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 qxbyte/pluginhub --skill wiki-curategit clone --depth 1 https://github.com/qxbyte/pluginhubWrote 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/qxbyte/pluginhub/wiki-curate)<a href="https://agentmods.dev/skills/qxbyte/pluginhub/wiki-curate"><img src="https://agentmods.dev/badge/skills/qxbyte/pluginhub/wiki-curate/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/qxbyte/pluginhub/wiki-curate"><img src="https://agentmods.dev/badge/skills/qxbyte/pluginhub/wiki-curate.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 | $0.00122 | $0.04298 |
| Opus 5.5 | $0.00049 | $0.01719 |
| Sonnet 5.5 | $0.00024 | $0.00860 |
| Haiku 4.5 | $0.00012 | $0.00430 |
Grade A, and why
wiki-curate 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Curate
Host-tool convention 🔧: tool names in this skill —
AskUserQuestion(structured multiple-choice question) — are written for Claude-family hosts (Claude Code / CodeBuddy), where naming them directly is the most reliable. On a host that lacks one, use its nearest equivalent (a structured-question tool); with no equivalent, fall back to a plain-text question. The described behavior is what matters, not the exact tool name.
配置说明：vault 的结构配置存在家目录注册表
~/.config/obsidian-wiki/configs/<库名>.json（按 active 库解析；未注册则回退库内<vault>/.wiki/config.json）。schema 见本插件根config.example.json。脚本仍通过--vault "<vault 根路径>"指定 vault，结构由注册表/回退提供。脚本定位：脚本装在本 skill 的
scripts/目录下。用本 skill 的 base directory 把相对路径scripts/<脚本名>.py拼成绝对路径来跑（不解析环境变量、不 find 缓存）。
把目标 vault 长期维护成 Karpathy 风格的 LLM Wiki——可累积、可检索、可双链浏览的本地知识库。
设计依据
本 skill 基于 Andrej Karpathy 在 2026-04 发布的 LLM Wiki 方法论。核心思想：
- 不靠 RAG 反复检索原始材料，而是让 LLM 增量维护一个结构化、持久的 Markdown wiki。
- 三层架构：Sources（只读）/ Wiki（LLM 写）/ Schema（规约）。
- 三类操作：Ingest（吸纳）/ Query（提问）/ Lint（健康检查）。
- 关键产物：index（带摘要的目录） + log（append-only 操作日志）。
- 哲学：人选材+提问，LLM 摘要+归类+补链+记账+体检。
详细方法论与原文出处见 references/karpathy-llm-wiki.md。
Vault 三层映射
| 层 | 当前 vault 中的目录 | 谁写 |
|---|---|---|
| Raw sources（只读） | 07-Ideas/、10-Work/、SpecIn/ |
用户写，LLM 绝不修改 |
| Raw sources（可归档） | 99-Inbox/、Clippings/ |
用户放入，LLM ingest 后用户确认可移动 |
| 参考资料 | 03-Memo/、Database/、_scaffold/ |
用户维护，LLM 仅引用 |
| Wiki | 00-Index/（结构归 wiki-struct）、01-Concepts/、02-Models/、04-Tools/、05-Workflows/、06-Prompts/、08-Sources/、09-Journal/ |
LLM 增量写入与维护 |
| Schema | obsidian-wiki/{wiki-curate, wiki-struct}/ |
人类制定 |
三条硬红线（必须遵守）
完整规则与边界情况见 references/readonly-dirs-policy.md。要点：
| 目录 | 永远不做 | 可以做 |
|---|---|---|
07-Ideas/ |
mv / rm / rename / 重写正文 / 修 frontmatter | 在相关内容笔记正文补 [[..]] 双链；在 01-Concepts/ 提炼通用概念 |
10-Work/ |
mv / rm / rename / 复制敏感字段到 Wiki / 批量改 MEMORY.md | 提炼可公开概念到 01-Concepts/（按用户启动、逐个确认） |
SpecIn/ |
mv / rm / rename / 改写 specode 工作流文档（requirements.md / design.md / tasks.md 等） | 在相关内容笔记补链接；知识沉淀交 specode 的 /specode:distill |
What ships with it
7 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.
- 1mo ago First seen · 203 lines · 122 tokens per session scan A 0aec01746223
wiki-curate is a skill published in the GitHub repository qxbyte/pluginhub (3 stars, last pushed 25d ago), licensed MIT. It adds 122 tokens to every session and 4,298 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
douyin-favorites-to-knowledge
A tool for copying videos saved in an authorised Douyin account into a local Markdown or Obsidian knowledge base. Douyin is a Chinese short-video platform, and Obsidian is an app for organising linked notes.
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…
kb-ingest
Ingest documents from the workhub vault inbox into the knowledge base. Classifies notes into projects/knowledge/archive, proposes tasks for actionable items, links, and indexes. Use when new notes land in inbox/ or a path needs filing.