What is onboard-from-code?

A command that builds a brand guide for the current code repository by reading files such as its README, package settings, and styling configuration.

Create a brand guide and start a Vibiz project from a local repository without scraping a website.

It helps when a project has no public website to study, or when the code better represents its identity than the website does.

onboard-from-code — Command for Claude Code by Vibiz-ai

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.

Clone the repo

git clone --depth 1 https://github.com/Vibiz-ai/vibiz-claude-plugin

Made for: Claude Code.

Or install vibiz, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 1 agent, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code/github.svg)](https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code)

Your own site

<a href="https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code"><img src="https://agentmods.dev/badge/commands/vibiz-ai/vibiz-claude-plugin/onboard-from-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,083 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01083
Opus 5	$0.00017	$0.00541
Sonnet 5	$0.00007	$0.00217
Haiku 4.5	$0.00003	$0.00108

Measured 9d ago against content hash af4cb8c6d049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

onboard-from-code 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 9d 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/vibiz/commands/onboard-from-code.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vibiz:onboard-from-code

For projects with no public marketing site (devtools, libraries, internal tools), or when the codebase is a more canonical brand source than a marketing site. Reads the local repo, synthesizes a brand kit, and creates a vibiz directly — no Firecrawl scrape, no ~30-60s wait.

Steps

MCP gate. Try list_vibiz. If unauthed → tell user /mcp → vibiz → Authenticate → re-run. Stop.
Match against existing vibizes by company name (read package.json name and the README intro paragraph). If you find a clear match (same project, same brand), tell the user and stop:
```
✓ Found an existing vibiz that looks like this project: "<name>" (slug: <slug>)
   Reusing it. To force-create a new one, say: /vibiz:onboard-from-code --force
```
Read the repo to synthesize the brand payload. Read in this order, stop pulling once you have enough signal:
- package.json — name, description, homepage, dependencies (for framework / component-lib detection).
- pyproject.toml / Cargo.toml / go.mod — name + description fallback when no package.json.
- README.md or README.mdx — first ~200 lines. Use the intro paragraph as headline, the "Features" / "Why X" sections for description and keyFeatures, the writing style for tone.
- tailwind.config.{js,ts} — extract theme.extend.colors into brand.colors (primary, secondary, accent).
- app/globals.css / src/index.css / similar — :root { --primary: ... } CSS variables fall back here.
- next.config.{js,ts} — confirm framework. Check dependencies for react/next/vite/fastapi/axum/etc.
- Component imports (grep for @radix-ui, shadcn, @chakra-ui, @mui) → componentLibrary.
Refuse to invent values. If you can't detect a color, leave it out — don't guess. The MCP tool accepts partial payloads. Same for logoUrl — only set it if there's a CDN-hosted logo URL in the README (e.g. a public S3 / Vercel asset). Don't pass local paths like ./public/logo.svg.

Read the full file on GitHub · 63 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.

9d ago First seen · 63 lines · 35 tokens per session scan A af4cb8c6d049

Subscribe to this mod's changes

onboard-from-code is a command published in the GitHub repository Vibiz-ai/vibiz-claude-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,083 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 2026-08-31.

Design and UX Frontend

seed-create-component

A command for creating a new SEED Design component, including its source specification, recipes, React implementation, documentation, examples, and optional headless layer.

daangn/seed-design · 12 tokens

sddesign

Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.

educlopez/ui-craft · 46 tokens

craft

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.

educlopez/ui-craft · 64 tokens

onboard-from-code