HanaAgent is a personal AI assistant that combines memory, personality, computer interaction, and autonomous actions through a graphical interface. It is intended for everyday computer users as well as developers, supporting tasks such as browsing, searching, file work, code execution, scheduling, and collaboration between multiple agents. The catalogue skills extend HanaAgent's abilities and workflows.
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 skills/lilimozi/openhanako/user-guidenpx skills add liliMozi/openhanako --skill user-guidegit clone --depth 1 https://github.com/liliMozi/openhanakoWrote 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/skills/lilimozi/openhanako/user-guide)<a href="https://agentmods.dev/skills/lilimozi/openhanako/user-guide"><img src="https://agentmods.dev/badge/skills/lilimozi/openhanako/user-guide.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 | $0.00091 | $0.06908 |
| Opus 5 | $0.00046 | $0.03454 |
| Sonnet 5 | $0.00018 | $0.01382 |
| Haiku 4.5 | $0.00009 | $0.00691 |
Grade A, and why
user-guide 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 6d 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 — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HanaAgent 用户说明书
面向普通用户的使用指南。当用户问到「怎么用」「这个功能是什么」「怎么设置」等问题时，参考本文档回答。 回答时用通俗语言，避免技术术语，必要时举例说明。
一、HanaAgent 是什么
HanaAgent 是一个运行在你电脑上的 AI 私人助手。
你可以把它理解成一个「住在你电脑里的伙伴」：它能和你聊天、帮你处理文件、写东西、搜索资料、定时执行任务，甚至连接到你的微信和 Telegram 帮你自动回复。
和 ChatGPT 网页版最大的区别是：
- 它有记忆。HanaAgent 能记住你之前说过的话，今天聊的、上周聊的、上个月聊的，它都会整理归档
- 它能动手。不只是聊天，它可以读写你电脑上的文件、执行命令、浏览网页、创建定时任务
- 它是私有的。所有数据存在你自己的电脑上，不经过第三方服务器
- 它可以有多个分身。你可以创建多个 Agent（助手），每个有不同的性格和专长
和 OpenClaw 有什么不同
OpenClaw 是一个 AI Agent 开发框架，偏向开发者和基础设施层面。HanaAgent 的定位是面向个人用户的成品应用：
| HanaAgent | OpenClaw | |
|---|---|---|
| 定位 | 个人 AI 助手（成品应用） | AI Agent 框架（开发工具） |
| 受众 | 普通用户 + 开发者 | 主要面向开发者 |
| 记忆 | 多层级自然衰退记忆系统 | 框架级，需自行实现 |
| 界面 | 精心设计的桌面应用 | 无自带 GUI |
| 技能格式 | 兼容 OpenClaw / Claude Code / Codex / Pi 的 Skill 格式 | 自有 Skill 格式 |
简单说：OpenClaw 是造 Agent 的工具箱，HanaAgent 是一个已经造好的、可以直接用的 Agent。同时 HanaAgent 兼容 OpenClaw 的技能生态，可以直接安装 OpenClaw 社区的 Skill。
二、开始使用
首次打开
- 打开 HanaAgent 后，你会看到一个欢迎界面，显示助手的头像和问候语
- 引导向导会带你选择语言、填写你的名字、连接模型供应商
- 进入设置 → 供应商，可以继续添加或调整 API Key、Base URL、OAuth 账号、本地 Ollama 或 Coding Plan
- 配置好模型后回到主界面，就可以开始对话了
模型角色
HanaAgent 会把不同任务分给不同模型：
- 聊天模型：主力模型，负责和你对话、执行任务
- 实用模型（轻量）：做摘要、分类等轻活，省钱省速度
- 实用模型（重型）：做记忆编译、深度分析等需要强推理的后台任务
- 视觉模型：当聊天模型不支持图片时，先把图片转成结构化说明，再交给聊天模型理解
视觉模型本身必须是支持图片输入的多模态模型。设置时请同时确认两件事：模型卡片里的「视觉 / 支持图片」能力没有被误关；设置 → 供应商底部的「辅助视觉开关」已开启，且「视觉辅助模型」没有选成纯文本模型。
在设置 → 助手里可以为每个助手单独选择聊天模型。在设置 → 供应商底部可以配置实用模型和视觉模型。输入框里的模型胶囊可以临时切换当前会话模型。
三、和 HanaAgent 对话
基本操作
- 发送消息：输入文字，按发送按钮或快捷键发送
- 换行：Shift + Enter
- 附加文件：把文件拖进聊天区域，或点击附件按钮
- 停止回复：HanaAgent 正在回复时，发送按钮会变成停止按钮
- 插话（Steer）：HanaAgent 回复过程中你可以发送新消息打断它、补充指令
- 选择消息：消息旁有勾选、复制、截图按钮。勾选多条后可以一起复制或生成截图
- 预览媒体：聊天里的图片、SVG、视频可以点开全屏查看，支持缩放、拖拽和左右切换
思考深度
输入框旁边有个思考深度按钮，可以调整 HanaAgent 思考问题的深入程度：
- 关闭 / 低 / 中 / 高 / 极高：越高越深入，适合复杂问题，但回复会慢一些。极高只在模型支持时显示
思考过程会显示在消息中，你可以展开查看它是怎么一步步推理的。
访问模式
输入框左侧有访问模式按钮：
- 操作：允许 HanaAgent 直接使用会改动系统的工具
- 询问：默认模式。读文件、搜索等信息类工具直接允许；写文件、运行命令、安装技能等动作会先询问
- 只读：只能阅读、搜索、查看，不允许写入、运行会改动系统的工具
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.
- 6d ago First seen · 568 lines · 91 tokens per session scan A cdbd47f17d51
user-guide is a skill published in the GitHub repository liliMozi/openhanako (6,492 stars, last pushed 9d ago), licensed Apache-2.0. It adds 91 tokens to every session and 6,908 once invoked, about $0.0005 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.