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.

am-i-exposed CLAUDE.md — Instructions file for Claude Code by Copexit: A set of project instructions for AI coding assistants…

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/copexit/am-i-exposed/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.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.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,744 This file is loaded in full into every session.

When invoked 1,744 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.

Model	Per session	Once invoked
Fable 5.1	$0.01744	$0.01744
Opus 5	$0.00872	$0.00872
Sonnet 5	$0.00349	$0.00349
Haiku 4.5	$0.00174	$0.00174

Measured 6d ago against content hash 09e78105f849, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 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

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 theme only - no light mode toggle
"use client" on all interactive pages/components (static export does not support RSC)

Bitcoin-specific

Support all mempool.space networks: mainnet, testnet4, signet
Address validation must be network-aware (bc1 for mainnet, tb1 for testnet/signet)
API: mempool.space only (no secondary/fallback APIs)
Never log or persist user addresses/txids

Severity levels

Use these consistently for findings:

critical - red (#ef4444)
high - orange (#f97316)
medium - amber (#eab308)
low - blue (#3b82f6)
good - green (#28d065)

Read the full file on GitHub · 135 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.

6d 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 (102 stars, last pushed 1mo ago), licensed MIT. It adds 1,744 tokens to every session, about $0.0087 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.

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

am-i-exposed CLAUDE.md