init

A project setup command that examines a codebase and writes project instructions for Claude Code in a CLAUDE.md file. It detects the programming languages, tools, commands, and coding patterns used by the project.

In plain words
What is it for?
Use it when starting work on an unfamiliar project to record how to test, build, format, lint, and follow the codebase's conventions.
Why use it?
It removes the need to document the project setup by hand or answer questions about it. The generated instructions give future coding sessions useful project context.

Command for Claude Code

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 commands/codeverbojan/claude-code-kickstart/init
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 747 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00747
Opus 5 $0.00010 $0.00374
Sonnet 5 $0.00004 $0.00149
Haiku 4.5 $0.00002 $0.00075

Measured yesterday against content hash 336958650e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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/commands/init.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Configure Project

Analyze this codebase and generate a complete Section 10 for CLAUDE.md. Do NOT ask the user questions — discover everything from the code.

1. Detect Stack

Check for these files and determine the stack:

  • package.json → Node.js / TypeScript
  • go.mod → Go
  • Cargo.toml → Rust
  • pyproject.toml / requirements.txt / setup.py → Python
  • Gemfile → Ruby
  • pom.xml / build.gradle → Java/Kotlin
  • composer.json → PHP
  • *.csproj / *.sln → C# / .NET
  • mix.exs → Elixir
  • pubspec.yaml → Flutter/Dart
  • Multiple → list all

2. Detect Commands

Node.js: Read package.json scripts field. Map to actual commands. Python: Check Makefile, pyproject.toml [tool.pytest], tox.ini. Go: Check Makefile targets. Default to go test/vet/build. Rust: Default to cargo check/clippy/test/build. Any stack: Check Makefile, justfile, Taskfile.yml, docker-compose.yml.

3. Detect Conventions

Read actual code to discover patterns (don't assume):

  • TypeScript: Check tsconfig.json for strict mode. Check for any usage.
  • Linting: Check .eslintrc*, ruff.toml, .golangci.yml, clippy.toml.
  • Formatting: Check .prettierrc*, biome.json, ruff.toml, rustfmt.toml.
  • Testing: Check test directory structure, framework config.
  • CSS: Check for CSS modules, Tailwind, styled-components, etc.
  • Components: Server vs client components, naming patterns.
  • Imports: Barrel files, path aliases (tsconfig.json paths).

4. Detect Architecture

  • Read the top-level directory structure
  • Identify: monorepo (turbo.json, nx.json, lerna.json, pnpm-workspace.yaml)?
  • Identify: app framework (Next.js app router, Django, Rails, FastAPI)?
  • Map key directories to their purpose
  • Note entry points (main files, route directories)

5. Write Section 10

Replace Section 10 in CLAUDE.md with what you discovered. Use this format:

## 10. Project-Specific Configuration

### Stack
[What you found]

### Build & Dev Commands
- `command` — what it does
- `command` — what it does

### Code Conventions
- [Convention discovered from config files]
- [Convention discovered from code patterns]

### Architecture
[Directory structure with purpose of each key directory]
[Entry points]
[Key patterns: monorepo, app router, etc.]

Read the full file on GitHub · 87 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. yesterday First seen · 87 lines · 19 tokens per session scan A 336958650e6a

Subscribe to this mod's changes

init is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 747 once invoked, about $0.0001 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 2026-08-31.