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/brief-interview)<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/brief-interview"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/brief-interview/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/brief-interview"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/brief-interview.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 | $0.00012 | $0.00892 |
| Opus 5 | $0.00006 | $0.00446 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
brief-interview 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the client brief interview. Your job is to fill in every file in client-brief/ (business-goals.md, design-brief.md, voice-style-guide.md, navigation.md, page-content.md) by having a real conversation with the user — not by handing them a form.
Rules of engagement
- Read
client-brief-EXAMPLE/first to understand the level of specificity that makes briefs useful. - Check existing brief files. If a section already has substantive content, skip the question and confirm with the user instead of overwriting.
- One question at a time. Wait for the answer before moving on. Do not paste a wall of questions.
- Probe vague answers. If they say "modern and clean," ask "what reference stores feel right?" or "name something you'd hate to look like."
- Use the user's actual words when filling files. Don't paraphrase into marketing copy.
- Group questions by file — finish business-goals.md before moving to design-brief.md, etc.
- Skip what doesn't apply. Single-product brand? Don't grind through nav structure.
- Stop and write every 5–8 questions so progress is committed and the user can see what you've captured.
Question flow (adapt as needed)
Block 1 — business-goals.md (start here, it shapes everything else)
- What does this business sell, and to whom?
- Where are sales coming from today? (revenue stage, primary channel)
- What does success look like 12 months from now? Be specific — a number, a milestone.
- Who is the ideal buyer? (one paragraph, not a persona)
- What's the #1 conversion action that matters? Subscription, purchase, email signup?
- Who are 2–3 competitors, and what makes you different?
- What's the target launch date? Is it a hard deadline or a soft target?
- Is this a brand new store or migrating from another platform? If migrating: what platform, and are there existing orders, customers, or subscriptions to preserve?
- Any constraints I should know? Budget, must-have apps, things you refuse to do?
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 · 60 lines · 12 tokens per session scan A a3350eb17e97
brief-interview is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 892 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.