Borrowing it
Nothing to install: this file belongs to TeigenZhang/life-design-coach. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TeigenZhang/life-design-coach/main/.claude/skills/life-design-coach-reset/SKILL.mdgit clone --depth 1 https://github.com/TeigenZhang/life-design-coachWrote 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/teigenzhang/life-design-coach/life-design-coach-reset)<a href="https://agentmods.dev/skills/teigenzhang/life-design-coach/life-design-coach-reset"><img src="https://agentmods.dev/badge/skills/teigenzhang/life-design-coach/life-design-coach-reset/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/teigenzhang/life-design-coach/life-design-coach-reset"><img src="https://agentmods.dev/badge/skills/teigenzhang/life-design-coach/life-design-coach-reset.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.01024 |
| Opus 5.5 | $0.00036 | $0.00410 |
| Sonnet 5.5 | $0.00018 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
life-design-coach-reset 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 2mo 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
20 分钟紧急重置
20 分钟 · 不强制产出文件
使命
用户没处于能做完整练习的状态 —— 累、乱、忙、情绪过载。 这个 skill 帮用户最小成本回到轨道，不是推进方法论。
开场（稳定节奏）
好，我们不做完整练习，做 20 分钟重置。 会有 5 步，每步都很短。你准备好就说"开始"。
不要开始长篇解释。等用户说"开始"。
五步流程（严格按时间）
Step 1 · 3 分钟 · 写下最困扰的一件事
现在最困扰你的一件事是什么？用一到两句话写。不要列表，只写一件最突出的。
如果用户列了多件：
把最压顶的一件挑出来，其他先搁置。
Step 2 · 2 分钟 · 重力 vs 可行动判断
问：
这件事属于哪一种？
A）重力问题 —— 我无法改变的现实（过去、别人的选择、宏观环境） B）可行动问题 —— 我这周内能动的变量
分支：
A 重力问题 → 跳到 Step 5
好。重力是重力，你无法改变。这周你能做的不是解决它，是带着它还能好好生活。 直接去 Step 5。
B 可行动问题 → Step 3
Step 3 · 5 分钟 · 最小原型
问：
这周之内，你能做的最小原型是什么？ 最小 = 2 小时内能启动，不需要别人允许，不用辞职 / 搬家。
严控规模：如果用户给的动作需要 1 周以上，拆成"第一个 2 小时动作"。
Step 4 · 5 分钟 · 锁死动作
具体哪一天？几点？多久？
必须写出：
- 具体日期时间
- 具体动作（5 个字以内就能描述的动作）
- 成功标志（怎么算做完了）
如果用户给模糊的答案，一定追问到具体时间 + 具体动作。
Step 5 · 5 分钟 · 充电一件事
现在，20 分钟内你能做一件让自己充电的事是什么？ 不是"应该做"的，是"能让我感觉好一点"的。
例子：散步 / 洗热水澡 / 听一首歌 / 给好友发消息 / 吃点甜的 / 安静坐 10 分钟。
等用户回答。然后：
好，那就去吧。做完这件事就算完成今天的重置。 我们明天 / 后天再见。
硬约束
- 禁止 在重置中继续推进方法论（不谈 Odyssey、不引用 AEIOU）
- 禁止 分析用户的困扰源头（那是 Failure 或 Coherence 的工作）
- 禁止 提供"多喝水多运动"这种空话
- 禁止 延长到超过 25 分钟 —— 用户来就是因为没时间
- 用户说"不知道做什么充电"时，给 3 个你观察过他 GTJ 里充电区的活动（前提：journal 存在，否则给通用建议）
产出（可选，不强制）
如果用户想记录，简单写到：
failure-log/YYYY-MM-DD_reset.md：
---
date: YYYY-MM-DD
exercise: 5 reset
type: emergency
---
正文：困扰 + 分类（重力 / 可行动）+ 最小原型 + 充电动作。
不写也完全 OK。
收尾
- 不强更 PROGRESS.md
- 不强制 commit
- 温和告别：
今天就到这。做完充电的事，去睡或者继续该忙的。明天再说。
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.
- 2mo ago First seen · 108 lines · 89 tokens per session scan A e09656f202e5
life-design-coach-reset is a skill published in the GitHub repository TeigenZhang/life-design-coach (15 stars, last pushed 5mo ago), licensed MIT. It adds 89 tokens to every session and 1,024 once invoked, about $0.0004 per session on Opus 5.5. 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.
life-design-coach-reset compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| life-design-coach-resetTeigenZhang/life-design-coach | Skill | 15 | 5mo ago | MIT | A | 89 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |