interface-craft

interface-craft is a skill for Claude Code, Codex from cbrock84/headcount. It costs 79 tokens per session (838 once invoked), scanned A, original, MIT.

An interface-quality guide for improving layout, visual hierarchy, typography, spacing, density, and interaction details.

In plain words
What is it for?
It helps refine screen layouts, choose a clear primary action, set type and spacing scales, improve readability, and finish interface states.
Why use it?
It helps explain why a working screen still feels unfinished or crowded. It turns vague visual problems into specific design decisions.

Skill for Claude CodeCodex

Part of the product plugin — 11 skills shipped together

About the project

headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.

cbrock84/headcount · 1,247 stars · on GitHub

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 skills/cbrock84/headcount/interface-craft
Any agent
npx skills add cbrock84/headcount --skill interface-craft
Clone the repo
git clone --depth 1 https://github.com/cbrock84/headcount

Made for: Claude Code, Codex.

Or install product, the plugin that ships this one along with the rest of its 11 skills.

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 interface-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/cbrock84/headcount/interface-craft.svg)](https://agentmods.dev/skills/cbrock84/headcount/interface-craft)
Your own site
<a href="https://agentmods.dev/skills/cbrock84/headcount/interface-craft"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/interface-craft.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 838 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 $0.00079 $0.00838
Opus 5 $0.00039 $0.00419
Sonnet 5 $0.00016 $0.00168
Haiku 4.5 $0.00008 $0.00084

Measured yesterday against content hash cd3432107db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interface-craft 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 yesterday.

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/product/skills/interface-craft/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interface craft

Most interfaces do not fail on ideas. They fail on execution — spacing that is nearly consistent, hierarchy that is nearly clear, type that is nearly right.

Diagnose before restyling

Ask what the screen is for. One primary action, at most one secondary. If you cannot name the primary action, the layout problem is a product problem and no amount of styling fixes it.

The things that actually read as quality

Hierarchy. A viewer should know where to look before they read anything. Achieve it with size, weight, and space — in that order. Color is the weakest hierarchy tool and the most overused.

Spacing rhythm. Related things sit closer than unrelated things, and the gaps come from one scale. Inconsistent spacing is the defect people feel but cannot name. Get proximity right and a plain layout reads as designed.

Type. One family for the interface, two at most on the page. Set a real scale and use its steps rather than inventing sizes. Body text wants a comfortable measure — roughly 60–75 characters — and line height that grows as the measure widens.

Restraint in surfaces. Borders, shadows, and fills all separate things. Pick one per boundary. Stacking all three is why interfaces look busy at normal density.

Alignment. Everything lines up with something. An element aligned to nothing reads as a mistake even when it is intentional.

Density is a decision

An information-dense tool and a marketing page want opposite treatments. Decide which this is and commit — the uncomfortable middle, where a data table has landing-page padding, serves neither.

Finish the states

Loading, empty, error, and overflow are where products feel unfinished. An empty state is a design opportunity; a spinner with no context is an admission. Long strings, long lists, and small screens must all be handled, not hoped about.

Dark mode is a palette, not an inversion

Inverting a light theme produces the characteristic bad dark mode: pure black backgrounds, pure white text, and shadows that do nothing.

Read the full file on GitHub · 79 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. yesterday First seen · 79 lines · 79 tokens per session scan A cd3432107db1

Subscribe to this mod's changes

interface-craft is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 838 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 2026-09-03.

Related

Other skills, from other repositories

swiftui-liquid-glass

Design, implement, review, and validate SwiftUI Liquid Glass interfaces across iOS and macOS. Use when choosing native glass effects, grouped glass surfaces, glass button styles, morphing transitions, availability fallbacks, or removing conflicting custom chrome.

gaelic-ghost/socket · 55 tokens

shiny-bslib

Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…

posit-dev/skills · 107 tokens

save

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

XTSoftwareLabs/neatcontext-plugins · 49 tokens

mode

Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other NeatContext host. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.

XTSoftwareLabs/neatcontext-plugins · 50 tokens

status

Report the NeatContext context and routing mode active in Codex, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.

XTSoftwareLabs/neatcontext-plugins · 39 tokens

list

List the local NeatContext Contexts available to Codex. Use when the user asks what contexts exist, what can be connected, or explicitly invokes this skill.

XTSoftwareLabs/neatcontext-plugins · 35 tokens