cardano-init: Instructions file for Claude Code

CLAUDE.md

cardano-init CLAUDE.md is an instructions file for Claude Code from input-output-hk/cardano-init. It costs 1,327 tokens per session, scanned A, original, Apache-2.0.

Project instructions for cardano-init, a Rust command-line tool that creates Cardano protocol projects from selected tools. It generates a monorepo, meaning several related projects managed in one repository.

In plain words
What is it for?
Use it when building, testing, formatting, reviewing, or extending cardano-init and its generated Cardano project structure.
Why use it?
It tells coding agents which documents define the design, which commands are available, and which features are implemented versus merely planned.

Instructions file for Claude Code

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

This is input-output-hk/cardano-init's own configuration. It tells Claude Code how to work on cardano-init 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 cardano-init configures →

Reuse

Borrowing it

Nothing to install: this file belongs to input-output-hk/cardano-init. 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/input-output-hk/cardano-init/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/input-output-hk/cardano-init

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 cardano-init CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/input-output-hk/cardano-init/claude-md/github.svg)](https://agentmods.dev/instructions/input-output-hk/cardano-init/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/input-output-hk/cardano-init/claude-md"><img src="https://agentmods.dev/badge/instructions/input-output-hk/cardano-init/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 cardano-init CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/input-output-hk/cardano-init/claude-md"><img src="https://agentmods.dev/badge/instructions/input-output-hk/cardano-init/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,327 This file is loaded in full into every session.
When invoked 1,327 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 $0.01327 $0.01327
Opus 5.5 $0.00531 $0.00531
Sonnet 5.5 $0.00265 $0.00265
Haiku 4.5 $0.00133 $0.00133

Measured 11d ago against content hash fe0ce1b78ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cardano-init 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 11d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 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

cardano-init is a Rust CLI tool that scaffolds Cardano protocol projects. Users select tools for each functional role (on-chain, off-chain, infrastructure, devnet, formal-methods) and the CLI generates a working monorepo. The authoritative docs live in docs/: read docs/design/prd.md (product), docs/contributing/architecture.md (system design), and docs/design/tech-spec.md (contracts, schemas, edge cases) before making any significant changes; docs/contributing/adding-a-tool.md is the contributor guide and docs/design/roadmap.md is the milestone plan.

docs/ is the source of the docs site (mdBook, published to GitHub Pages by .github/workflows/docs.yml), in three folders: user-guide/ (CLI users; follows the Cardano Developer Portal writing rules), contributing/, and design/. Every page must be listed in docs/SUMMARY.md. Preview with mdbook serve docs.

The dependency doctor, list, --json, and the pre-generation version-update notice are implemented. Minimum-version checks remain planned, not yet implemented. docs/design/roadmap.md tracks what's real vs. upcoming.

Commands

# Build
cargo build

# Run
cargo run -- [args]

# Tests
cargo test

# Single test
cargo test <test_name>

# Lint/format
cargo fmt
cargo clippy

Architecture

The codebase is a single Rust crate. The module structure is as follows (see docs/contributing/architecture.md §2):

  • src/cli/: impure edge: argument parsing (clap), interactive prompts (dialoguer), and the output presenter. Orchestrates the core; holds no generation logic.
  • src/registry/: deserializes embedded TOML tool definitions into typed structs. The Role enum (5 roles) is the sole source of truth for the role vocabulary; the registry only references roles.
  • src/scaffold/: four-phase pipeline: context building → planning → rendering → writing.
  • src/doctor/: dependency detection + install advice.
  • src/contract.rs: constants for the interface contract (canonical paths, env var names, role dirs).

Read the full file on GitHub · 82 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. 11d ago Changed · -1 tokens per session fe0ce1b78ae7
  2. 25d ago Changed · -10 tokens per session f917e3850395
  3. 27d ago Changed · +2 lines · +86 tokens per session f5d766fab96a
  4. 2mo ago First seen · 80 lines · 1,252 tokens per session scan A 3f1802af770c

Subscribe to this mod's changes

cardano-init CLAUDE.md is an instructions file published in the GitHub repository input-output-hk/cardano-init (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,327 tokens to every session, about $0.0053 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.

Related

cardano-init CLAUDE.md compared with instructions from other repositories

cardano-init CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cardano-init CLAUDE.mdinput-output-hk/cardano-initInstructions file13yesterdayApache-2.0A1,327Claude 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