A codebase analysis and setup add-on that studies a software project and creates Claude Code guidance and supporting tools based on what it finds. It can produce project instructions, folder-specific rules, skills, agents, hooks, and a list of checks still needing verification.

Use it when onboarding an AI coding assistant to an existing project, documenting project conventions, setting up automated coding helpers, or identifying configuration decisions that need review.

It reduces the time needed to understand an unfamiliar codebase and configure Claude for that project. The generated guidance is based on researched evidence from the repository rather than guesswork.

onboard — Plugin by ApurvBazari

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.

Claude Code

/plugin marketplace add ApurvBazari/claude-plugins

agentmods

npx agentmods add plugins/apurvbazari/claude-plugins/onboard

Clone the repo

git clone --depth 1 https://github.com/ApurvBazari/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

onboard 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.

onboard/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "onboard",
  "version": "3.1.1",
  "description": "Analyze codebases with deep, verified research and generate evidence-grounded Claude tooling — CLAUDE.md, path-scoped rules, skills, agents, hooks, and a verify backlog.",
  "author": {
    "name": "Apurv Bazari"
  },
  "repository": "https://github.com/ApurvBazari/claude-plugins",
  "license": "MIT",
  "keywords": [
    "onboarding",
    "setup",
    "wizard",
    "claude-md",
    "codebase-analysis",
    "plugin-integration",
    "quality-gates",
    "ai-assisted-development"
  ]
}

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.

yesterday First seen · 21 lines scan A c10cd11a17a5

Subscribe to this mod's changes

onboard is a plugin published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Code review Project management Research agentic-workflows ai-driven-development claude-code developer-tools macos notifications

onboard

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

aidd-framework

deckhand

deckhand

claude-code-ghostty

ghostty-notify

beans-prime