gitmesh: Skill for Claude Code

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

design-guide is a skill for Claude Code from LF-Decentralized-Trust-labs/gitmesh. It costs 83 tokens per session (3,171 once invoked), scanned A, original, Apache-2.0.

A UI design guide for GitMesh Agents, a dark, keyboard-focused interface for managing coding agents. It defines the visual rules, reusable components, layout choices, and project conventions.

In plain words
What is it for?
Use it when creating or changing frontend components, pages, features, styling, or other parts of the GitMesh Agents interface.
Why use it?
It helps new interface work look and behave consistently with the rest of the product instead of introducing unrelated styles or interactions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is LF-Decentralized-Trust-labs/gitmesh's own configuration. It tells Claude Code how to work on gitmesh 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 gitmesh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LF-Decentralized-Trust-labs/gitmesh. 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/LF-Decentralized-Trust-labs/gitmesh/main/.claude/skills/design-guide/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LF-Decentralized-Trust-labs/gitmesh

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 design-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/lf-decentralized-trust-labs/gitmesh/design-guide.svg)](https://agentmods.dev/skills/lf-decentralized-trust-labs/gitmesh/design-guide)
Your own site
<a href="https://agentmods.dev/skills/lf-decentralized-trust-labs/gitmesh/design-guide"><img src="https://agentmods.dev/badge/skills/lf-decentralized-trust-labs/gitmesh/design-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,171 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 $0.00083 $0.03171
Opus 5 $0.00042 $0.01586
Sonnet 5 $0.00017 $0.00634
Haiku 4.5 $0.00008 $0.00317

Measured 7d ago against content hash bdbbc95719eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

design-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 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/design-guide/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitMesh Agents Design Guide

This guide is split into:

  • Section A - Foundations. What the system is, what it's built on, and the tokens you draw from.
  • Section B - Building blocks. Components, when to make new ones, how to compose them.
  • Section C - Working in the codebase. File conventions, the showcase page, common mistakes.

Use this skill alongside frontend-design (visual polish) and web-design-guidelines (web best practices).


Section A - Foundations

A.1 Stance

GitMesh Agents is a professional control plane - dense, keyboard-driven, dark-themed by default. Every pixel earns its place.

The five non-negotiable principles:

  1. Density beats padding. Show information without requiring clicks. Whitespace separates; it does not pad.
  2. Keyboard-first. Global shortcuts (Cmd+K, C, [, ]). Power users rarely touch the mouse.
  3. Contextual, not modal. Inline editing over dialogs. Dropdowns over page navigations.
  4. Dark-themed by default. Neutral grays (OKLCH), not pure black. Accent colour reserved for status / priority. Text is the primary visual element.
  5. Component-driven. Reusable components capture conventions. Build at the right abstraction - not too granular, not monolithic.

A.2 Stack

Concern Choice
Framework React 19 + TypeScript + Vite
Styling Tailwind CSS v4 with CSS variables (OKLCH)
UI primitives shadcn/ui (new-york style, neutral base, CSS variables on)
Accessibility Radix UI primitives
Icons Lucide React (16px nav, 14px inline)
Variants class-variance-authority (CVA)
Class merging clsx + tailwind-merge via the cn() utility

Path aliases live in ui/components.json: @/components, @/components/ui, @/lib, @/hooks.

A.3 Tokens

All tokens are CSS variables in ui/src/index.css. Both light and dark themes use OKLCH. Never use raw hex / rgb values - always use a semantic token.

Colour tokens
Token pair Used for
--background / --foreground Page background and primary text
--card / --card-foreground Card surfaces
--primary / --primary-foreground Primary actions and emphasis
--secondary / --secondary-foreground Secondary surfaces
--muted / --muted-foreground Subdued text and labels
--accent / --accent-foreground Hover states and active nav
--destructive Destructive actions
--border All borders
--ring Focus rings
--sidebar-* Sidebar-specific variants
--chart-1...--chart-5 Data visualisation

Read the full file on GitHub · 341 lines

Files

What ships with it

1 file 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. 7d ago First seen · 341 lines · 83 tokens per session scan A bdbbc95719eb

Subscribe to this mod's changes

design-guide is a skill published in the GitHub repository LF-Decentralized-Trust-labs/gitmesh (143 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 3,171 once invoked, about $0.0004 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 2026-08-30.