claude-code-portable CLAUDE.md

claude-code-portable CLAUDE.md is an instructions file for coding agents from SonnyTaylor/claude-code-portable. It costs 700 tokens per session, scanned A, original, MIT.

Repository instructions for a portable Claude Code launcher that runs from a USB drive or any folder without installation. They describe its scripts, structure, and constraints.

In plain words
What is it for?
Use them when changing or reviewing the launcher scripts, configuration, portable downloads, or platform-specific behavior.
Why use it?
They give the coding agent the project context needed to work safely, including supported systems, download checks, and where local state is stored.

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/sonnytaylor/claude-code-portable/claude-md
Clone the repo
git clone --depth 1 https://github.com/SonnyTaylor/claude-code-portable

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-code-portable CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sonnytaylor/claude-code-portable/claude-md.svg)](https://agentmods.dev/instructions/sonnytaylor/claude-code-portable/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sonnytaylor/claude-code-portable/claude-md"><img src="https://agentmods.dev/badge/instructions/sonnytaylor/claude-code-portable/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 700 This file is loaded in full into every session.
When invoked 700 The same file — it is already loaded in full.
Security scan A 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 $0.00700 $0.00700
Opus 5 $0.00350 $0.00350
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured 4d ago against content hash e9977b115d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-portable CLAUDE.md scanned grade A 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `claude.sh` - macOS/Linux bash launcher (uses `curl` for downloads, `sha256sum`/`shasum` for verification)
CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 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.

What This Is

A portable launcher for Claude Code that runs from a USB drive or any folder with no installation. Three launcher scripts (claude.ps1 as the primary Windows launcher, claude.cmd as the Windows fallback, and claude.sh for macOS/Linux) download the official Claude Code binary, optionally download Portable Git (Windows only), and configure environment variables so all state stays within this folder.

Architecture

The project has no build system, tests, or dependencies -- it is purely shell scripts.

  • claude.ps1 - Primary Windows launcher (PowerShell, uses Invoke-WebRequest for downloads, Get-FileHash for SHA256 verification)
  • claude.cmd - Windows batch fallback launcher (used when PowerShell is unavailable; auto-forwards to claude.ps1 when possible)
  • claude.sh - macOS/Linux bash launcher (uses curl for downloads, sha256sum/shasum for verification)
  • config.example - Template for optional API key / proxy configuration
  • data/CLAUDE.md - Auto-generated starter CLAUDE.md placed into the portable config directory by the launcher scripts on first run

All three launchers share identical logic:

  1. Create bin/, data/, tmp/ directories
  2. Create a default data/CLAUDE.md if missing
  3. Handle subcommands (update, version, setup, --help)
  4. Load config file (key=value pairs) into environment if it exists
  5. Download Claude Code binary from GCS bucket with SHA256 verification if not present
  6. On Windows: find or download Portable Git
  7. Set CLAUDE_CONFIG_DIR=data/, CLAUDE_CODE_TMPDIR=tmp/, DISABLE_AUTOUPDATER=1
  8. Exec the binary, forwarding all arguments

Binary downloads come from https://storage.googleapis.com/claude-code-dist-86c565f3-f756-42ad-8dfa-d59b1c096819/claude-code-releases. The version manifest at {bucket}/{version}/manifest.json contains per-platform SHA256 checksums.

Key Constraints

Read the full file on GitHub · 41 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. 4d ago First seen · 41 lines · 700 tokens per session scan A e9977b115d4a

Subscribe to this mod's changes

claude-code-portable CLAUDE.md is an instructions file published in the GitHub repository SonnyTaylor/claude-code-portable (10 stars, last pushed 3mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 4,345 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

next.js 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