limitations

Read the full file on GitHub · 84 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. 3d ago First seen · 84 lines · 617 tokens per session scan A cdbb889043a5

Subscribe to this mod's changes

claude-code-toolkit CLAUDE.md is an instructions file published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 25d ago), licensed MIT. It adds 617 tokens to every session, about $0.0031 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.