claude-code-starter-kit CLAUDE.md

Project instructions for the Claude Code Starter Kit, including its setup commands, supported environments, and script-validation process.

In plain words
What is it for?
Use them when working on the setup wizard, installation options, dry runs, updates, or shell-script checks.
Why use it?
They give agents the exact project context and commands needed to make safe, verifiable changes.

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/cloudnative-co/claude-code-starter-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/cloudnative-co/claude-code-starter-kit
Per session 6,604 This file is loaded in full into every session.
When invoked 6,604 The same file — it is already loaded in full.
Security scan F 4 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.

ModelPer sessionOnce invoked
Fable 5 $0.06604 $0.06604
Opus 5 $0.03302 $0.03302
Sonnet 5 $0.01321 $0.01321
Haiku 4.5 $0.00660 $0.00660

Measured 2d ago against content hash 77a278a1a56e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

claude-code-starter-kit CLAUDE.md scanned grade F with 4 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh | bash

Reads agent configuration directoriesmediumAgent snooping

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

| assembled settings.json | `~/.claude/settings.json` | always |

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`install.sh` validates `INSTALL_DIR` via `_safe_install_dir()` before any `rm -rf` operations. Requires an absolute path, strips ALL trailing slashes (so `$HOME//` cannot bypass the `$HOME` check), blocks dangerous paths

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh | bash
CLAUDE.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 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.

Project Overview

Claude Code Starter Kit — a shell-based toolkit that bootstraps a complete Claude Code development environment via an interactive wizard. Supports macOS, Linux, WSL, and MSYS/Git Bash on Windows.

Commands

# Run setup wizard (interactive)
bash setup.sh

# Non-interactive setup
bash setup.sh --non-interactive --profile=standard --language=en --editor=vscode

# Dry-run (preview changes without modifying files)
bash setup.sh --dry-run
bash setup.sh --update --dry-run

# One-liner install (interactive)
curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh | bash

# One-liner install (non-interactive, standard profile + all default plugins)
curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh | bash -s -- --non-interactive
NONINTERACTIVE=1 bash -c "$(curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh)"

# Validate every tracked shell script exactly as CI does (one file per run)
git ls-files -z '*.sh' | xargs -0 -n 1 shellcheck -S warning

# Run unit tests
bash tests/run-unit-tests.sh

# Run scenario tests
bash tests/run-scenarios.sh

# Validate a single file
shellcheck lib/ghostty.sh

# Validate plugins.json
jq . config/plugins.json

# Clean uninstall (manifest-based)
bash uninstall.sh

# Update existing installation (auto-detected when re-running install.sh)
curl -fsSL https://raw.githubusercontent.com/cloudnative-co/claude-code-starter-kit/main/install.sh | bash

# Force update mode explicitly
bash setup.sh --update

# Force full re-setup (ignores existing installation)
bash setup.sh

All scripts use set -euo pipefail. ShellCheck (severity: warning) runs automatically on PRs via .github/workflows/shellcheck.yml. Validation also includes bash tests/run-unit-tests.sh and bash tests/run-scenarios.sh.

Read the full file on GitHub · 288 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. 2d ago First seen · 288 lines · 6,604 tokens per session scan F 77a278a1a56e

Subscribe to this mod's changes

claude-code-starter-kit CLAUDE.md is an instructions file published in the GitHub repository cloudnative-co/claude-code-starter-kit (147 stars, last pushed 9d ago), licensed MIT. It adds 6,604 tokens to every session, about $0.0330 per session on Opus 5. A static security scan graded it F with 4 findings (downloads and executes remote code, reads agent configuration directories, recursive force delete). 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

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

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

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