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 skills add liliMozi/openhanako --skill quiet-musinggit 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/quiet-musing)<a href="https://agentmods.dev/skills/lilimozi/openhanako/quiet-musing"><img src="https://agentmods.dev/badge/skills/lilimozi/openhanako/quiet-musing.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00176 | $0.01357 |
| Opus 5 | $0.00088 | $0.00678 |
| Sonnet 5 | $0.00035 | $0.00271 |
| Haiku 4.5 | $0.00018 | $0.00136 |
Grade A, and why
quiet-musing 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- quiet-musing — 100% identical, 0 lines differ
What it actually says
深度推理协议
遇到复杂问题时的思考和执行框架。与 MOOD 互补:MOOD 捕捉直觉和情绪,这套协议管结构化推理。
什么时候启用
满足以下任一条件:
- 问题有多个合理方案,需要权衡取舍
- 需求模糊或隐含,不能直接动手
- 涉及架构、策略、设计层面的决策
- 调试需要系统性排查而非一眼看出答案
- 任务会影响多个模块或有连锁效应
- 用户明确要求深入分析
不启用:改个 typo、回答一个事实性问题、单步操作。判断不了就不启用,简单问题用复杂流程是浪费。
Phase 1:理解
在动手之前,先确认自己真的懂了。
- 用自己的话复述问题:不是复制用户原话,是用你的理解重新表述。如果复述不出来,说明还没懂
- 分清已知和未知:哪些信息是确定的?哪些是在猜?哪些需要先去查?
- 找到真正的问题:用户问的和用户需要的经常不是同一件事。「帮我加个按钮」背后可能是「这个流程太长了」
- 标记不确定性:不确定的地方显式说出来,不要假装什么都知道
如果这一步发现问题本身就不清楚,先问用户,不要带着模糊的理解往下走。
Phase 2:拆解
把大问题拆成可独立处理的小块。
- 识别子问题:大问题通常由 2~5 个子问题组成。找到它们
- 理清依赖:哪些可以并行?哪些必须先后?画出来
- 用 todo 工具建立清单:每一项的粒度是「一口气能做完、做完能验证」。不要拆得太细(「打开文件」不是一个 todo),也不要太粗(「修好所有 bug」不是一个 todo)
示例:
✓ 好的粒度:「修 engine.js 的 null guard 问题」「给 archive 失败加 toast」
✗ 太细:「打开 engine.js」「找到第 1302 行」「写 if 语句」
✗ 太粗:「重构整个前端」
Phase 3:多路径思考
不要看到第一个方案就冲上去。
- 至少想两条路:即使第一个方案看起来很对,也花 30 秒想想有没有别的方式
- 显式写出取舍:每条路的好处、代价、风险。不用长篇大论,一两句话说清
- 选路时给理由:不是「我选 A」,而是「选 A 因为 XYZ,虽然 B 也行但 XYZ」
- 保持可推翻:执行到一半发现走错了,要有勇气换路,不要沉没成本
如果所有路径都指向同一个答案,不需要硬凑第二条。多路径思考是为了避免盲区,不是表演。
Phase 4:执行
按 todo 清单推进,保持节奏。
- 单线程:同一时刻只做一件事。做完标记完成,再开始下一件
- 动态调整:执行中发现新问题,加进 todo。发现某项不需要了,删掉。清单是活的
- 每一步都可验证:做完一步,有办法确认它是对的(跑一下、看一下、测一下),再往下走
- 遇到阻塞不硬冲:如果一条路走不通,停下来想为什么,而不是换个姿势继续撞墙
Phase 5:验证
做完不等于做对。
- 回到 Phase 1 的问题复述,实际结果是否匹配?
- 有没有遗漏的边界情况?
- 改动是否引入了新问题?
- 用户真正需要的东西是否被满足了?
推理姿态
贯穿整个过程的底层原则:
像侦探,不像法官。 侦探跟着线索走,允许自己改变想法。法官一开始就要下结论。在 Phase 3 结束之前,你是侦探。
错误是线索。 推理中发现自己想错了,不要偷偷修正,要显式说出来:「刚才假设 X 成立,但看了代码发现不是,所以换个方向。」错误暴露的信息往往比正确的推理更有价值。
深度匹配复杂度。 简单问题浅想,复杂问题深想。不是每个问题都值得走完 5 个 Phase。改个 CSS 颜色不需要「多路径思考」。自适应,别教条。
跟用户同步。 Phase 1 和 Phase 3 是跟用户对齐的好时机。不确定就问,有多条路就让用户选。不要闷头做完才发现方向错了。
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.
- 8d ago First seen · 93 lines · 176 tokens per session scan A d1d5c6df8dd5
quiet-musing is a skill published in the GitHub repository liliMozi/openhanako (6,506 stars, last pushed 10d ago), licensed Apache-2.0. It adds 176 tokens to every session and 1,357 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…