What is am-i-exposed CLAUDE.md?

A set of project instructions for AI coding assistants, covering commands, code style, and the wording used in the interface. It specifies pnpm for package management and the commands for development, building, and linting.

Use it to guide repository setup, tests and builds, TypeScript style, punctuation, and the voice of interface copy.

It gives coding assistants consistent rules for working in the repository and prevents avoidable differences in commands or user-facing text.

How Copexit/am-i-exposed configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Copexit/am-i-exposed. 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/Copexit/am-i-exposed/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Copexit/am-i-exposed

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/copexit/am-i-exposed/claude-md/github.svg)](https://agentmods.dev/instructions/copexit/am-i-exposed/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/copexit/am-i-exposed/claude-md"><img src="https://agentmods.dev/badge/instructions/copexit/am-i-exposed/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/copexit/am-i-exposed/claude-md"><img src="https://agentmods.dev/badge/instructions/copexit/am-i-exposed/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,005 This file is loaded in full into every session.

When invoked 2,005 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.

Model	Per session	Once invoked
Fable 5.1	$0.02005	$0.02005
Opus 5.5	$0.00802	$0.00802
Sonnet 5.5	$0.00401	$0.00401
Haiku 4.5	$0.00200	$0.00200

Measured 1mo ago against content hash e50324d693ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

am-i-exposed 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 1mo 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Project Instructions for AI Assistants

Build & Test

Package manager: pnpm (do not use npm or yarn)
Dev server: pnpm dev
Build (static export): pnpm build
Lint: pnpm lint (--max-warnings 0, type-aware rules)
Type-check: pnpm type-check
Unit/hook tests: pnpm test (one Vitest run; DOM tests opt into jsdom per file), pnpm test:coverage
E2E: pnpm test:e2e (Playwright against out/, run pnpm build first)
CLI tests: cd cli && pnpm test

Code Style Rules

No em dashes

Never use em dashes in any form:

No literal --- (U+2014) characters
No \u2014 unicode escapes
No — HTML entities

Use a regular hyphen with spaces instead: -

This applies to all strings, comments, UI text, metadata, test descriptions, and documentation within src/.

Voice and tone in UI text

Never use "we", "us", or "our" in UI copy, metadata, FAQ answers, or any user-facing text. This tool is not a person, company, or group.
Use passive voice or refer to the tool by name ("am-i.exposed").
Data is never "transmitted to us" - say "transmitted to anyone" or specify the actual recipient (e.g., "mempool.space for blockchain data").
Correct: "Your addresses and transactions are never logged, stored, or transmitted to anyone except the mempool.space API (or your own instance)."
Wrong: "We don't store your data." / "Your data is never transmitted to us."

General

TypeScript strict mode, no any types
Tailwind CSS 4 for styling (use semantic tokens like bg-surface-inset over hardcoded hex values)
Use motion/react (not framer-motion) for animations
Next.js 16 with static export (output: "export")
All Bitcoin amounts in satoshis (never BTC floats in logic)
Dark and light themes: the theme follows the OS by default (System / Light / Dark in settings, useTheme); tokens live in src/app/globals.css (:root dark, html[data-theme="light"] light) and are mirrored for JS in src/lib/palette.ts
"use client" on all interactive pages/components (static export does not support RSC)

Read the full file on GitHub · 140 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.

1mo ago Changed · +38 tokens per session e50324d693ad
1mo ago Changed · +1 lines · +116 tokens per session 474437a3ec8c
1mo ago Changed · +4 lines · +107 tokens per session 990ce78a313c
2mo ago First seen · 135 lines · 1,744 tokens per session scan A 09e78105f849

Subscribe to this mod's changes

am-i-exposed CLAUDE.md is an instructions file published in the GitHub repository Copexit/am-i-exposed (108 stars, last pushed 18d ago), licensed MIT. It adds 2,005 tokens to every session, about $0.0080 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.

am-i-exposed CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
am-i-exposed CLAUDE.mdCopexit/am-i-exposed	Instructions file	108	18d ago	MIT	A	2,005	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

am-i-exposed: Instructions file for Claude Code