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/khadinakbarlabs/shopify-app-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/commands/khadinakbarlabs/shopify-app-builder/start-shopify-app)<a href="https://agentmods.dev/commands/khadinakbarlabs/shopify-app-builder/start-shopify-app"><img src="https://agentmods.dev/badge/commands/khadinakbarlabs/shopify-app-builder/start-shopify-app/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/khadinakbarlabs/shopify-app-builder/start-shopify-app"><img src="https://agentmods.dev/badge/commands/khadinakbarlabs/shopify-app-builder/start-shopify-app.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 | $0.00014 | $0.00380 |
| Opus 5.5 | $0.00006 | $0.00152 |
| Sonnet 5.5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
start-shopify-app 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 14d 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
start-shopify-app
Skills: using-shopify-app-builder, shopify-project-copilot, app-framework
Read the named skills from this plugin before following the workflow. Use only the relevant ones; commands guide work rather than grant permissions.
- Inspect available project context first. Clarify only the merchant task or next dependent decision that is genuinely missing.
- Recommend one small MVP and the next milestone; don't assume all integrations/extensions are needed.
- Preserve an existing stack. Use shopify-connections only when the next live operation needs it; don't block local implementation on account setup or optional market validation.
- Maintain Done / Next / Blocked / Not tested; explain one small action and success signal at a time.
- Offer local context for an ongoing project, explain what is saved, and preserve unknowns. Choose one next milestone and a concise cross-session handoff; no tracking or mandatory schedule.
Beginner-friendly delivery
Explain unfamiliar terms once, recommend one next action and state the expected result before executing. Preserve unrelated work. Never read credential caches or print secrets. Paid runs, store writes, scope/access expansion, charges, deployment and submission require explicit task-specific authorization.
Completion evidence
For a planning request: an agreed merchant problem and concrete next step. For a build request: implement the first merchant feature with affected tests, authenticated shop isolation and loading/empty/error states as relevant. See the router's first-merchant-value reference. A plan or record alone is not a built app; leave live checks explicitly unverified when unavailable. Show actual results, the remaining blocker and the next step; do not print anticipated success checkmarks. If the host cannot register commands, invoke the listed skills in ordinary language instead.
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.
- 14d ago Changed 4b69fedc7fff
- 15d ago Changed · +1 lines d1ddc49e357c
- 17d ago First seen · 25 lines · 14 tokens per session scan A 7b225b403e60
start-shopify-app is a command published in the GitHub repository khadinakbarlabs/shopify-app-builder (2 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 380 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.
Other commands, from other repositories
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.
feedback
Review comments on your display.dev artifacts, then apply them, reply, and resolve the threads after you approve.
project_init
A command that starts tracking a project with ocul-pm by creating its project records and agent logging rules.
tray-referencia-api
Referência rápida de todos os endpoints da API da Tray, aceita nome do recurso como filtro.
analysis-next
Advance the current analysis to the next ALIVE stage.
analysis-retro
Generate an automatic retrospective report from archived analyses.