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 instructions/nanonative/nano/agents-mdgit clone --depth 1 https://github.com/NanoNative/nanoWrote 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/instructions/nanonative/nano/agents-md)<a href="https://agentmods.dev/instructions/nanonative/nano/agents-md"><img src="https://agentmods.dev/badge/instructions/nanonative/nano/agents-md.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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
nano 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 today.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Nano favors static, event-driven Java code with zero reflection and minimal dependencies. Treat this guide as the fastest path to productive contributions without violating the framework’s immutability and functional constraints.
Project Structure & Module Organization
- Core source lives under
src/main/java/org/nanonative/nano, grouped by domain (core,services,helper, etc.) instead of classic MVC layers. - Tests and runnable examples sit in
src/test/java, while fixtures (PNG logos, JSON payloads) are undersrc/test/resources. - Long-form docs live in
docs/(concept, context, services), and build artifacts land intarget/. Keep generated files out of version control.
Build, Test, and Development Commands
./mvnw clean compile– compile all sources with Java 21 toolchain../mvnw test– execute the JUnit 5 suite with AssertJ assertions../mvnw clean verify– run tests plus Jacoco coverage (target/site/jacoco/index.html)../mvnw clean package– produce the distributable JAR intarget/../mvnw clean deploy -P release– semantic-release build (requires configured GPG and credentials).
Coding Style & Naming Conventions
- Favor static methods, fluent chains, and
finalfields; never introduce shared mutable state ornullreturns. - Event constants use screaming snake case (
EVENT_HTTP_RECEIVE), packages remainorg.nanonative.nano.<domain>. - Indentation is 4 spaces; rely on
spotless:applyif present in your toolchain but keep formatting deterministic. - Zero reflection, no parallel streams, and only virtual threads (
Executors.newVirtualThreadPerTaskExecutor) for concurrency.
Testing Guidelines
- Write component tests in
src/test/java, naming files*Testand methods withshould...to express behavior. - Use embedded resources (Flapdoodle Mongo, in-memory HTTP) instead of mocks; prefer real HTTP calls or WireMock stubs.
- Keep tests deterministic by injecting
Clockor seeds, and assert exact payloads. Failing tests must reproduce locally with./mvnw test -DfailIfNoTests=false.
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.
- today First seen · 37 lines · 651 tokens per session scan A 88de6682dd7e
nano AGENTS.md is an instructions file published in the GitHub repository NanoNative/nano (107 stars, last pushed 26d ago), licensed Apache-2.0. It adds 651 tokens to every session, about $0.0033 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 2026-09-04.
Other instructions, from other repositories
questdb CLAUDE.md
Claude Code instructions for questdb/questdb, covering claude.md, project overview, coding guidelines, tests and questdb's sql dialect.
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目(模块集由 jdk 版本自动选择 —— 见下方说明).
BitcoinAddressFinder CLAUDE.md
Claude Code instructions for bernardladenthin/BitcoinAddressFinder, covering claude.md — bitcoinaddressfinder, project overview, build system, common commands and compile only.
imgui-java CLAUDE.md
Claude Code instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
langchain4j-cdi copilot-instructions.md
Copilot instructions for langchain4j/langchain4j-cdi, covering langchain4j cdi integration, working effectively, prerequisites, bootstrap and build and essential commands.
leyden-perf-test AGENTS.md
Instructions for quintesse/leyden-perf-test, covering agents.md - leyden performance test harness, project overview, purpose, primary goals and current state.