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/backendforth/next-sanity-starterWrote 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/rules/backendforth/next-sanity-starter/web)<a href="https://agentmods.dev/rules/backendforth/next-sanity-starter/web"><img src="https://agentmods.dev/badge/rules/backendforth/next-sanity-starter/web/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/rules/backendforth/next-sanity-starter/web"><img src="https://agentmods.dev/badge/rules/backendforth/next-sanity-starter/web.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 | $0.00224 |
| Opus 5.5 | $0.00000 | $0.00090 |
| Sonnet 5.5 | $0.00000 | $0.00045 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
web 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 yesterday.
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
Canonical: AGENTS.md. Deep docs: web/README.md, web/sanity/README.md, web/src/i18n/README.md.
- i18n: field-level — thread
{ locale, siteLocale }down every render path and resolve fields there; GROQ projects the full{ _key, _type, language, value }arrays. - Server components by default;
"use client"only for state, effects or browser APIs. - Heavy client code that only some pages render goes behind a lazy boundary (
next/dynamicin a"use client"file); CI fails a route over its first-load JS ceiling in.github/bundle-budget.json. - A module gets the locale as a prop, never from the router, the URL or cookies (
AGENTS.md§"i18n DO / DON'T"). - Build locale-prefixed URLs with the helpers in
web/src/i18n/, never by concatenating prefixes.
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.
- yesterday Changed · -20 lines c4810c74a6c8
- 2d ago Changed 47f85b8b915b
- 1mo ago First seen · 34 lines · 0 tokens per session scan A e83e5618a5d8
web is a cursor rule published in the GitHub repository backendforth/next-sanity-starter (4 stars, last pushed yesterday), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 224 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 cursor rules, from other repositories
branching-strategy
GitFlow-inspired branching strategy for this project. Solo development omits the develop branch.
design-tokens-guide
The single source of truth for all design tokens is located in packages/design-tokens/src/tokens.ts.
test-guide
Cursor rule "test-guide" from first-fluke/fullstack-starter, covering test guide, quick commands, run all tests, all tests and or individually.
frontend
React/Next.js frontend coding standards with shadcn/ui, Tailwind CSS v4, and FSD-lite architecture.
lint-format-guide
Cursor rule "lint-format-guide" from first-fluke/fullstack-starter, covering lint & format guide, quick commands, check all, from root and python (in apps/api or apps/worker).
i18n-guide
Response language rules for agents and workflows.