new-project

new-project is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 34 tokens per session (859 once invoked), scanned A, original, MIT.

A natural-language router for starting new projects. It identifies the requested technology or project type and sends the request to the matching scaffold command.

In plain words
What is it for?
Use it to start Flutter, React Native, NestJS, Python, Java, Angular, agent, database, and related project types.
Why use it?
It avoids choosing separate setup commands manually when you describe the project in ordinary language.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to start Flutter, React Native, NestJS, Python, Java, Angular, agent, database, and related project types.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/new-project
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.

Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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 new-project

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/new-project.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/new-project)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/new-project"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/new-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00034 $0.00859
Opus 5 $0.00017 $0.00430
Sonnet 5 $0.00007 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 4d ago against content hash c1ec45d64c72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

new-project 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 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.

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/new-project.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Project — Keyword Router

Request: $ARGUMENTS

Step 1 — Detect Project Type

Analyze $ARGUMENTS using this keyword matrix. Match the FIRST row that fits:

Keywords in request Project Type Route to command
flutter, dart, ios app, android app Flutter Mobile /scaffold-flutter-app
react native, expo, rn app React Native Load mobile-developer skill
nestjs, nest, node api, typescript api NestJS API /scaffold-nestjs-api
python, fastapi, django, flask Python API /scaffold-python-api
java, spring, spring boot Java Spring API /scaffold-spring-api
angular, spa, web app, dashboard Angular SPA /scaffold-angular-app
agent, langchain, langgraph, ai agent, rag Agentic AI /scaffold-agentic-ai
adk, gemini agent, google adk Google ADK Agent /scaffold-google-adk
a2ui, agent ui, agent-driven ui A2UI Angular /scaffold-a2ui
database, schema, postgres, sql Database Schema /design-database
No clear match Ambiguous Ask one clarifying question (see Step 2)

Step 2 — If ambiguous

Ask exactly ONE question:

I need one clarification: what is the primary technology?
Options: Flutter mobile / NestJS API / Python FastAPI / Java Spring / Angular SPA / AI Agent

Do not ask multiple questions. One answer is enough to route.

Step 3 — Route

Once type is determined:

  1. Extract the app name from $ARGUMENTS (everything after the tech keyword, e.g. "fitness tracker" from "flutter fitness tracker"). Use as the project name for the scaffold command.

  2. Run the Plan Verification gate first:

    🔴 Does docs/plans/YYYY-MM-DD-<project-name>.md exist?
    NO → Create it before scaffolding (list: feature scope, key screens/endpoints, data models)
    YES → Verify it is current, then proceed
    
  3. Execute the routed command with the extracted name as argument.

Read the full file on GitHub · 72 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 · 72 lines · 34 tokens per session scan A c1ec45d64c72

Subscribe to this mod's changes

new-project is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 859 once invoked, about $0.0002 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 2026-09-03.