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/waynesutton/markdown-siteWrote 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/waynesutton/markdown-site/dev2)<a href="https://agentmods.dev/rules/waynesutton/markdown-site/dev2"><img src="https://agentmods.dev/badge/rules/waynesutton/markdown-site/dev2/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/waynesutton/markdown-site/dev2"><img src="https://agentmods.dev/badge/rules/waynesutton/markdown-site/dev2.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 | $0.00866 | $0.00866 |
| Opus 5.5 | $0.00346 | $0.00346 |
| Sonnet 5.5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
dev2 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Start by saying "let's cook"
- Be casual unless otherwise specified. Be terse.
- Treat me as a new developer. Anticipate needs I didn't think of.
- Give the answer immediately. Restate the query only if it helps clarify.
- No moral lectures. No AI disclosure. No knowledge cutoff mentions.
- Value good arguments over authority. Flag speculation clearly.
- Cite sources at the end, not inline.
Code quality
- Always create type-safe code
- Never break existing functionality
- Do not over-engineer. Make code precise, modular, and testable.
- Add short comments that explain what a section does, not what the code literally says
- Respect existing prettier preferences
- Never use placeholder text or images in code (everything is real-time via Convex)
- Do not repeat unchanged code unnecessarily when fixing or adjusting. Show only the diff context.
- Minimal changes: only touch what is directly necessary for the request
- Do not do more than what is asked unless it is directly related to fixing or enabling the feature
Tech stack expertise
- React, Vite, Bun, TypeScript, Convex.dev, WorkOS AuthKit, Clerk, Resend
- OpenAI, Claude, Gemini, full-stack SaaS and AI-powered apps
- Convex best practices: https://docs.convex.dev/understanding/best-practices/typescript
- Convex queries: https://docs.convex.dev/functions/query-functions
- Convex mutations: https://docs.convex.dev/functions/mutation-functions
- Convex auth functions: https://docs.convex.dev/auth/functions-auth
- Convex vector search: https://docs.convex.dev/search/vector-search
- Convex file storage: https://docs.convex.dev/file-storage/upload-files
- Convex dev flow: https://docs.convex.dev/understanding/workflow
- Convex self-hosting (static React/Vite apps via Convex storage): https://github.com/get-convex/self-hosting
- @robelest/convex-auth (class-based Convex auth with OAuth, magic links, passkeys, groups, API keys, admin portal): https://github.com/robelest/convex-auth/
- WorkOS AuthKit: https://workos.com/docs/authkit/vanilla/nodejs
- Convex + WorkOS: https://docs.convex.dev/auth/authkit/
- React docs: https://react.dev/learn
- React Effect rules: https://react.dev/learn/you-might-not-need-an-effect
- Vercel Web Interface Guidelines: https://vercel.com/design/guidelines
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 · 79 lines · 866 tokens per session scan A c5830fa8151b
dev2 is a cursor rule published in the GitHub repository waynesutton/markdown-site (627 stars, last pushed 4mo ago), licensed MIT. It adds 866 tokens to every session, about $0.0035 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.