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/juliusbrussee/caveman-code/cavekit-design-systemnpx skills add JuliusBrussee/caveman-code --skill cavekit-design-systemgit clone --depth 1 https://github.com/JuliusBrussee/caveman-codeWrote 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/juliusbrussee/caveman-code/cavekit-design-system)<a href="https://agentmods.dev/skills/juliusbrussee/caveman-code/cavekit-design-system"><img src="https://agentmods.dev/badge/skills/juliusbrussee/caveman-code/cavekit-design-system.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 5.1 | $0.00062 | $0.04696 |
| Opus 5 | $0.00031 | $0.02348 |
| Sonnet 5 | $0.00012 | $0.00939 |
| Haiku 4.5 | $0.00006 | $0.00470 |
Grade A, and why
cavekit-design-system 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System: DESIGN.md for AI Agents
Core Principle: DESIGN.md Describes WHAT It Looks Like, Not HOW to Build It
DESIGN.md is the visual equivalent of kits. It defines the project's visual language — colors, typography, spacing, components, responsive behavior — in a format AI agents can read and apply consistently. It is a parallel constraint layer that all Hunt phases consult.
| Document | Defines | Audience |
|---|---|---|
| CLAUDE.md | How to build the project | Coding agents |
| Kits | What must be true (behavior) | All agents |
| DESIGN.md | What it looks like (visual) | UI-building agents |
| Plans | How to build it (tasks) | Builder agents |
Why a Dedicated Design System Document?
Without DESIGN.md, visual decisions scatter across kits, plans, and code:
- Colors get hardcoded differently per component
- Typography choices vary between agents and sessions
- Spacing becomes inconsistent across the UI
- New components reinvent patterns that already exist
DESIGN.md centralizes these decisions. Every agent reads it before writing UI code.
The 9-Section Stitch Format
DESIGN.md follows the Google Stitch format — 9 sections that together define a complete visual language. Every DESIGN.md must contain all 9 sections.
Section 1: Visual Theme & Atmosphere
The design philosophy, mood, and overall aesthetic. Use evocative, specific language — not generic terms like "clean and modern."
## 1. Visual Theme & Atmosphere
This is a warm editorial experience built on natural materials. Think: a well-curated
bookshop with soft overhead lighting and carefully chosen display shelves. The density
is low — generous whitespace signals confidence and clarity. Every element earns its
place; nothing decorative exists without functional purpose.
**Key attributes:** Warm, unhurried, editorial, confident
**Density:** Low — generous whitespace, single-column focus
**Personality:** Thoughtful librarian, not flashy storefront
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.
- 6d ago First seen · 526 lines · 62 tokens per session scan A 7568f279d910
cavekit-design-system is a skill published in the GitHub repository JuliusBrussee/caveman-code (931 stars, last pushed 22d ago), licensed MIT. It adds 62 tokens to every session and 4,696 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…