onboard-dev

A command that prepares a new developer to work on a project by examining the codebase, explaining the setup, and creating initial tasks.

In plain words
What is it for?
Use it to create an onboarding guide, identify prerequisites and environment variables, map the architecture, and suggest first tasks.
Why use it?
It reduces the time a newcomer spends figuring out the technology, project structure, required access, and local setup.

Command

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/alphaaiservice/cortex/onboard-dev
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 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 $0.00029 $0.00857
Opus 5 $0.00015 $0.00428
Sonnet 5 $0.00006 $0.00171
Haiku 4.5 $0.00003 $0.00086

Measured yesterday against content hash 4d7a0da5a810, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard-dev 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.

commands/onboard-dev.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Onboarding Automation

You are an expert developer onboarding assistant. Your job is to onboard a new developer ($ARGUMENTS) to this project by executing a comprehensive, structured onboarding workflow.

Phase 1: Project Discovery

  1. Read the project structure — Scan the entire repo tree, README, CONTRIBUTING.md, package.json / pyproject.toml / Cargo.toml / go.mod, and any existing CLAUDE.md or .claude/ config.
  2. Identify the tech stack — Languages, frameworks, databases, cloud services, CI/CD tools, package managers.
  3. Map the architecture — Identify entry points, core modules, API layers, database models, shared utilities, and external service integrations.

Phase 2: Environment Setup Guide

Generate a comprehensive ONBOARDING.md file in the project root with:

Prerequisites

  • Required software versions (Node.js, Python, Docker, etc.)
  • Required accounts and access (cloud providers, package registries, etc.)
  • Environment variables needed (create a .env.example if missing)

Setup Steps

  • Lead with the one-command path if the project follows the Cortex local-dev standard (LOCAL_DEV.md / commands/references/LOCAL_DEV_STANDARD.md): git clonecp .env.example .envmake dev → open the app, then make verify to confirm a healthy boot. Link LOCAL_DEV.md rather than re-documenting — and if it's missing, generate it (it's the single source for ports, seed creds, and the Troubleshooting matrix).
  • Otherwise: step-by-step commands to clone, install dependencies, configure, run locally
  • Database setup / migration commands
  • How to run the development server
  • How to run tests
  • Common troubleshooting tips (reuse the LOCAL_DEV.md Troubleshooting matrix)

IDE Configuration

  • Recommended VS Code extensions or IDE settings
  • Linting / formatting setup
  • Debugging configurations

Phase 3: Codebase Walkthrough Document

Generate ARCHITECTURE.md covering:

  • High-level architecture diagram (as ASCII/Mermaid)
  • Directory structure explained — What each top-level folder does
  • Key files and entry points — Where to start reading code
  • Data flow — How a typical request moves through the system
  • Dependency map — Key internal and external dependencies
  • Design patterns used — Patterns, conventions, and coding standards
  • API endpoints (if applicable) — Key routes/endpoints with brief descriptions

Read the full file on GitHub · 94 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 · 94 lines · 29 tokens per session scan A 4d7a0da5a810

Subscribe to this mod's changes

onboard-dev is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 26d ago), licensed MIT. It adds 29 tokens to every session and 857 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.