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/qxbyte/pluginhub/wiki-curatenpx skills add qxbyte/pluginhub --skill wiki-curategit clone --depth 1 https://github.com/qxbyte/pluginhubWhat 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 | $0.00122 | $0.04298 |
| Opus 5 | $0.00061 | $0.02149 |
| Sonnet 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 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 — 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.
- 2d 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 28d ago), licensed MIT. It adds 122 tokens to every session and 4,298 once invoked, about $0.0006 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
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
knowledge-base-management
Obsidian 知识库全生命周期管理：三层架构、素材入库(ABC分级)、健康检查、GBrain/GraphRAG/LLM Wiki 三件套集成、目录整理.
textbook-to-md
Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference. Use this skill whenever: (1) the user asks to convert a textbook/PDF chapter to markdown, (2) you need to search textbook content and no markdown version exists yet, (3) batch-converting a set of reference books into a knowledge…
skillbuddy-skill-creator
通过自然语言对话创建或更新可由多个本机 AI agent 使用的 Skill，并检查重复、触发条件、资源依赖与跨平台兼容性。用户在 SkillBuddy 中要求新建、完善、迁移或适配 Skill 时使用。.