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/sollawen/microneo/agents-mdgit clone --depth 1 https://github.com/sollawen/microNeoWrote 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/sollawen/microneo/agents-md)<a href="https://agentmods.dev/instructions/sollawen/microneo/agents-md"><img src="https://agentmods.dev/badge/instructions/sollawen/microneo/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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
microNeo 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 5d 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
基本规则
- 如非必要，勿增实体。能复用已有代码和方法的，就不要新写代码的方法
- 编译本项目时，必须使用
make build，不要直接使用go build。如果想快速编译跳过 generate 步骤，可以使用make build-quick - 首次 clone 或换机器后必须先跑一次
make generate（或直接make build）：generate生成runtime/syntax/*.hdr（filetype 检测头，被.gitignore忽略、不入库），只有*.yaml没.hdr时所有语法高亮会全失效（全文 default 色）。make build-quick跳过 generate，已在仓库里跑过一次 generate 后才能安全使用 - 用户配置目录统一在
$XDG_CONFIG_HOME/microNeo（未设置时 fallback 到~/.config/microNeo），启动时可用--config <dir>临时覆盖 docs/目录是本项目所有设计方案和计划- 代码注释不引用文档：注释必须自包含，用散文讲清「为什么」，不依赖任何外部文档即可读懂。禁止在代码注释里写设计文档的文件名或章节号
- 特殊 Skill 触发：当用户说
commit/changelog/release时，不要 summon 任何 assistant。先读取.agents/skills/下对应的SKILL.md文件，按规则直接执行。这些是项目的特殊 skill，有专门的执行规则。
Debug
- microNeo 有统一的 debug 日志机制，不要自己另写一套（自建日志文件、自建 print 等），一律复用下面这个
- 开关：对齐 micro 原生
util.Debug。make build-dbg编译时注入util.Debug=ON，运行时追加写/tmp/microNeo_debug.log；make build/make build-quick默认OFF，不写日志、零开销 - 写日志（函数都在
internal/display/bufwindow_md.go，内部先判util.Debug=="ON"才写）：display包内：直接用dbgLog(format, args...)- 其他包（如
action）：用导出的display.DbgLog(format, args...)——dbgLog的透传包装，共用同一个 sink
- 所有层（MD 渲染、分屏 resize 等）写进同一个文件，排查时用
grep按各自前缀过滤
核心概念
- Segment：每行 buffer 属于一个 Segment。表格/代码块的
Segment.Rows行数 > buffer 行数（frame 装饰行），是 v1.0.5 光标跨段滚动的核心难点。 - 检测/渲染分离：
buffer 变化 → DetectSegments() → SharedBuffer.MDSegments → displayBufferMD() 读 → renderer 算 → 写屏。detect 不依赖屏宽；render 按屏宽布局。触发点buffer.go:211-212（NewBuffer）+1031-1032（编辑增量）。 - 阅读/编辑模式：
BufWindow.editMode（bufwindow.go:42）。observeEditModeToggle观察 ESC/click 切换；主循环里editMode && 光标在 seg 内→ 回退原生渲染。
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.
- 5d ago First seen · 28 lines · 803 tokens per session scan A 2f3c260703d2
microNeo AGENTS.md is an instructions file published in the GitHub repository sollawen/microNeo (55 stars, last pushed 19d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 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 instructions, from other repositories
waveloom AGENTS.md
AGENTS.md instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.
go-micro CLAUDE.md
Claude Code instructions for micro/go-micro, covering claude.md - go micro project guide, project overview, build & test, run all tests and run tests for a specific package.
go-micro AGENTS.md
AGENTS.md instructions for micro/go-micro, covering repository agent instructions and pull requests from codex tasks.
zot AGENTS.md
AGENTS.md instructions for patriceckhart/zot, covering working agreement for zot, product intent, starting a task, code ownership map and correctness contracts.
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
hex1b AGENTS.md
AGENTS.md instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.