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/marckrenn/rtfmbro-mcp/rtfmbrogit clone --depth 1 https://github.com/marckrenn/rtfmbro-mcpWrote 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/marckrenn/rtfmbro-mcp/rtfmbro)<a href="https://agentmods.dev/rules/marckrenn/rtfmbro-mcp/rtfmbro"><img src="https://agentmods.dev/badge/rules/marckrenn/rtfmbro-mcp/rtfmbro.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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
rtfmbro 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.
What it actually says
Cursor Instructions for Package Documentation
Package Documentation Policy
- Before using any package, module, or library, ALWAYS consult its documentation — your internal knowledge may be outdated and could cause errors or failures.
- Don't assume anything about the package's functionality, usage, or configuration without verifying it against the official documentation.
- If you are unsure about a user's request that may involve a package, module, or library, ALWAYS refer to the documentation first or ask the user to provide the package name and version.
Workflow
- Don't immediately lookup the user's original codebase.
- First, Identify the package name and the EXACT pinned version (eg. "==1.0.5") from the project’s lock file (eg. uv.lock, bun.lock).
- Using this information fetch documentation by executing one of the provided tools:
get_readmeget_documentation_treeread_filessearch_github_repositories- Search for Github packages and repositories by topic, language, or keywords. Note, sometimes the documentation is located in a separate repository (liketailwindlabs/tailwindcss.com). Use the repo owner to search for the repo containing the documentation.
- Review the documentation carefully to understand:
- Core functionality
- Usage patterns
- Any caveats or special instructions
- Reference examples from the documentation to guide your implementation.
Ecosystem Selection:
- Use
pypifor Python packages - Use
npmfor Node.js packages - Use
spmfor Swift packages - Use
ghonly as a fallback for languages not supported by the above registries (package name must be in 'owner/repo' format) or if you're unsure about the package's ecosystem. Also useghwhen you don't find the package in the lock file.
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 · 32 lines · 417 tokens per session scan A 74ce4e51f2be
rtfmbro is a cursor rule published in the GitHub repository marckrenn/rtfmbro-mcp (91 stars, last pushed 1y ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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
librechat-documentation
When updating the LibreChat config version (e.g., from v1.2.6 to v1.2.7), follow these steps.
project-overview
Core project architecture, patterns, and conventions for the AI Documentation Generator.
agent-development
Guidelines for developing pydantic-ai agents, tools, and handlers.
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
use-docfork
Use Docfork to retrieve up-to-date library and API documentation instead of relying on training data.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.