What is moonbit-template AGENTS.md?

Project instructions for MoonBit, a programming language and toolchain. They describe the project layout, commands for checking and testing code, and the project's coding conventions.

Running checks, formatting, tests, and the program; navigating and documenting MoonBit code; and following the repository's structure and naming rules.

They give a coding agent the local rules it needs to work consistently in this MoonBit repository. This reduces guesswork about commands, file types, naming, and language syntax.

moonbit-template AGENTS.md — Instructions file by mizchi

Install

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.

agentmods

npx agentmods add instructions/mizchi/moonbit-template/agents-md

Clone the repo

git clone --depth 1 https://github.com/mizchi/moonbit-template

Made for: Codex, OpenCode.

Per session 469 This file is loaded in full into every session.

When invoked 469 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00469	$0.00469
Opus 5	$0.00234	$0.00234
Sonnet 5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 2d ago against content hash 5606265f2e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moonbit-template AGENTS.md 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 2d 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.

AGENTS.md · 55 lines

What it actually says

MoonBit Project

This is a MoonBit project.

Quick Commands

just           # check + test
just fmt       # format code
just check     # type check
just test      # run tests
just test-update  # update snapshot tests
just run       # run main
just info      # generate type definition files

Project Structure

moon.mod.json - Module definition
moon.pkg - Package dependencies (per directory)
*.mbt - Source files
*_test.mbt - Blackbox test files
*_wbtest.mbt - Whitebox test files
*.mbt.md - Doc test files
*.mbti - Generated type interfaces (auto-generated by moon info)

Coding Convention

Each block is separated by ///|
Use moon ide commands for code navigation (prefer over grep)
Use moon doc '<Type>' to explore APIs before implementing
MoonBit code uses snake_case for variables/functions (lowercase only)
UpperCamelCase for types, enums, and enum variants
nobreak (not else) for functional for-loop exit values
No return needed — last expression is the return value
No try needed for error propagation — automatic (unlike Swift)
Type parameter comes after fn: fn[T] foo(x: T) -> T
Legacy function_name!(...) and function_name(...)? are deprecated

Tooling

moon fmt - format code
moon info - update generated package interfaces (.mbti)
moon test - run tests. Use moon test --update to update snapshots.
moon check --deny-warn - type check with warnings as errors
moon doc '<query>' - discover APIs (more accurate than grep)
moon ide peek-def <Symbol> - show symbol definition
moon ide find-references <Symbol> - find all references

Before Commit

just release-check  # fmt + info + check + test

Changes

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.

2d ago First seen · 55 lines · 469 tokens per session scan A 5606265f2e92

Subscribe to this mod's changes

moonbit-template AGENTS.md is an instructions file published in the GitHub repository mizchi/moonbit-template (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 469 tokens to every session, about $0.0023 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 2026-08-31.

Languages

intelligent-terminal rust.instructions.md

Concise Rust coding conventions for this repository.

microsoft/intelligent-terminal · 435 tokens

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

cryptoexchange-net

Use CryptoExchange.Net abstractions when generating C#/.NET code that needs to work across MULTIPLE cryptocurrency exchanges (Binance + Bybit + OKX + Kraken + Coinbase + ...) — for arbitrage, best-execution routing, multi-exchange portfolio dashboards, exchange-agnostic trading bots, or comparison tools. Triggers on…

JKorf/CryptoExchange.Net · 2,291 tokens

moonbit-template AGENTS.md