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-revalidationgit 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-revalidation)<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-revalidation"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-revalidation/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-revalidation"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/sfnext-revalidation.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 | $0.00201 | $0.01869 |
| Opus 5.5 | $0.00080 | $0.00748 |
| Sonnet 5.5 | $0.00040 | $0.00374 |
| Haiku 4.5 | $0.00020 | $0.00187 |
Grade A, and why
sfnext-revalidation 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storefront Next Revalidation
React Router re-runs loaders after every action submission. A storefront has deep route trees, persistent fetchers (mini-cart) and lazy modals (quick view), so one add-to-cart can re-run many loaders that never read the basket, each with its own SCAPI fan-out. This skill is how to keep only the re-runs that are needed. The authoritative guide is docs/README-REVALIDATION.md in your project; read it before changing policy.
What revalidates
An action submission (<Form>, useSubmit, fetcher.submit) re-runs the whole active set:
- the matched route chain (root, layouts, leaf),
- mounted resource fetchers (
fetcher.load()of a resource route whose component is still mounted), - fetchers inside open modals, drawers and sheets.
A raw fetch(), a SCAPI client call, or fetcher.load() is not a submission and triggers nothing. A route that only exports an action fires revalidation but has no loader to re-run.
When a re-run is justified
For each pair (action, active loader) it is justified only if both are true:
- Overlap: the action result changes something the loader reads.
- Value not already available: the new value does not already reach the UI another way (for example the basket provider is updated from the action result, so a cart action does not need the PDP loader to re-run).
Two waste types: no overlap, or overlap with the value already available. Do not gate a re-run that is itself the sync mechanism (a provider that refills from loader output).
Where the policy lives
Each route re-exports a shared policy rather than inlining logic:
// src/routes/_app.cart.tsx
export { shouldRevalidate } from '@/lib/revalidation/routes/cart';
Module (src/lib/revalidation/routes/) |
Used by |
|---|---|
root.ts |
src/root.tsx (export { shouldRevalidate } from ...); denylist of irrelevant mutations, safe default is revalidate |
cart.ts, checkout.ts, home.ts, wishlist.ts |
the matching route files |
product.ts |
_app.p.$.tsx: relevant mutations force true; navigation re-runs only on different path or pid |
category.ts |
_app.c.$.tsx and _app.search.tsx: skips client-only param changes and non-ambient mutations |
api-client.ts |
resource.api.client.$resource.ts |
shared.ts |
helpers: getActionPath, isContextMutation, isIdentityMutation, isAmbientMutation |
What ships with it
2 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 First seen · 122 lines · 201 tokens per session scan A c9b093f490ac
sfnext-revalidation is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (56 stars, last pushed today), licensed Apache-2.0. It adds 201 tokens to every session and 1,869 once invoked, about $0.0008 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 2026-10-05.
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…