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.
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.
npx agentmods add skills/cbrock84/headcount/interface-craftnpx skills add cbrock84/headcount --skill interface-craftgit clone --depth 1 https://github.com/cbrock84/headcountWrote 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.
[](https://agentmods.dev/skills/cbrock84/headcount/interface-craft)<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>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 | $0.00079 | $0.00838 |
| Opus 5 | $0.00039 | $0.00419 |
| Sonnet 5 | $0.00016 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
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.
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.
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.
- yesterday First seen · 79 lines · 79 tokens per session scan A cd3432107db1
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.
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.
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…
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.
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.
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.
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.