claude-onramp: Instructions file for Claude Code

CLAUDE.md

claude-onramp CLAUDE.md is an instructions file for Claude Code from laurelkorwin/claude-onramp. It costs 1,866 tokens per session, scanned A, original, MIT.

Instructions for explaining computer actions in everyday language before taking them, especially when they involve private files, internet content, or installing software. It is designed for people who may not be software engineers.

In plain words
What is it for?
Use it when explaining network requests, package installations, server setup, code changes, or other actions that could affect a computer or send data elsewhere.
Why use it?
It helps people understand what an action will access, send, change, or install before it happens, including risks that may be hard to see from a terminal command.

Instructions file for Claude Code

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

This is laurelkorwin/claude-onramp's own configuration. It tells Claude Code how to work on claude-onramp 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 claude-onramp configures →

Reuse

Borrowing it

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

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 claude-onramp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/laurelkorwin/claude-onramp/claude-md"><img src="https://agentmods.dev/badge/instructions/laurelkorwin/claude-onramp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,866 This file is loaded in full into every session.
When invoked 1,866 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 $0.01866 $0.01866
Opus 5 $0.00933 $0.00933
Sonnet 5 $0.00373 $0.00373
Haiku 4.5 $0.00187 $0.00187

Measured 9d ago against content hash 6cd912ea79b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-onramp 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 9d 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 · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Transparency Guidelines

This project is used by people who are not software engineers. Before taking any action, explain what you're about to do in plain language — as if the person has never used a terminal, written code, or configured a server. The guiding principle is informed consent: no action should happen until the user understands what it does, what it touches, and whether it can be undone.

Why this matters

Three things become dangerous when they combine: accessing private data on your machine, processing content from the internet that could be manipulated, and taking actions that leave your machine (sending data somewhere, publishing code, installing software from the internet). Any time an action involves one of these, call it out explicitly. When two or three combine, treat it as high-risk and ask for confirmation.

What to explain, by category

Network requests [external action]

A network request means the computer reaches out to another computer over the internet to ask for or send information.

Before doing this, explain: Where the request is going, what data (if any) is being sent, and what you expect to get back.

[permission_explanation] I'm going to contact the Hacker News API at hacker-news.firebaseio.com to download the current top stories. No data from your machine is sent — it's just asking for a list. This is read-only and doesn't change anything.


Package installs [external action] [untrusted input]

A "package" is a bundle of code someone else wrote that gets downloaded from the internet and added to the project. Think of it like installing an app — it can run code on your machine.

Before doing this, explain: What package you're installing, what it does, and that it downloads code from the internet onto the machine.

[permission_explanation] I'm going to install a package called date-fns — it helps format dates for display. This downloads code from the npm registry (a public library of JavaScript packages) onto your machine. It does not send any of your data anywhere. You can remove it later by running npm uninstall date-fns.

Read the full file on GitHub · 154 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. 9d ago First seen · 154 lines · 1,866 tokens per session scan A 6cd912ea79b3

Subscribe to this mod's changes

claude-onramp CLAUDE.md is an instructions file published in the GitHub repository laurelkorwin/claude-onramp (10 stars, last pushed 6mo ago), licensed MIT. It adds 1,866 tokens to every session, about $0.0093 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens