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 agentmods add rules/davis7dotsh/river/globalgit clone --depth 1 https://github.com/davis7dotsh/riverWhat 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 | $0.00188 | $0.00188 |
| Opus 5 | $0.00094 | $0.00094 |
| Sonnet 5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
global 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
Guidelines for working on this project:
- Always use typescript
- Always use svelte 5 and the modern features
- Always use bun as the package manager
- Do NOT write explicit return types for functions (unless there is a VERY good reason)
- Do NOT add unit tests unless explicitly asked to
- The only project specific commands you are allowed to run are:
bun checkto check for type errorsbun formatto format the codebun lintto lint the code
- Always use tailwind css (tailwind v4 to be clear) unless there is something you need to do that tailwind doesn't support
- When handling errors, use the
neverthrowlibrary to handle errors - Be extremely concise. Sacrifice grammar for the sake of concision.
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 First seen · 21 lines · 188 tokens per session scan A 8fa24435da37
global is a cursor rule published in the GitHub repository davis7dotsh/river (227 stars, last pushed 5mo ago), licensed MIT. It adds 188 tokens to every session, about $0.0009 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
svelte
You are an expert in Svelte 5, SvelteKit, TypeScript, and modern web development.
testing
Comprehensive Testing Best Practices for Svelte 5 + vitest-browser-svelte.
cursorrules
Comprehensive Testing Best Practices for Svelte 5 + vitest-browser-svelte.
upgrade-tests
// ✅ CORRECT: Upgrade package pattern await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
react-query-tests
// ✅ CORRECT: Legacy React Query pattern const ctx = konn() .beforeEach(() => createAppRouter()) .afterEach((ctx) => ctx?.close?.()) .done().
tanstack-react-query-tests
// ✅ CORRECT: Use await using for automatic cleanup await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).