bobi-agent: Skill for Claude Code

.claude/skills/bobi-design/SKILL.md

bobi-design is a skill for Claude Code from moda-labs/bobi-agent. It costs 60 tokens per session (736 once invoked), scanned A, original, Apache-2.0.

A design guide and asset library for Bobi, an open-source framework for teams of coding agents. It provides visual rules, reusable interface components, fonts, colours, and other design assets for production interfaces or prototypes.

In plain words
What is it for?
Use it to build or prototype Bobi screens, choose approved colours and typography, inherit design tokens, and use documented React components and UI kits.
Why use it?
It gives Bobi projects a shared visual language so interfaces do not have to be designed from scratch or styled inconsistently. The guide also identifies the files that serve as the source of truth for the design system.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

This is moda-labs/bobi-agent's own configuration. It tells Claude Code how to work on bobi-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bobi-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to moda-labs/bobi-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/moda-labs/bobi-agent/main/.claude/skills/bobi-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moda-labs/bobi-agent

Made for: Claude Code.

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 bobi-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/moda-labs/bobi-agent/bobi-design.svg)](https://agentmods.dev/skills/moda-labs/bobi-agent/bobi-design)
Your own site
<a href="https://agentmods.dev/skills/moda-labs/bobi-agent/bobi-design"><img src="https://agentmods.dev/badge/skills/moda-labs/bobi-agent/bobi-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 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 $0.00060 $0.00736
Opus 5 $0.00030 $0.00368
Sonnet 5 $0.00012 $0.00147
Haiku 4.5 $0.00006 $0.00074

Measured 7d ago against content hash f4a85240e67b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bobi-design 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 7d 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.

.claude/skills/bobi-design/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bobi design system

The system itself lives at docs/design-system/ in this repo, not here.

This file is only the entry point that makes it invocable as /bobi-design. The assets are a product artifact — the source of truth for anything visual on any Bobi surface — so they live under docs/ where anyone can find them, whether or not they use Claude Code. .claude/ is tooling config; a design system is not.

Start here

  1. Read docs/design-system/README.md — the design guide: sources, content fundamentals, visual foundations, iconography, the enterprise app layer, and the four rules that matter most. Read this first.
  2. Read docs/design-system/SKILL.md for the fast orientation and the non-negotiables.
  3. Then explore what you need:
    • docs/design-system/styles.css — link this one file to inherit every token.
    • docs/design-system/tokens/ — colors, typography, spacing, surfaces, motion.
    • docs/design-system/components/*/ — each has <Name>.jsx, <Name>.d.ts (props + adherence rules), <Name>.prompt.md (what/when + example).
    • docs/design-system/ui_kits/control-plane/index.html — open this to see the product surface assembled.
    • docs/design-system/guidelines/*.card.html — foundation specimens.

The four rules that matter most

  1. Violet is state, not decoration. Live, enforced, gated, focused. If it isn't one of those, it's clay, ink, or muted.
  2. Gates are sacred. A human approval step always renders with the violet left rail + 4% wash + rotated-square glyph, and always names the workflow and step that stopped. Never a toast.
  3. Config is the interface. Show real filenames, real YAML, real shell.
  4. The Moda Labs byline travels with the lockup. Always.

Also load-bearing: mono is for data (paths, ids, crons, code) and sans for chrome; product chrome is lowercase, with uppercase only on document plate labels and corner marks; Bobi's own hand-drawn icon set only — never Lucide, Heroicons, or emoji; Moda Labs' red #FD4235 never appears on a Bobi surface.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 60 tokens per session scan A f4a85240e67b

Subscribe to this mod's changes

bobi-design is a skill published in the GitHub repository moda-labs/bobi-agent (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 60 tokens to every session and 736 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

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens