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/krivoox/agent-stack-template/performancegit clone --depth 1 https://github.com/krivoox/agent-stack-templateWhat 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 | $0.00000 | $0.00346 |
| Opus 5 | $0.00000 | $0.00173 |
| Sonnet 5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
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 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
Performance and navigation
Detail: docs/architecture.md §7.
Required
- Soft navigation only. The shell in
(app)/layout.tsxis persistent; a full page reload during an authenticated session is a bug. - Every
(app)segment ships aloading.tsxbuilt onPageSkeleton. experimental.staleTimes.dynamic: 0. Perceived speed comes from skeletons and prefetch, not from showing data captured before the last mutation.- Nav destinations live in
nav-config.tsso idle prefetch covers them. - After a mutation, use
refreshAfterMutation/navigateAndRefreshfromsrc/lib/navigation.ts. A plainrouter.pushcan land on a Client Router Cache entry captured before the write. - Authenticated routes are
private, no-store— add the prefix toPRIVATE_ROUTE_PREFIXESinnext.config.ts.
Forbidden
- Cross-request caching of tenant data (balances, membership, anything per-user).
- A service worker that caches HTML or
/api/*. Static assets under/_next/static/*only — they are content-hashed and immutable. - Offline UI that displays stale authoritative data. Users trust what they see; a stale number is worse than no number.
- Relaxing
staleTimes.dynamicto make a page feel faster.
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 · 34 lines · 0 tokens per session scan A 48aae35adb95
performance is a cursor rule published in the GitHub repository krivoox/agent-stack-template (30 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 346 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 2026-08-30.
Other cursor rules, from other repositories
coding-guidelines
You are working on tRPC - a TypeScript-first RPC library that provides end-to-end type safety between client and server. As a TypeScript expert contributing to this library, you should.
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 }), ], }; }, }).
test-patterns
// ✅ CORRECT: Use await using for automatic cleanup await using ctx = testServerAndClientResource(router, { client(opts) { return { links: [ httpLink({ url: opts.httpUrl, fetch: mockFetch, }), ], }; }, }).
test-running
When running tests, use the --watch false flag to avoid watch mode.