Cangjie Skill is a system that turns methods from books, long videos, podcasts, and other source material into executable skills for AI agents. It helps users package knowledge into callable workflows, using the repository's code, methods, and templates; catalogue add-ons relate to these agent skills.
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 kangarooking/cangjie-skill --skill monkey-mind-meditationgit clone --depth 1 https://github.com/kangarooking/cangjie-skillWrote 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/kangarooking/cangjie-skill/monkey-mind-meditation)<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/monkey-mind-meditation"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/monkey-mind-meditation/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/kangarooking/cangjie-skill/monkey-mind-meditation"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/monkey-mind-meditation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00158 | $0.01704 |
| Opus 5 | $0.00079 | $0.00852 |
| Sonnet 5 | $0.00032 | $0.00341 |
| Haiku 4.5 | $0.00016 | $0.00170 |
Grade A, and why
monkey-mind-meditation 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 11d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
心猴关停：观察思维与冥想
R — 原文 (Reading)
它就像一只在扔粪便的猴子，在房间里跑来跑去，制造麻烦，大喊大叫，打碎东西。它是完全不受制的。……从计算机编程的角度来解释，我尽量让我的大脑以“调试模式”运行。……当你观察你的想法时，你就会意识到其中有多少想法是出于恐惧的。当你意识到恐惧的那一刻，甚至不用去尝试，它就会消失。
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》 第二章·幸福
I — 方法论骨架 (Interpretation)
大脑的内心独白（「心猴」）是一个失控的焦虑程序，而不是「我」。 它大约 90% 的念头出于恐惧、10% 出于欲望；它默认开着，消耗能量、加速主观时间。 关闭它的方法不是对抗，而是观察： ① 调试模式——像看程序执行一样逐条检视念头，问「为什么我有这个想法」「我现在真的需要处理它吗」； ② 识别即分离——念头被意识到的那一刻就失去控制力； ③ 冥想=收件箱归零——坐着不抵抗，让童年以来的未解决情绪（藤壶/未回复邮件）逐个浮现、被客观处理； ④ 频率纪律——每天一小时、坚持 60 天，作为早上第一件事；冥想是心灵的间歇性禁食。 目标是让头脑成为仆人和工具，而不是主人；「专注的能力与迷失自我、活在当下、快乐以及更有效率的能力有关」。
A1 — 书中的应用 (Past Application)
案例 1: 刷牙时的心猴
- 问题: 刷牙时幻想未来播客采访
- 方法论的使用: 切到调试模式，逐条追问「为什么我要幻想未来？我终将死去」
- 结论: 念头被意识到即消散
- 结果: 回到对牙刷的觉察，「我只需要注意牙刷是多么的好」
案例 2: 冥想收件箱零
- 问题: 堆积的未解决情绪像藤壶黏住内心
- 方法论的使用: 每天静坐一小时，不抵抗念头，让它们逐个浮现
- 结论: 解决它们不需要工作，只需要观察（成年后有了距离与时间）
- 结果: 有一天进入「收件箱零」的心境——快乐、幸福和平静
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 睡前/独处时脑子停不下来
- 焦虑反刍：「总在担心/反复想同一件事」
- 想开始冥想但不知怎么做
- 专注力差：「做什么都分心」
语言信号
- "我脑子停不下来/胡思乱想"
- "怎么冥想/冥想有用吗"
- "我总是焦虑/担心"
- "monkey mind / can't stop thinking / how to meditate"
与相邻 skill 的区分
- 与
screen-detox的区别: 本 skill 处理内部杂念；屏幕戒断处理外部刺激源 - 与
rational-buddhism的区别: 冥想是技术，理性佛教是验证该技术的哲学框架
E — 可执行步骤 (Execution)
-
切换调试模式
- 完成标准: 发现自己在反刍/幻想时，暂停并问「我现在为什么有这个想法？」
- 判停条件: 若念头指向必须马上处理的实际问题（火灾/截止），先处理问题再回来
-
分类念头
- 完成标准: 把念头标为「恐惧类」或「欲望类」或「中性」，体会分类后的距离感
-
启动每日冥想
- 完成标准: 每天固定时间静坐（起步 10–20 分钟，目标 1 小时），只观察不抵抗，连续 60 天
-
做情绪收件箱整理
- 完成标准: 每周一次，把浮现的旧情绪写下来（写日志=写作冥想），标记已处理/待处理
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 急性精神危机/严重抑郁发作（先就医，冥想不能替代治疗）
- 用户需要立刻行动时（观察念头≠逃避行动）
作者在书中警告的失败模式
- 用冥想控制情绪: 「冥想并不意味你能突然获得控制你内心状态的超能力」，它先让你看见失控
- 期待超能力: 理性佛教拒绝「冥想带来漂浮/超能力」的玄学承诺
作者的盲点 / 时代局限
- 「每天一小时」对大多数人门槛过高，作者以自身高投入为标准
- 冥想收益是个人体验证据，个体差异大
容易混淆的邻近方法论
happiness-skill: 冥想是幸福训练的工具之一
相关 skills (阶段 3 定稿)
- composes-with:
happiness-skill、screen-detox、rational-buddhism
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 123 lines · 158 tokens per session scan A bd6aadac5a1d
monkey-mind-meditation is a skill published in the GitHub repository kangarooking/cangjie-skill (9,795 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 1,704 once invoked, about $0.0008 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
capability-circle
A framework for deciding which companies and industries an investor understands well enough to judge their future cash flow.
carl-file-organizer
A cautious tool for surveying and organising a messy folder, or analysing where disk space is being used. It first creates a proposed plan and waits for the user's approval before moving files.
gmail-summarize-latest
You are the Gmail Summarize Latest worker.
joko-moltbook
Use when queue-driven Moltbook posting agent with deduplication, idempotent operations, exponential backoff retries, and real-time monitoring. Use when working with joko moltbook.
moltbook-interact
Use when automating Moltbook engagement — content posting, community management, sentiment-aware replies, and account growth at scale.
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.