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/tantodefi/xmtpauthWrote 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/tantodefi/xmtpauth/readmes)<a href="https://agentmods.dev/rules/tantodefi/xmtpauth/readmes"><img src="https://agentmods.dev/badge/rules/tantodefi/xmtpauth/readmes/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/tantodefi/xmtpauth/readmes"><img src="https://agentmods.dev/badge/rules/tantodefi/xmtpauth/readmes.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 | $0.00332 | $0.00332 |
| Opus 5.5 | $0.00133 | $0.00133 |
| Sonnet 5.5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
readmes 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
globs: *.md alwaysApply: false
README Style Guide
README Writing Standards
When creating or editing README files, follow these strict guidelines:
Content Style
- Sentence-style capitalization: Use sentence-style capitalization for headers
- No emojis: Never use emojis in READMEs
- Concise: Be brief and to the point
- No redundancy: Avoid repeating information
- Code-heavy: Prioritize code examples and snippets over lengthy explanations
- Sentence-style capitalization: Use sentence-style capitalization for headers
Structure
- Use clear, direct headers without decorative elements
- Lead with practical examples rather than theory
- Include minimal explanatory text - let code speak for itself
- Focus on "how" rather than "why"
Format Requirements
- Use plain text headers (no emoji prefixes)
- Include more code blocks than paragraphs
- Keep descriptions brief - one sentence when possible
- Use tables for structured data without emoji indicators
Code Examples
- Always include working code examples
- Show real command line usage
- Provide copy-paste ready snippets
- Include minimal setup instructions
Performance Tables
- Use text instead of emoji status indicators:
- "On Target" instead of ✅
- "Concern" instead of ⚠️
- "Failed" instead of ❌
- Keep table data clean and readable
Anti-patterns to Avoid
- Emoji decorations in headers or content
- Long explanatory paragraphs
- Redundant information across sections
- Flowery or marketing language
- Over-explanation of simple concepts
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 · 55 lines · 332 tokens per session scan A f6ff99064923
readmes is a cursor rule published in the GitHub repository tantodefi/xmtpauth (3 stars, last pushed 1y ago), licensed MIT. It adds 332 tokens to every session, about $0.0013 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
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.