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/tincopper/neeko/claude-mdgit clone --depth 1 https://github.com/tincopper/neekoWrote 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/tincopper/neeko/claude-md)<a href="https://agentmods.dev/instructions/tincopper/neeko/claude-md"><img src="https://agentmods.dev/badge/instructions/tincopper/neeko/claude-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 | $0.00790 | $0.00790 |
| Opus 5 | $0.00395 | $0.00395 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
neeko CLAUDE.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 4d 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
Neeko — CLAUDE.md
Claude Code 项目上下文。核心规范见
AGENTS.md，本文件仅补充 Claude Code 角色与快捷键速查。
项目概览
Neeko：基于 Tauri 2.0 + React 18 的桌面应用，统一管理多项目 AI Agent 会话。
- 版本: 1.0.4 | 标识符:
com.neeko.app - 前端: React 18 + TypeScript + Vite | 后端: Rust + Tauri 2.0 + tokio
- 包管理器: pnpm
9.12.2| Node: 18+ | Rust edition: 2021
完整目录结构、架构与数据流、开发规范、测试指南见
AGENTS.md（单一事实源）。
常用命令速查
| 命令 | 用途 |
|---|---|
pnpm tauri dev |
启动开发模式 |
pnpm tauri build |
构建发布版本 |
pnpm type-check |
前端类型检查 |
pnpm lint |
Rust lint（fmt + clippy） |
pnpm lint:fe |
前端 lint（ESLint + tsc） |
pnpm test:run |
运行前端测试 |
cargo test --manifest-path src-tauri/Cargo.toml |
运行 Rust 测试 |
cargo check --manifest-path src-tauri/Cargo.toml |
Rust 编译检查 |
键盘快捷键
| 快捷键 | 功能 |
|---|---|
Ctrl+1 ~ Ctrl+9 |
跳转到第 N 个项目 |
Ctrl+Q |
循环切换项目 |
Ctrl+Alt+T / Ctrl+W |
打开/关闭副终端 |
Ctrl+O |
在 IDE 中打开项目 |
Ctrl+N |
循环切换 Worktree 终端 |
Ctrl+R |
手动刷新终端 |
Escape |
关闭设置面板 |
预置 Agent & IDE
- Agent: opencode, claude-code, gemini, codex, qoder, codebuddy
- IDE: VS Code, Cursor, Zed, IntelliJ IDEA, GoLand, RustRover, PyCharm
架构要点
- 终端缓存 key:
{projectId}/{projectId}:side/{projectId}:wt:{worktreePath}/wsl:{distro}:{projectId}/remote:{entryId}:{projectId} - SSH IO:
tokio::select!三路并发（input / resize / output） - Agent 启动延迟: 本地即时 / WSL 500ms / SSH 800ms
- 持久化:
~/.neeko/sessions.json+~/.neeko/config.json
已知问题
- SSH 凭据重连自动填充可能有边界情况
- SSH 路径自动补全下拉可能有 z-index 问题
- 自定义 IDE 的 icon 解析不支持
相关文档
docs/neeko-development-spec.md— 全栈架构规范docs/ARCHITECTURE.md— 架构总览docs/REQUIREMENTS.md— 完整需求文档
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.
- 4d ago First seen · 63 lines · 790 tokens per session scan A fd6e52c07ccd
neeko CLAUDE.md is an instructions file published in the GitHub repository tincopper/neeko (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 790 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 2026-08-31.
Other instructions, from other repositories
detrix CLAUDE.md
Instructions for flashus/detrix, covering claude.md, rust development, workflows, code audit workflow and task completion.
grok-delegate AGENTS.md
Instructions for arthurkatcher/grok-delegate, covering agents.md — grok-delegate, what this repo is, layout (do not invent a second one), non-negotiables and how to work here.
clique CLAUDE.md
Claude Code instructions for thejdubb02/clique, covering clique — standing rules, motion, looking at it, the api is the whole surface and releasing.
grok-build-mcp AGENTS.md
AGENTS.md instructions for zai-one/grok-build-mcp, covering agents.md — grok-delegate / unofficial grok mcp, язык, typed tools vs navigator, откуда берётся корень and проект должен сам включить мост.
ccteam AGENTS.md
Instructions for firstintent/ccteam, covering agents.md — ccteam 实现导引, 〇、架构总览(定向图;红线唯一清单 = §三), 一、需求与版本管理(两条来源,都住 gitignored docs-local/), 二、仓库内文档(只有用户面;架构与协议一律读代码) and 三、不可触碰的架构红线(唯一权威清单).
grok-build-mcp CLAUDE.md
Claude Code instructions for zai-one/grok-build-mcp: Неофициальный MCP-мост к Grok CLI. Правила проекта живут в AGENTS.md — он импортируется ниже, отдельно открывать не нужно. Плюс skill grok-mcp как роутер по инструментам.