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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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.
[](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/new-project)<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>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.
| Model | Per session | Once 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 |
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.
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:
-
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. -
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 -
Execute the routed command with the extracted name as argument.
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.
- 4d ago First seen · 72 lines · 34 tokens per session scan A c1ec45d64c72
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.
Other commands, from other repositories
standup
Quick daily standup from today's Claude Code sessions — grouped by project, with cost and errors.
fire-todos
Capture, list, and manage todos during work sessions.
gsd:resume-work
Resume work from previous session with full context restoration.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.
standup
A command that creates a daily stand-up report by summarizing recent work, planned tasks, calendar events, and blockers.