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/maccman/ai-expo-starter-templateWrote 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/maccman/ai-expo-starter-template/style)<a href="https://agentmods.dev/rules/maccman/ai-expo-starter-template/style"><img src="https://agentmods.dev/badge/rules/maccman/ai-expo-starter-template/style/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/maccman/ai-expo-starter-template/style"><img src="https://agentmods.dev/badge/rules/maccman/ai-expo-starter-template/style.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 | $0.00422 | $0.00422 |
| Opus 5.5 | $0.00169 | $0.00169 |
| Sonnet 5.5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
style 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 1mo 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.
What it actually says
Context:
- Conventions: small files, single-responsibility, testable interfaces, providers+hooks for state, one component per file, '@/' imports, zod for parsing/validation, no any.
- Events: define event name constants; payloads are discriminated unions; normalize snake_case (Rust) → camelCase (TS).
- Rust: offload blocking work with spawn_blocking; emit structured serde-tagged payloads; keep interfaces minimal.
- Quality gates: Propose a plan first; after edits run cargo check, pnpm typecheck, pnpm lint; fix issues; ensure hooks rules respected.
Do this:
- Propose a concise plan (files to add/edit, public APIs, event names, schemas).
- After approval, implement:
- Keep modules small and composable.
- Add zod schemas for all incoming data; normalize to camelCase once in a bridge layer.
- Use discriminated unions and type guards; export helper predicates (e.g., isTerminalEvent).
- Centralize constants (event names, keys) in a types or constants file.
- In React, create a provider and a small hook for state; avoid conditional hooks.
- In Rust, use spawn_blocking for blocking ops; include identifiers like repo_id in every event.
- After coding, run:
- cargo check
- pnpm typecheck
- pnpm lint Fix issues immediately.
- Summarize the changes succinctly and note any follow-up suggestions.
Non-negotiables:
- No any. Use zod for runtime validation.
- Normalize casing at boundaries; TS types are camelCase.
- Small, testable modules; clear public APIs.
- Don’t call hooks conditionally.
- Prefer to split out logic into smaller files.
- Never use
anyoras anyin Typescript. - Never use single character variable names.
- Always write documentation for all public APIs.
- Always run build/typecheck/lint before declaring done.
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.
- 1mo ago First seen · 40 lines · 422 tokens per session scan A 05b67145aacb
style is a cursor rule published in the GitHub repository maccman/ai-expo-starter-template (4 stars, last pushed 1y ago), licensed MIT. It adds 422 tokens to every session, about $0.0017 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 2026-08-31.
Other cursor rules, from other repositories
rust
Rules for writing Rust services at PostHog. Focuses on writing async Rust with Tokio and encoding general Rust best practices from the Rust book and docs.
vue-typescript-patterns
A set of coding rules for Vue 3 projects using TypeScript, a language that adds type checking to JavaScript. It covers component structure, file locations, TypeScript usage, and Pinia, a library for shared application state.
nextjs-typescript-app-cursorrules-prompt-file
Cursor rules for Next.js development with TypeScript integration.
typescript-security
A secret scanner owns hardcoded keys. Read secrets from the environment and fail startup when a required one is missing.
platform-pattern-2-filesystem-operations
Cursor rule "platform-pattern-2-filesystem-operations" from PaulJPhilp/EffectPatterns, covering platform pattern 2: filesystem operations and example.
bundling
The project uses a custom type bundling system to provide full TypeScript IntelliSense support in the Monaco editor for @bubblelab/bubble-core and its dependencies. This is necessary because Monaco cannot directly resolve workspace packages or external dependencies.