project-init

project-init is a command for Claude Code from jonase47/ccpr. It costs 0 tokens per session (1,596 once invoked), scanned A, original, MIT.

A project setup command that creates a new project’s folders, project instructions, and Git repository. Git is a system for recording changes to files over time.

In plain words
What is it for?
Use it when beginning a project, optionally providing its name, or when promoting an earlier prototype into a fuller project.
Why use it?
It gives a new project a consistent starting structure and a place to track its code history.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions 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/jonase47/ccpr/project-init
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr

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 project-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/project-init.svg)](https://agentmods.dev/commands/jonase47/ccpr/project-init)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/project-init"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/project-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,596 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 5.1 $0.00000 $0.01596
Opus 5 $0.00000 $0.00798
Sonnet 5 $0.00000 $0.00319
Haiku 4.5 $0.00000 $0.00160

Measured 2d ago against content hash bd09a88d8b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-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 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.

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.

commands/project-init.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/project-init

Initializes a new project with directory structure, project-specific CLAUDE.md, and Git repository.

Argument: $ARGUMENTS = [Project name]

If provided: use as project name (also used as directory name). If not provided: ask for the project name.

Execution

0. Detect Promotion Brief (Lean → Full Promotion)

If docs/PROMOTION_BRIEF.md exists (created by /lean-promote):

  • Read the brief in full
  • Take the project name from the path / repo name (do not ask again)
  • Use the brief as bootstrap input instead of a greenfield prompt:
    • Validated findings → P0 input (proposal for /p0-problem)
    • Confirmed assumptions → carry into CLAUDE.md under "Key Decisions" with date
    • Refuted assumptions → note in CLAUDE.md under "Open Risks" as "Lean-Lessons"
    • Constitution candidates → hand off to /constitution (step 4 below)
    • Catch-up obligations → schedule later via /p4-backlog as stories; note in HANDOVER.md now

If docs/PROMOTION_BRIEF.md does not exist: follow the normal greenfield path (steps 1–6).

1. Collect project information

Ask the user for the following information (if not already known):

  • Project name: Name of the project (used as directory name, kebab-case)
  • Project type: Software | Business | Software+Business
  • Short description: 1-2 sentences describing what the project is
  • Project goals: What should be achieved at the end? (1-3 goals)
  • Target audience: Who uses the result?
  • Budget: Rough estimate or "still unclear"
  • Timeline: When should it be done? or "open"
  • Regulatory: DSGVO (GDPR), health data, financial regulation, or "Standard"
  • Tech preferences: For software – are there requirements? or "open"
  • Agent notes: Special instructions for specific agents? (optional)

2. Create directory structure

Create the following structure in the current directory:

mkdir -p $PROJECTNAME/.claude
mkdir -p $PROJECTNAME/docs/{discovery,concept,validation,architecture,planning,quality,launch}
mkdir -p $PROJECTNAME/src
mkdir -p $PROJECTNAME/tests

Read the full file on GitHub · 173 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 · 173 lines · 0 tokens per session scan A bd09a88d8b0f

Subscribe to this mod's changes

project-init is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,596 tokens. 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 2026-09-03.