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/puppylpg/puppylpg.github.io/archive-chatnpx skills add puppylpg/puppylpg.github.io --skill archive-chatgit clone --depth 1 https://github.com/puppylpg/puppylpg.github.ioWrote 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/puppylpg/puppylpg.github.io/archive-chat)<a href="https://agentmods.dev/skills/puppylpg/puppylpg.github.io/archive-chat"><img src="https://agentmods.dev/badge/skills/puppylpg/puppylpg.github.io/archive-chat.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 | $0.00101 | $0.01789 |
| Opus 5 | $0.00051 | $0.00894 |
| Sonnet 5 | $0.00020 | $0.00358 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
archive-chat 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
将对话归档为文章
核心原则
对话是素材,不是文章结构;主线是问题链,不是知识清单。
最终读者没有参与对话,不知道谁问过什么、发生过哪些纠正。先从对话中提炼一个能够独立成立的主题,再把对话中的"为什么"重排成一条读者视角的问题链,按链成文。
最常见的失败模式:把对话覆盖的知识点当作待办清单,逐条写成章节。这样产出的是面向提问者的总结,不是科普文——每节的存在理由是"对话里讲过",而不是"读者读到这里必然想问"。零上下文读者没有那些背景,看到的是一堆突兀、互不关联的块。
禁止:
- 按聊天时间线复述"先问了什么、后来又补充什么";
- 把用户的问题逐条改成标题,形成隐性的 FAQ;
- 使用"你问到""前面回答过""真正的问题是"等依赖聊天上下文的表达;
- 把追问答案和纠错内容直接追加到文章末尾。
工作流程
1. 提炼主题与问题链素材
回顾完整对话,先确定:
- 一句话主题:文章最终解释什么对象或解决什么认知问题;
- 读者起点:零上下文读者已经知道什么,还缺哪些前置概念;
- 概念依赖:哪些对象、关系和背景必须先介绍;
- 问题链素材:对话中的哪些"为什么"和追问构成了认知推进,各自依赖什么前置概念;
- 关键素材:值得保留的例子、公式、图、代码、反例和边界;
- 文章范围:最终内容是否已经超出对话最初的问题。
删除重复问答、过程性确认、已被后续纠正的旧说法和仅对聊天参与者有意义的内容。对话里讲过但主线不需要的内容,同样删除,或降级进文末 FAQ。
2. 先搭问题链,再定骨架
不要先列章节再填内容。先把全文压缩成一条问题链:
场景/现象 → 读者必然产生的第一个疑问 → 回答 → 该回答引出的新疑问 → …… → 结论
规则:
- 每节必须被上一节必然逼出。 为每个链节写下"读者读到上一节末尾必然会问什么",本节就是它的答案;答不上来,说明这节位置错了,或者根本不该存在。
- 知识按需引入。 工具性概念(术语、分层、数据格式)不前置成"预备知识"章节——那是教科书思维。在第一个需要它的链节引入,概念才有存在理由,读者才知道为什么要学它。
- 删除测试。 某节删掉后文不会断裂,就说明它不在主线上。
- 链节定小节,相邻归大块。 链节即小节(H3);同属于一个论证阶段的相邻链节归并为一个大块(H2),每块开头用一句导语说明这块解决什么、和上一块的关系。平级 H2 超过约 6 个时,停下来归堆。
- 兜底顺序模板(场景→背景→例子→组件→机制→取舍→结论)只用于检查遗漏环节,不能替代问题链校验——模板排得通但问题链断掉的结构,仍然不合格。
写正文前检查每个小节:这一节为什么此时出现;它依赖的概念是否已经介绍;它为下一节建立了什么基础。
对话中的追问和纠正必须拆开,放回相应概念第一次需要它们的链节,改写成陈述式正文。
3. 写成独立、可读的科普文章
- 从具体场景、直觉冲突或读者能够感知的问题切入,不在开头直接宣布最终结论。
- 先用自然语言建立直觉,再给专业术语、公式或实现细节。
- 保留关键推理链和必要例子;不要为了缩短篇幅省略"为什么"。
- 公式使用本站兼容的行内
$...$和块级$$...$$,首次出现时解释符号与维度。 - 流程、层级、时序、架构和状态关系优先使用合适的 Mermaid 图;图必须承担解释任务。
- 引用外部资料时使用有意义的 Markdown 内联链接,优先引用官方或一手来源。
- 中文表达使用配对的弯引号"",避免翻译腔、套话和营销号标题。
标题应直接、可检索并覆盖全文范围。内部比较至少 3 个候选,优先选择最朴素准确的标题。
4. 写入博客
发布目录、分类、文件命名和 frontmatter 遵循根目录 AGENTS.md。未指定时写入 _ai/。
新建文章时使用 assets/TEMPLATE.md 提供的最小文件骨架。它只固定 frontmatter 和 TOC 的位置,不规定章节数量或叙事顺序;根据前面设计的问题链替换所有占位内容。
执行以下命令获取实际时间,不得硬写:
date '+%Y-%m-%d %H:%M:%S %z'
正文包含固定 TOC:
1. Table of Contents, ordered
{:toc}
5. 冷读验收
完稿后至少检查:
- 只读标题、H2 和每节首句,零上下文读者能否理解全文推进路径;
- 只读每节的首句和末句,能否连成一条"问题 → 回答 → 新问题"的递进链;断在哪节,就重排哪节;
- 逐节追问"这一节为什么此时出现":答案必须是"上一节结尾必然引出它",不能是"对话里讨论过这个点";
- 是否存在"预备知识"式的前置章节——工具性概念是否在第一个需要它的问题处才引入;
- 平级 H2 是否超过约 6 个、该归堆的是否已归为大块加小节;
- 是否仍有问答记录、聊天时间线、无前文指代或答疑式过渡;
- 每个概念是否在依赖它的内容之前出现;
- 公式、图、代码和例子是否真正帮助理解,并在首次需要的位置出现;
- 标题、description、categories、tags 和文件名是否符合
AGENTS.md; - 中文引号、Markdown 围栏和 LaTeX 分隔符是否正确。
What ships with it
1 file 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.
- 5d ago First seen · 109 lines · 101 tokens per session scan A f3a28e3776be
archive-chat is a skill published in the GitHub repository puppylpg/puppylpg.github.io (2 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 1,789 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…