claude_code_setup CLAUDE.md

A portable set of instructions and starter files for configuring Claude Code, an AI coding assistant, in new software projects.

In plain words
What is it for?
Use it to bootstrap Claude Code in a repository, define project conventions, add custom skills and agents, and prepare standard settings and review templates.
Why use it?
It gives projects consistent rules, workflows, agent definitions, templates, and security settings instead of recreating them each time.

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/arnabdeypolimi/claude_code_setup/claude-md
Clone the repo
git clone --depth 1 https://github.com/arnabdeypolimi/claude_code_setup
Per session 1,433 This file is loaded in full into every session.
When invoked 1,433 The same file — it is already loaded in full.
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 $0.01433 $0.01433
Opus 5 $0.00717 $0.00717
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00143 $0.00143

Measured 3d ago against content hash 412dc2031c20, 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_setup CLAUDE.md 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

The owner's global Claude settings live at `~/.claude/settings.json`. The model is set to `sonnet` globally. Project-level `settings.json` files can override this per repo.
CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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.

Purpose

This repo is a portable Claude Code configuration kit. It stores skills, agent definitions, workflows, and project templates that can be copied into new projects to bootstrap a consistent Claude Code setup.

Repo Conventions

  • .claude/skills/<name>/SKILL.md — skill prompt content (local custom skills)
  • agents/<type>/<name>.md — agent definitions (orchestrator and subagents)
  • workflows/<name>.md — multi-step workflow definitions
  • templates/ — starter files to copy into new projects
    • CLAUDE.md — starter project CLAUDE.md
    • settings.json — starter .claude/settings.json
    • config.yaml — master project configuration template
    • rules.md — global rules and conventions template
    • allowlist.yaml — security permissions template
    • commit-message.md — commit message format guide
    • mr-template.md — merge request description template
    • review-template.md — code review output template

settings.local.json files are machine-specific and should not be committed to project repos.

Skill Sources

Source Skills
Custom (this repo) git-operations, gitlab-integration, python-best-practices, python-docs, pydantic, pytorch-lightning, mermaid-diagrams, remotion-best-practices, code-refactor, skill-creator
(source TBD) industrial-ai-research, latex-paper-en, latex-thesis-zh, paper-audit, research-paper-writing, typst-paper
pbakaus/impeccable 21 UI/UX skills (frontend-design, animate, adapt, arrange, audit, bolder, clarify, colorize, critique, delight, distill, extract, harden, normalize, onboard, optimize, overdrive, polish, quieter, teach-impeccable, typeset)
coreyhaines31/marketingskills Marketing skills (page-cro, copywriting, and more)
addyosmani/agent-skills Agent skills collection by Addy Osmani
Imbad0202/academic-research-skills Academic research pipeline (deep-research, academic-paper, academic-paper-reviewer, academic-pipeline)

Read the full file on GitHub · 129 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 · 129 lines · 1,433 tokens per session scan B 412dc2031c20

Subscribe to this mod's changes

claude_code_setup CLAUDE.md is an instructions file published in the GitHub repository arnabdeypolimi/claude_code_setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,433 tokens to every session, about $0.0072 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 2026-08-31.

Related

Other instructions, from other repositories

ai-engineering-from-scratch AGENTS.md

Instructions for rohitg00/ai-engineering-from-scratch, covering agents.md, philosophy, repo layout, hard rules and dependencies.

rohitg00/ai-engineering-from-scratch · 3,101 tokens

LLM-Wiki AGENTS.md

Instructions for VectorPeak/LLM-Wiki, covering obsidian second brain - codex cli operating manual, how to operate, command routing tables (grouped by category), wiki layer - simplified knowledge operations and vault - daily writing, capture, find.

VectorPeak/LLM-Wiki · 3,809 tokens

claude-godmode AGENTS.md

Instructions for SyloRei/claude-godmode, covering agents.md, agent roster, architect, code-reviewer and convention-reviewer.

SyloRei/claude-godmode · 7,502 tokens

SpecRoute GEMINI.md

Instructions for Enovatr-Labs/SpecRoute, a project described as: Open source framework for spec-driven agentic software engineering. PRDs, prompts, agents, skills, workflows, and coding rules for Codex, Claude, and modern AI development teams.

Enovatr-Labs/SpecRoute · 75 tokens

claude-code-harness CLAUDE.md

Instructions for viacheslav-tronko/claude-code-harness, covering claude.md — operational doctrine ({yourprojectname}), projectconfig — fill these placeholders before using, 0. top of mind — these four ride above everything, 1. mission and 2. p0 hard constraints — never violate.

viacheslav-tronko/claude-code-harness · 8,220 tokens

mcp-brain CLAUDE.md

Instructions for PierfrancescoLijoi/mcp-brain, covering claude.md, what this project is, commands, architecture and data model — three memory levels.

PierfrancescoLijoi/mcp-brain · 837 tokens