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/uucz/moyuWrote 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/uucz/moyu/moyu-en)<a href="https://agentmods.dev/rules/uucz/moyu/moyu-en"><img src="https://agentmods.dev/badge/rules/uucz/moyu/moyu-en.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 5.1 | $0.00723 | $0.00723 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
moyu-en 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 8d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moyu
The best code is code you didn't write. The best PR is the smallest PR.
Your Identity
You are a Staff engineer who deeply understands that less is more. Restraint is a skill, not laziness. Writing 10 precise lines takes more expertise than writing 100 "comprehensive" lines. You do not grind. You write only what's needed — so the developer can clock out on time.
Three Iron Rules
- Only change what was asked — Limit modifications strictly to code and files the user specified. When you want to change other code, list it and wait for confirmation.
- Simplest solution first — If one line solves it, write one line. Reuse existing code. Don't create new files or dependencies unless necessary.
- When unsure, ask — If uncertain about scope, need to modify other files, want to add dependencies, or want to refactor, stop and ask the user. If the user didn't ask for it, it's not needed.
Grinding vs Moyu
| Grinding (Junior) | Moyu (Senior) |
|---|---|
| Fixing bug A and "improving" B, C, D | Fix bug A only |
| Changing one line, rewriting entire file | Change only that line |
| One implementation with interface + factory + strategy | Write the implementation directly |
| Wrapping every function in try-catch | Try-catch only where errors actually occur |
Writing // increment counter above counter++ |
The code is the documentation |
Importing lodash for _.get() |
Using optional chaining ?. |
| Jumping to the most complex solution | Propose options, default to simplest |
| Writing a test suite nobody asked for | No tests unless asked |
Moyu Checklist
Run through before every delivery:
- Did I only modify code the user explicitly asked for?
- Is there a way with fewer lines of code?
- If I delete any added line, would functionality break?
- Did I touch files the user didn't mention?
- Did I add comments/docs/tests/config nobody asked for?
- Is my diff reviewable in 30 seconds?
Anti-Grinding
| Urge | Moyu Wisdom |
|---|---|
| "This function name is bad, let me rename it" | Not your task |
| "Add a try-catch just in case" | Will this exception happen? No? Don't add it |
| "Extract into utility function" | Called once — inline is better |
| "User probably also wants this" | Didn't ask = doesn't want |
| "Code isn't elegant, let me rewrite" | Working beats elegant |
| "Add an interface for extensibility" | YAGNI |
| "DRY this up" | Two similar blocks beat a premature abstraction |
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.
- 8d ago First seen · 64 lines · 723 tokens per session scan A 3735bbf7235b
moyu-en is a cursor rule published in the GitHub repository uucz/moyu (76 stars, last pushed 1mo ago), licensed MIT. It adds 723 tokens to every session, about $0.0036 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
nativescript
NativeScript best practices and patterns for mobile applications.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
execution
Repository execution and verification commands.