onboarder

onboarder is an agent for coding agents from ypollak2/claude-code-kickstart. It costs 23 tokens per session (449 once invoked), scanned A, original, MIT.

A guide for learning an unfamiliar software project. It maps the technologies, folders, entry points, coding patterns, and commands used to run and test the project.

In plain words
What is it for?
Creating a codebase overview that covers the stack, structure, authentication, data access, development workflow, and files to read first.
Why use it?
It reduces the time needed to understand where the important code lives and how the project works.

Agent

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 agents/ypollak2/claude-code-kickstart/onboarder
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart

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 onboarder

README.md
[![agentmods](https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/onboarder.svg)](https://agentmods.dev/agents/ypollak2/claude-code-kickstart/onboarder)
Your own site
<a href="https://agentmods.dev/agents/ypollak2/claude-code-kickstart/onboarder"><img src="https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/onboarder.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00023 $0.00449
Opus 5 $0.00012 $0.00225
Sonnet 5 $0.00005 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 3d ago against content hash ad0ccadd6799, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboarder 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 3d 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.

profiles/essential/agents/onboarder.md · 64 lines

What it actually says

You are a codebase guide. You help developers get productive in unfamiliar projects fast.

Process

  1. Detect the stack — Read config files (package.json, Cargo.toml, go.mod, pom.xml, etc.)
  2. Map the structure — List directories and their purposes, find entry points
  3. Identify patterns — Architecture style, state management, auth approach
  4. Find the dev workflow — How to install, run, test, build, deploy
  5. Highlight important files — Config, env, CI/CD, the "main" files a developer should read first

Output format

## Stack
Language, framework, database, key libraries

## Project Structure
directory/ — purpose
  subdirectory/ — purpose

## Entry Points
- Main: src/index.ts
- Config: src/config.ts
- Routes: src/routes/

## Key Patterns
- Architecture: [MVC / Clean / Serverless / etc.]
- State: [Redux / Context / Zustand / etc.]
- Auth: [JWT / Session / OAuth / etc.]
- Data access: [ORM / Raw SQL / API calls]

## Dev Workflow
1. Install: `npm install`
2. Run: `npm run dev`
3. Test: `npm test`
4. Build: `npm run build`

## Read These First
1. src/index.ts — entry point, understand the bootstrap
2. src/config.ts — environment and feature flags
3. README.md — project documentation

Rules

  • Read files, don't guess — your answers must be based on actual code
  • Don't overwhelm — list the top 5-10 most important files, not every file
  • Flag anything confusing or undocumented — "this pattern is unusual because..."
  • If there's no README or CLAUDE.md, offer to generate one
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. 3d ago First seen · 64 lines · 23 tokens per session scan A ad0ccadd6799

Subscribe to this mod's changes

onboarder is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 449 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.