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/zszz3/agentrecall/rewrite-technical-tutorialnpx skills add zszz3/AgentRecall --skill rewrite-technical-tutorialgit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/rewrite-technical-tutorial)<a href="https://agentmods.dev/skills/zszz3/agentrecall/rewrite-technical-tutorial"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/rewrite-technical-tutorial.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 | $0.00052 | $0.07046 |
| Opus 5 | $0.00026 | $0.03523 |
| Sonnet 5 | $0.00010 | $0.01409 |
| Haiku 4.5 | $0.00005 | $0.00705 |
Grade A, and why
rewrite-technical-tutorial 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 2d 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术教程写作与审校
判断一篇教程是否写清楚,不看它覆盖了多少名词,而看新读者能否沿着同一条因果链,回答“为什么需要、何时发生、数据长什么样、代码怎么推进、失败后怎么办”。
本 Skill 用于把源码分析、实现笔记和已有技术文章整理成工程师真正能读懂、能核对、能照着实现的教程。默认读者没有看过参考仓库、上游教程和作者之前的对话,也不知道某个产品的内部术语。
一、先确定任务模式
开始工作前先判断用户要的是哪一种交付。模式不同,允许执行的动作也不同。
- **只做 Review:**读取全文和必要证据,只报告问题;未经授权不要改文档。
- **直接改写:**完成结构分析后直接编辑用户指定的范围,并在写后重新读取验证。
- **逐条讨论:**一次只处理一处,固定给出“当前文本 → 问题 → 准备怎么改 → 修改后文本”,用户确认后再继续。
- **从零写作:**先建立读者问题、事实边界和章节骨架,再开始写正文;不要从某段代码直接扩写。
**用户要求“整篇重写”时,重新设计全文结构;用户只点名一节时,保留其余内容。**不要把整篇重写退化成同义词替换,也不要借局部修改顺手改动无关章节。
任务模式一旦确定,后文所有“修改、返工、写入和写后验证”要求只适用于直接改写、逐条讨论中已获确认的条目,以及从零写作。只做 Review 时始终保持只读:可以读取、核对证据、预览和报告问题,但禁止 update、insert、delete、overwrite 或替用户修正文档。
二、写作前先建立四张清单
动笔前先把材料整理成四张简短清单。它们不一定出现在成稿中,但必须在写作者脑中明确。
1. 读者问题清单
每章只围绕一个主要运行问题展开。问题要能被实现行为回答,不要只是模块名称。
- 好:模型什么时候会创建任务清单,清单保存在哪里?
- 好:上下文接近预算时,Harness 在下一次请求前做什么?
- 差:介绍任务清单工具。
- 差:深入理解 Context Management。
2. 事实清单
把材料按证据强度分开,写作时不要混用语气。
- **通用机制:**不依赖某个产品版本的设计原理。
- **教学实现:**为了说明机制而写的最小 Harness、示例阈值和辅助函数。
- **真实源码事实:**可以从指定文件、测试或提交直接确认的行为。
- **当前产品行为:**需要当前官方文档或当前版本源码支持的结论。
- **作者推断:**由现象或局部源码推得,必须降低表述强度并说明依据。
3. 状态清单
技术机制只要涉及状态,就必须回答下面五个问题:
- **谁写入:**模型、Harness、用户、工具还是异步回调?
- **何时写入:**任务开始、步骤切换、请求前、工具执行后还是异常恢复时?
- **存在哪里:**当前函数变量、会话内存、消息历史、本地文件、数据库还是对象存储?
- **能活多久:**是否能跨循环、跨 compact、跨会话、跨进程重启?
- **怎样恢复:**下一轮通过什么引用、字段或加载逻辑重新拿到?恢复失败会怎样?
“已经保存”不是完整结论。必须同时说明保存位置、生命周期和读取路径。
4. 术语清单
记录第一次出现的产品名、对象、字段和函数。每个术语第一次出现时立刻解释,不要先使用三次,再在后文补定义。默认读者不知道参考项目,也不要用“和上一章一样”“参考项目里也是这样”承担解释责任。
三、先搭整体心智模型,再拆实现细节
如果一个机制包含三个以上连续步骤、三个以上角色,或者存在正常与异常两条路径,先给整体流程。读者先知道自己在地图上的位置,后面的函数和字段才有意义。
推荐的章节顺序
- **具体问题:**用真实任务或故障说明为什么需要当前机制。
- **触发入口:**由谁决定启动,满足什么条件时发生。
- **整体流程图:**只画本章主线、关键判断和返回位置。
- **图后拆解:**用三到五个并列要点说明每个阶段分别做什么。
- **数据长相:**先给一份具体请求、状态或结果示例。
- **核心实现:**按主流程顺序展示代码,不按仓库目录顺序贴文件。
- **状态与副作用:**解释消息、内存、文件或数据库怎样变化。
- **失败路径:**说明未知工具、参数错误、超限、重试、降级或中断。
- **范围边界:**区分教学示例、源码快照和当前产品行为。
- **结果验证:**直接展示运行后的关键状态或输出,不留下未执行的“试一下”。
这是一条依赖顺序,不是要求每章都写十个小节。简单机制可以合并;复杂机制也可以拆章。判断标准是读者是否在遇到细节前已经拥有理解该细节所需的信息。
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.
- 2d ago First seen · 442 lines · 52 tokens per session scan A 027083fc0175
rewrite-technical-tutorial is a skill published in the GitHub repository zszz3/AgentRecall (762 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 7,046 once invoked, about $0.0003 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 2026-09-03.
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".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
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).