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/patrickjs/awesome-cursorrules/cursor-rules-pack-v2-cursorrules-prompt-filegit clone --depth 1 https://github.com/PatrickJS/awesome-cursorrulesWrote 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/patrickjs/awesome-cursorrules/cursor-rules-pack-v2-cursorrules-prompt-file)<a href="https://agentmods.dev/rules/patrickjs/awesome-cursorrules/cursor-rules-pack-v2-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/rules/patrickjs/awesome-cursorrules/cursor-rules-pack-v2-cursorrules-prompt-file.svg" alt="Measured on agentmods" 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 | $0.00569 | $0.00569 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
cursor-rules-pack-v2-cursorrules-prompt-file 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 4d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules Pack v2 — Sample Rules
7 production-tested rules from the full 50-rule pack
Full pack: https://oliviacraftlat.gumroad.com/l/wyaeil
Rule 1 — Dependency Discipline
Before suggesting a new npm package: (1) state what it does in one sentence, (2) check if it's actively maintained (last publish < 6 months), (3) confirm whether we could implement it in < 30 lines without the dependency. Prefer fewer, well-maintained packages. Never add a dependency for a task under 20 lines of code.
Rule 2 — Explicit Error Handling
Always wrap async operations in try/catch. Never swallow errors silently. Return typed error objects using a Result pattern or throw typed errors. Log errors with context: logger.error('[FunctionName] description', { error, context }). Always provide user-facing error states in UI components.
Rule 3 — Comments Policy
Write self-documenting code first. Add comments only for: (1) non-obvious business logic — explain WHY, not WHAT, (2) workarounds — explain why the workaround exists and link to the issue, (3) complex algorithms — reference the algorithm name. Never comment what the code clearly does.
Rule 4 — State Management Hierarchy
Follow this state hierarchy strictly:
- URL state → filters, pagination, search (useSearchParams)
- React state → UI-only, ephemeral (useState)
- Zustand → cross-component app state
- React Query → all server state Never use Zustand to cache server data — that's React Query's job. Never reach for Redux.
Rule 5 — Parallel Data Fetching
Identify and parallelize independent data fetches. Never await sequentially when operations are independent — use Promise.all. When making a sequential await, add a comment explaining the dependency that forces the sequence.
Rule 6 — Webhook Security
For incoming webhooks: verify the signature in the first 3 lines of the handler — reject immediately if invalid. Respond with HTTP 200 within 5 seconds — offload processing to a background job. Store the raw webhook event before processing. Implement idempotency using the event ID.
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.
- 4d ago First seen · 35 lines · 0 tokens per session scan A 18618d64f17f
cursor-rules-pack-v2-cursorrules-prompt-file is a cursor rule published in the GitHub repository PatrickJS/awesome-cursorrules (40,722 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 569 tokens to every session, about $0.0028 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
snyk_rules
Snyk Security At Inception.
cursorrules
// Good: Use anyhow for application errors use anyhow::{Context, Result}.
project
Project rules for application source, tests, and documentation.
nextjs
Next.js: App Router, Server Components, server actions.
go
Go patterns: error wrapping, goroutines, interfaces.
code-review
Code review: reviewing approach, authoring PRs, feedback conventions.