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 renky1025/agent-skills --skill graspgit clone --depth 1 https://github.com/renky1025/agent-skillsWrote 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/renky1025/agent-skills/grasp)<a href="https://agentmods.dev/skills/renky1025/agent-skills/grasp"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/grasp/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/renky1025/agent-skills/grasp"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/grasp.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 | $0.00092 | $0.04479 |
| Opus 5 | $0.00046 | $0.02240 |
| Sonnet 5 | $0.00018 | $0.00896 |
| Haiku 4.5 | $0.00009 | $0.00448 |
Grade A, and why
grasp 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 9d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grasp — 十维认知框架 × 加速学习协议
基于认知科学验证的7阶段交互协议,以十维认知框架为内容骨架,嵌入 Feynman 讲解、第一性原理拆解、主动回忆和间隔重复四种学习技术。
用户调用:/grasp <topic> [--phase=N]
协议设计理念
十维认知框架(内容骨架) × 学习科学技术(方法引擎)
───────────────────── ─────────────────────
维度 1-4 → Phase 1 Identity Feynman Technique + Teach-back
维度 5-6 → Phase 2 Anatomy 第一性原理拆解
维度 7-8 → Phase 3 Ecosystem 时间线 + 条件分析
维度 9-10 → Phase 4 Horizon 情景推演 + 批判审视
全 10 维 → Phase 5 Recall 主动回忆 + 维度诊断
全 10 维 → Phase 6 Map 知识地图 + 间隔重复
全 10 维 → Phase 7 Path 进阶路线 + 行动清单
10个维度依次为:
- 名称和概念 2. 类别和种属 3. 含义和定义 4. 特征和属性
- 组成和结构 6. 作用和功能 7. 条件和环境 8. 历程与演变
- 前景与趋势 10. 风险与挑战
Phase 1 — Identity · 身份层(维度 1-4)
目标:建立对知识对象的基本身份认知——它叫什么、属于什么类、如何定义、有哪些区分性特征。
方法:Feynman Technique + Teach-back loop
1.1 讲解(Feynman 方式)
用通俗语言依次覆盖 4 个维度,避免术语,使用类比:
| 维度 | 引导问题 | 输出 |
|---|---|---|
| 名称和概念 | 它叫什么?如果只能用一句话解释给外行,怎么说? | 一句话解释 + 常见别名/误称 |
| 类别和种属 | 它在知识树上属于哪个分支?上位/同位/下位概念是什么? | 概念层级关系 |
| 含义和定义 | 标准定义是什么?不同流派/场景下含义有差异吗? | 权威定义 + 语境差异 |
| 特征和属性 | 最关键的 3-5 个特征是什么?如何识别/衡量? | 核心特征清单 |
1.2 Teach-back
讲解结束后,要求用户用自己的话复述:
"现在用你自己的话给我讲一遍:它是什么、属于哪一类、如何定义、有什么特征。我会指出遗漏。"
1.3 诊断
根据用户复述,标出:
- 表达准确的部分(强化)
- 遗漏或模糊的部分(补讲)
- 概念混淆的部分(澄清,特别关注"类别和种属"中的易混淆概念)
签退:"Phase 1 complete. 对 [topic] 的身份特征已建立。进入解剖层? (y/n)"
Phase 2 — Anatomy · 解剖层(维度 5-6)
目标:理解知识的内部构造和外部功能——由什么构成、各部分如何协作、整体发挥什么作用。
方法:第一性原理拆解 + 功能分析
2.1 结构拆解(维度 5:组成和结构)
- 列出组成部分——将其拆解为不可再分的子单元
- 绘制关系——各组件之间的依赖、层次、时序或数据流关系
- 区分核心与辅助——哪些组件不可替代?哪些是可替换的?
- 展示一条因果链——从最基础组件出发,逐步组合,推导出完整的结构
2.2 功能分析(维度 6:作用和功能)
- 核心功能——它解决什么痛点 / 满足什么需求?
- 作用机制——输入端 → 内部过程 → 输出端,完整走通
- 典型场景——在哪些实际情境中发挥作用?
- 替代方案对比——为什么选它而不是别的?它在什么场景下是更好的选择?
2.3 第一性原理验证
"基于你看到的这些组件和它们的关系,如果把[某个核心组件]去掉或改变,会发生什么?"
引导用户从结构推导功能,而非死记硬背。
签退:"Phase 2 complete. 对 [topic] 的内部结构和工作原理已拆解。进入生态层? (y/n)"
Phase 3 — Ecosystem · 生态层(维度 7-8)
目标:理解知识存在的条件和历史脉络——它需要什��环境才能成立、从何而来、经历了哪些关键演变。
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.
- 9d ago First seen · 345 lines · 0 tokens per session scan A 89eab05d7a3d
grasp is a skill published in the GitHub repository renky1025/agent-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 4,479 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 2026-08-31.
Other skills, from other repositories
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
hidden-talents
Interview you in depth to surface overlooked or suppressed talents and write your Personal Talent Manual.
two-layer-explain
Explain a concept twice — for a newcomer and for an expert — then bridge the two layers, flag the likely misunderstandings, and set three check questions.
deconstruct
Reverse-engineer why a finished piece of work succeeds and extract what transfers to your own — rules, a checklist, and a first exercise.
socratic
Diagnose a confusion Socratically, one question at a time, until the question actually worth answering surfaces — then answer that one.
newbie-guide
A Chinese-language guide for beginners who have an unclear goal or do not know how to break a task into steps.