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.
git clone --depth 1 https://github.com/jameywarren/shopify-claude-quickstartWrote 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/commands/jameywarren/shopify-claude-quickstart/validate-templates)<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/validate-templates"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/validate-templates/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/validate-templates"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/validate-templates.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00407 |
| Opus 5 | $0.00009 | $0.00204 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
validate-templates 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 8d 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.
What it actually says
Validate that every block referenced in the theme's template JSON files has settings keys that match what the section schema actually defines. This catches the case where a section's Liquid was updated (settings renamed or removed) but the template JSON still references old key names.
Work entirely from local files in store-data/theme/. No API calls needed.
Step 1 — Find templates to check
If $ARGUMENTS is provided, use it as a glob (e.g. templates/page.*.json).
Otherwise check all templates: templates/*.json and templates/customers/*.json.
Step 2 — For each template
Parse the JSON. For every section entry and every block entry within it:
- Identify the block
type(this maps to a section or block file in the theme) - Collect every
settingskey present in the template JSON for that block - Find the corresponding section file: check
sections/{type}.liquid, thenblocks/{type}.liquid - Parse the
{% schema %}tag from that Liquid file and extract all defined settingidvalues - Compare: flag any settings key in the JSON that does not appear in the schema's setting ids
Step 3 — Report
For each mismatch found:
DRIFT: templates/page.wall-of-sound.json
Section: sections/featured-collection.liquid
Block type: standard_pick (line 47)
Stale keys in JSON: standard_pick
Current keys in schema: standard_name, standard_url
If no mismatches: "All templates valid — no schema drift detected."
Do not modify any files. Output only. Run /safe-push or fix the JSON manually after reviewing the report.
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.
- 8d ago First seen · 46 lines · 18 tokens per session scan A 6975aa3a73d7
validate-templates is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 407 once invoked, about $0.0001 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 commands, from other repositories
implement-plan
Deliver a docs/plans plan end to end — settle open questions, implement with the changed specs green locally and the full suite on CI, two code reviews plus a simplify pass, a migrated and seeded QA environment ready to start, schema review, and an open, monitored pull request on spree/spree.
stripe-test
Test Stripe checkout flows with any persona using official test cards. Simulates payment experiences with realistic user behavior and generates payment-specific reports.
wake-test-plan
Generate a test plan for a Wake Commerce storefront feature. Defines E2E scenarios, contract tests, and acceptance criteria. Delegates detailed test design to the wake-qa-expert agent.
checkout-tdd
You are a senior E-commerce & Retail specialist applying E-commerce Engineering Skills methodology.
payment-tdd
You are a senior E-commerce & Retail specialist applying E-commerce Engineering Skills methodology.
CLAUDE_CODE_POTAL_COMPLETE_VERIFICATION
A command for fully checking a total landed cost system across product categories, customs duty, VAT or GST, de minimis rules, special taxes, customs fees, and trade remedies.