claude-local-starter: Instructions file for Claude Code

CLAUDE.md

claude-local-starter CLAUDE.md is an instructions file for Claude Code from indranildchandra/claude-local-starter. It costs 3,023 tokens per session, scanned B, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, describing the project files, installer, and global configuration. They explain how the starter setup is copied to a machine.

In plain words
What is it for?
Use them when installing or maintaining the Claude Code starter environment, auditing token-related settings, or enabling and disabling the repository's safe auto-approval mode.
Why use it?
They give the assistant a clear map of the repository and prevent confusion about which files control the installed configuration. They also document that running the installer overwrites the global setup.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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-local-starter CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/indranildchandra/claude-local-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/indranildchandra/claude-local-starter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,023 This file is loaded in full into every session.
When invoked 3,023 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.03023 $0.03023
Opus 5 $0.01511 $0.01511
Sonnet 5 $0.00605 $0.00605
Haiku 4.5 $0.00302 $0.00302

Measured 9d ago against content hash e330c101e9cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

claude-local-starter CLAUDE.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| `settings.json` | Source of truth for plugins, env vars, MCP servers, hooks — merged into `~/.claude/settings.json` |
CLAUDE.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 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.

Note: install.sh copies claude-md-master/CLAUDE.md to ~/.claude/CLAUDE.md on every run (always overwrites). The "Global Claude Code Configuration" section below is kept in sync manually — edit claude-md-master/CLAUDE.md to change what gets installed globally.

Repository Overview

claude-local-starter is a single-script bootstrap installer that replicates a full Claude Code environment onto any machine. It is not a library or application — the primary deliverable is install.sh.

Key Files

File Purpose
install.sh The installer — idempotent, safe to re-run
scripts/token-audit.sh Snapshot + restore extension states for token cost measurement
scripts/enable-safe-yolo.sh Add auto-approve permissions + acceptEdits mode to a repo
scripts/disable-safe-yolo.sh Remove safe-yolo permissions from a repo
scripts/config/claude-safe-yolo-permissions.txt Single source of truth for safe-yolo allow/deny/defaultMode
claude-md-master/CLAUDE.md Source of truth for ~/.claude/CLAUDE.md — always overwrites on install
settings.json Source of truth for plugins, env vars, MCP servers, hooks — merged into ~/.claude/settings.json
commands/ Slash command definitions synced to ~/.claude/commands/
skills/ Custom skill directories synced to ~/.claude/skills/
claude-local-starter.html Visual dashboard — open from ~/.claude/ after install (data is injected there)

Installer Modes

bash install.sh                  # safe update — merges, never overwrites
bash install.sh --clean-install  # full overwrite from repo (backs up first)
bash install.sh --dry-run        # preview all actions, no changes written

What install.sh Does (in order)

  1. Pre-flight checks (git, node, npm, python3, bun)
  2. Interactive prompts — preserve CLAUDE.md? preserve MCP/plugin/skill states? (update mode only)
  3. Backup mutable components (only on --clean-install)
  4. Create ~/.claude/ directory structure
  5. Install/merge settings.json
  6. Install CLAUDE.md from claude-md-master/ (always overwrites)
  7. Install skills via npx skills add (patched with disable-model-invocation: true)
  8. Clone/update blader/humanizer skill
  9. Install uipro-cli globally
  10. Install LSP binaries (typescript-language-server, pyright, gopls, rust-analyzer, jdtls) — pyright-lsp and typescript-lsp enabled by default; others installed but disabled
  11. Install @playwright/cli, run playwright-cli install --skills, install Chromium
  12. Register MCP servers via npx gitnexus setup
  13. Write ~/.claude/plugin_commands.sh (manual paste into Claude Code)
  14. Create ~/.claude-work/ structure and templates
  15. Write shell aliases/functions to ~/.zshrc / ~/.bashrc
  16. Sync commands/, skills/, HTML dashboard → ~/.claude/ (with settings.json + CLAUDE.md injected into dashboard)

Read the full file on GitHub · 229 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 · 229 lines · 3,023 tokens per session scan B e330c101e9cc

Subscribe to this mod's changes

claude-local-starter CLAUDE.md is an instructions file published in the GitHub repository indranildchandra/claude-local-starter (13 stars, last pushed 1mo ago), licensed MIT. It adds 3,023 tokens to every session, about $0.0151 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 3,737 tokens