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/mentilead/shopify-app-skillWrote 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/mentilead/shopify-app-skill/review-bfs)<a href="https://agentmods.dev/commands/mentilead/shopify-app-skill/review-bfs"><img src="https://agentmods.dev/badge/commands/mentilead/shopify-app-skill/review-bfs/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/mentilead/shopify-app-skill/review-bfs"><img src="https://agentmods.dev/badge/commands/mentilead/shopify-app-skill/review-bfs.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 | $0.00000 | $0.01175 |
| Opus 5 | $0.00000 | $0.00588 |
| Sonnet 5 | $0.00000 | $0.00235 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
review-bfs 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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Built for Shopify
Audit a Shopify app codebase against Built for Shopify (BfS) certification requirements.
Arguments
$ARGUMENTS = optional focus area (e.g., "polaris only", "security and performance"). If empty, run all categories.
Instructions
-
Read the project's
CLAUDE.mdto discover file paths, conventions, app structure, and any project-specific overrides. Use what you learn to locate admin routes, server files, TOML configs, and billing-related code. -
Parse
$ARGUMENTS. If a specific category is mentioned, run only that category. Otherwise run all 6 categories below. -
Run all applicable category checks in parallel using Grep and Glob tools (not shell commands). For each violation found, record the file path, line number, what's wrong, and how to fix it.
-
Output the structured report described in the Output Format section.
Category 1: Polaris Compliance
Scan admin route files (typically app/routes/app.*.tsx) for:
- Raw HTML elements that should be Polaris components:
<button,<input,<table,<select,<textarea,<form(case-insensitive). Ignore test files. - Inline styles on layout elements:
style=attributes orstyle={{JSX expressions in admin routes. CSS-in-JS or Tailwind in admin UI violates Polaris guidelines. - Missing HydrateFallback — every admin route with a
loadershould export aHydrateFallbackcomponent for Remix streaming. Grep for files that export aloaderbut do not exportHydrateFallback.
Category 2: Performance
Scan server-side files (*.server.ts, *.server.tsx, route loaders/actions) for:
- Sequential awaits that could be parallelized: two or more
awaitstatements on independent calls in the same function that could usePromise.all()orPromise.allSettled(). - Unretried GraphQL mutations —
admin.graphql()mutation calls not wrapped in a retry utility (e.g.,withGraphQLRetry). Shopify recommends retry logic for rate-limited mutations. - Sequential array processing —
for...oforforloops containingawaitthat could usePromise.all()with.map().
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.
- 9d ago First seen · 108 lines · 0 tokens per session scan A 98587d3efc25
review-bfs is a command published in the GitHub repository mentilead/shopify-app-skill (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,175 tokens. 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
autofix-pr
Monitor a pull request and fix code review and CI issues automatically.
reviews-plans
Review all active architecture plans relevant to the current task.
comments
Show cubic's review comments on a pull request.
learnings
Show what this team cares about in code reviews (cubic learnings).
run-review
Run cubic AI code review on local changes.
checklist
Generate a custom checklist for the current feature based on user requirements.