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 instructions/jonathanmoore/kona-theme/claude-mdgit clone --depth 1 https://github.com/jonathanmoore/kona-themeWrote 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/instructions/jonathanmoore/kona-theme/claude-md)<a href="https://agentmods.dev/instructions/jonathanmoore/kona-theme/claude-md"><img src="https://agentmods.dev/badge/instructions/jonathanmoore/kona-theme/claude-md.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 | $0.01103 | $0.01103 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
kona-theme CLAUDE.md 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Vite-powered Shopify theme systemwith islands hydration for interactive components. Zero runtime JS dependencies — all interactivity is vanilla Web Components.
Commands
pnpm install # Install dependencies
pnpm dev -- --store <store-name> # Run Shopify + Vite dev servers in parallel
pnpm run build # Build frontend assets to theme/assets
pnpm run deploy # Build + push theme to Shopify
pnpm run lint # ESLint
pnpm run format # Prettier (Liquid + JS + CSS)
pnpm docs:dev # Run docs site locally (VitePress)
pnpm docs:build # Build docs site
Dev runs two servers concurrently: shopify theme dev --path theme (proxies the store) and vite (serves frontend assets with HMR at localhost:5173).
Architecture
Project Layout
theme/ → Shopify theme (assets, blocks, config, layout, locales, sections, snippets, templates, frontend)
scripts/ → Build/utility scripts
docs/ → VitePress documentation site (10 sections, 40 pages)
vite.config.js → Vite config (references theme/ via themeRoot)
package.json → Dependencies and scripts
Islands Hydration System
The core pattern: Liquid renders HTML server-side, interactive components hydrate client-side via Web Components.
theme/frontend/lib/revive.js— Hydration runtime. Usesimport.meta.glob()to map alltheme/frontend/islands/*.jsfiles. Scans the DOM for custom elements with kebab-case names matching island files, then loads them based on hydration directives.theme/frontend/islands/*.js— Each file defines one custom element (extendsHTMLElement, registered withcustomElements.define). These are dynamically imported by revive.js.theme/frontend/entrypoints/theme.js— Main entry point, imports revive and accessibility utilities.
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.
- 4d ago First seen · 97 lines · 1,103 tokens per session scan A 4375a77e25ff
kona-theme CLAUDE.md is an instructions file published in the GitHub repository jonathanmoore/kona-theme (6 stars, last pushed 3mo ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
shopify-theme-builder AGENTS.md
Instructions for moVictor99/shopify-theme-builder, covering agents.md — shopify-theme-builder, three hard constraints (never trade these away), conventions and composition.
vuestrata AGENTS.md
Instructions for boussadjra/vuestrata, covering using vite+, the unified toolchain for the web, built-in commands vs scripts, tool versions, review checklist and vuestrata project rules.
vuestrata CLAUDE.md
Instructions for boussadjra/vuestrata, covering claude.md, the one thing that trips people up, slash commands, verifying and testing reka-backed components.
vuestrata copilot-instructions.md
Instructions for boussadjra/vuestrata, covering copilot instructions, copilot-specific notes and before you finish.
vital AGENTS.md
Instructions for jvidalv/vital, covering ai agent development guide, quick reference, component creation workflow, step 1: determine component level and step 2: create component files.
quiver AGENTS.md
Instructions for go4cas/quiver, covering quiver — ai agent context, folder structure, commands, types and arrow.js rules.