create-onboarding-guide

create-onboarding-guide is a skill for Claude Code from atman-33/workhub. It costs 66 tokens per session (928 once invoked), scanned A, original, MIT.

A tool that creates a self-contained HTML tour of a code repository, including its structure, architecture, important flows, and a suggested reading order.

In plain words
What is it for?
Use it to prepare onboarding material for a repository, a team member, or an external contributor.
Why use it?
It gives new engineers a single guide for understanding an unfamiliar codebase and finding the relevant files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the engineering plugin — 18 skills, 4 agents, 2 MCP servers shipped together

Good fit Use it to prepare onboarding material for a repository, a team member…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add atman-33/workhub
Claude Code
/plugin install engineering

Made for: Claude Code.

Or install engineering, the plugin that ships this one along with the rest of its 18 skills, 4 agents, 2 MCP servers.

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 create-onboarding-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/atman-33/workhub/create-onboarding-guide.svg)](https://agentmods.dev/skills/atman-33/workhub/create-onboarding-guide)
Your own site
<a href="https://agentmods.dev/skills/atman-33/workhub/create-onboarding-guide"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-onboarding-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 928 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 $0.00066 $0.00928
Opus 5 $0.00033 $0.00464
Sonnet 5 $0.00013 $0.00186
Haiku 4.5 $0.00007 $0.00093

Measured 6d ago against content hash 7a5892fe1e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-onboarding-guide 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 6d 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.

plugins/engineering/skills/create-onboarding-guide/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Onboarding Guide

Produce one self-contained HTML file that takes a newcomer from zero to "I know where things live and how the main flows run" in one sitting.

1. Resolve the output directory

Same per-installer configuration as this plugin's other guide skills:

  1. ${CLAUDE_PLUGIN_ROOT}/config.jsonoutputDir (shared across this plugin's skills)
  2. config.json next to this SKILL.md → outputDir (skill-level override)
  3. Neither exists → read config.example.json for the shape, ask the user for a real absolute path, then write the skill-level config.json (git-ignored).

Honor openAfterGenerate (default true).

2. Confirm the target

Confirm which repository (and, for a monorepo, which package/area) the guide covers, and who it's for (new engineer on the team vs. external contributor) — that decides how much project-specific context to assume. Default: the whole current repo, for a new team engineer.

3. Explore the codebase — the guide is only as true as this step

  • Map the layout: top-level directories, build/config files, README/docs.
  • Identify the architecture: layers/modules and the dependencies between them, traced from real imports/references (Grep), not directory names alone.
  • Trace 2–3 key flows end-to-end (e.g. a request from route → handler → service → persistence; app startup; the primary user action). Record actual file:line hops.
  • Note conventions a newcomer must know: naming patterns, where tests live, how config/env is loaded, codegen or other "don't edit by hand" areas.
  • Completion criterion: every module in the architecture diagram and every hop in a flow walkthrough is backed by a file you actually read.

4. Generate the HTML guide

One self-contained .html file: inline <style>, <script>, SVG — no CDN. Prose in the user's conversation language; identifiers and paths as-is. Sections, in order:

  1. Header — repo, purpose in one sentence, tech stack, date generated.
  2. Architecture diagram — inline SVG of layers/modules with dependency arrows; a legend; each node listing its main directory.
  3. Directory map — collapsible tree of the significant directories, each with a one-line role ("what lives here / when you'd touch it"). Skip vendored/generated noise.
  4. Key flow walkthroughs — one per traced flow: a numbered sequence diagram (SVG) plus a step table of file → function → what happens.
  5. Conventions & gotchas — the step-3 conventions list, including anything marked "don't edit by hand".
  6. Recommended reading order — an ordered path of ~5–10 files to read first, each with one line on why it's on the path.
  7. Getting started — real setup/build/test commands taken from the repo's README or scripts, in copyable code blocks.

Read the full file on GitHub · 82 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 82 lines · 66 tokens per session scan A 7a5892fe1e4b

Subscribe to this mod's changes

create-onboarding-guide is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 928 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

gonavi-cli

Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…

Syngnat/GoNavi · 144 tokens

教程类H5-小红书小工具

A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.

huangrichao2020/pretty-skills · 110 tokens

sansheng-distill

A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.

huangrichao2020/pretty-skills · 108 tokens

explain

Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…

harnessprotocol/harness-kit · 95 tokens

academic-paper-workflow

Use when a user needs to plan, compose, or revise an academic paper in a staged workflow.

Natsummerance/readMD · 25 tokens

beginner-tone

A set of Korean-language conversation and safety instructions for people new to coding and AI. It tells the assistant to explain difficult terms and guide the user with one clear next action.

sodam-ai/SoDam-Harness-Eng · 34 tokens