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/movictor99/shopify-theme-builder/agents-mdgit clone --depth 1 https://github.com/moVictor99/shopify-theme-builderWrote 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/movictor99/shopify-theme-builder/agents-md)<a href="https://agentmods.dev/instructions/movictor99/shopify-theme-builder/agents-md"><img src="https://agentmods.dev/badge/instructions/movictor99/shopify-theme-builder/agents-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 | $0.01564 | $0.01564 |
| Opus 5 | $0.00782 | $0.00782 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
shopify-theme-builder AGENTS.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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — shopify-theme-builder
Cross-agent entry point (the agents.md convention, read automatically by OpenAI Codex, Cursor, Zed, Gemini CLI, and others). If you are a coding agent asked to build, generate, scaffold, or design a Shopify theme, follow the instructions here. They mirror
SKILL.md(the native format for Claude Code / Claude apps) — both describe the same workflow.
You build production-grade, Online Store 2.0 (OS 2.0) Shopify themes that a
non-technical merchant can run entirely from the theme editor, that pass
shopify theme check with zero errors, and that meet Shopify Theme Store
requirements. Do not generate the whole theme in one pass — move through the
gated phases below and checkpoint with the user.
Read these when the relevant phase needs them (progressive disclosure)
SKILL.md— the full workflow, phase gates, and token vocabulary (start here).references/reliability-and-sync.md— read this first. The import/sync landmines that passtheme-checkbut break the store (silently dropped sections, 404s, dead color schemes, broken add-to-cart). Enforced byscripts/validate_theme.py.references/shopify-standards.md— official standards + Theme Store rules.references/settings-control.md— the "100% theme-editor controllable" rulebook.references/os2-architecture.md— JSON templates, sections, blocks, section groups.references/design-tokens.md— settings_schema ↔ CSS custom properties.references/liquid-patterns.md,references/i18n-rtl.md,references/accessibility.md,references/performance.md,references/seo-structured-data.md— the quality references.references/interview.md— the Phase 0 question bank.references/qa-checklist.md— the Phase 6 pass/fail checklist.assets/theme-skeleton/— the scaffold base to copy.examples/section-hero.liquid— the reference section every new section copies.
Three hard constraints (never trade these away)
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 · 106 lines · 1,564 tokens per session scan A 2d97aa6a602f
shopify-theme-builder AGENTS.md is an instructions file published in the GitHub repository moVictor99/shopify-theme-builder (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,564 tokens to every session, about $0.0078 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
kona-theme CLAUDE.md
Instructions for jonathanmoore/kona-theme, covering claude.md, what this is, commands, architecture and project layout.
talisman-skill AGENTS.md
Instructions for jeunecraack/talisman-skill, covering talisman — agent playbook (v1), when to run, workflow (8 phases), key features and repo structure.
codemap AGENTS.md
Instructions for beadnall/codemap, covering codemap, if you are claude, if you are grok build, if you are another agent and the short version.
codemap copilot-instructions.md
Instructions for beadnall/codemap: This repository holds a skill for turning a codebase into an explorable isometric diagram. The full instructions are in SKILL.md — read that file and follow it when asked to map, diagram or visually explain how a system fits together.
crypto-claude-skills AGENTS.md
Instructions for Vo1ganin/crypto-claude-skills, covering agents.md, skills, operating rules, read-only by default and credentials.
ai-saas-starter CLAUDE.md
Instructions for nikandr-surkov/ai-saas-starter, a project described as: AI SaaS boilerplate for Next.js 16 — Better Auth, Stripe subscriptions, credits system, AI image generation. AI-native: AGENTS.md, Claude Code skills & hooks.