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 skills add SalesforceCommerceCloud/b2c-developer-tooling --skill sfnext-performancegit clone --depth 1 https://github.com/SalesforceCommerceCloud/b2c-developer-toolingWrote 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/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-performance)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-performance"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-performance/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/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-performance"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00217 | $0.01859 |
| Opus 5.5 | $0.00087 | $0.00744 |
| Sonnet 5.5 | $0.00043 | $0.00372 |
| Haiku 4.5 | $0.00022 | $0.00186 |
Grade A, and why
sfnext-performance 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 15d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storefront Next Performance
Performance rules are part of AGENTS.md ("Performance & Data Rules") and detailed in docs/README-PERFORMANCE.md, docs/README-SUSPENSE.md, docs/README-IMAGES.md and docs/README-PERFORMANCE-METRICS.md in your project. This skill is the working summary plus a checklist to run on your own diff: PERFORMANCE-REVIEW-CHECKLIST.md.
Core rules
- Server-load data. Await only what SEO, LCP, layout or the HTTP status needs; return promises for the rest (see
storefront-next:sfnext-data-fetching). - One
<Suspense>per async operation, with a skeleton that reserves the final size. Nofallback={null}above the fold unless space is reserved. - Promise identity must be stable across renders: compose in the loader, read from
loaderData/props, neverPromise.all/.then/new Promisein render, neveruseMemoaround a promise. Escape hatches:useState(() => ...)pinning oruseRefre-pinning. - Every
use()/<Await>consumer needs a<Suspense>ancestor; otherwise it blocks the first byte of the streamed shell. - Heavy or hidden UI (modals, drawers, dialogs, rich editors) is
React.lazyand mounted only while needed. - Shape data in the loader, not in render.
- Hints and third-party scripts cost: preconnect only to origins used on every page; load scripts
async/defer.
Lazy modals and drawers
import { lazy, Suspense, useState } from 'react';
import { useDeferredUnmount } from '@/hooks/use-deferred-unmount';
const SizeGuide = lazy(() => import('@/components/size-guide').then((m) => ({ default: m.SizeGuide })));
export function SizeGuideButton() {
const [open, setOpen] = useState(false);
const mounted = useDeferredUnmount(open); // stays mounted briefly after close for the exit animation
return (
<>
<button onClick={() => setOpen(true)}>Size guide</button>
{mounted && (
<Suspense fallback={null}>
<SizeGuide open={open} onOpenChange={setOpen} />
</Suspense>
)}
</>
);
}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed · -30 lines · +161 tokens per session 7ada21242208
- 1mo ago First seen · 133 lines · 56 tokens per session scan A cd9f73aa0643
sfnext-performance is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (56 stars, last pushed today), licensed Apache-2.0. It adds 217 tokens to every session and 1,859 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
shopping
Skill "shopping" from Hmbown/Codewhale, covering shopping, when to use, setup, workflow and non-goals.
daiso-cli
A command-line interface for searching Daiso and related Korean shopping, store, food, cinema, and convenience-store data through the Daiso project. It can return structured JSON for searches and comparisons.
goofish-publish-item
A workflow for publishing second-hand items on Xianyu, a Chinese marketplace for used goods. It turns an item description and images into a category, title, listing text, and a ready-to-submit listing.
goofish-reply-buyer
A Chinese-language workflow for handling buyer messages on Xianyu, a Chinese second-hand marketplace. It reviews conversations, classifies buyer intent, and drafts replies according to the seller’s rules, but waits for human approval before sending.
goofish-shop-diagnosis
A read-only diagnostic workflow for Xianyu shops and listings. It compares how a shop’s items appear in marketplace search with their stored details to investigate visibility and sales problems.
booking-cli
Searches Booking.com from the terminal via cli-web-booking — find hotels, apartments, and hostels by destination, dates, and guests; get property details by slug; resolve destination names to IDs. Use when the user asks about Booking.com, hotel search, accommodation prices, property ratings, or comparing places to…