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.
git clone --depth 1 https://github.com/vbarsoum1/llm-wiki-compilerWrote 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/plugins/vbarsoum1/llm-wiki-compiler/klore)<a href="https://agentmods.dev/plugins/vbarsoum1/llm-wiki-compiler/klore"><img src="https://agentmods.dev/badge/plugins/vbarsoum1/llm-wiki-compiler/klore/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/plugins/vbarsoum1/llm-wiki-compiler/klore"><img src="https://agentmods.dev/badge/plugins/vbarsoum1/llm-wiki-compiler/klore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
klore 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.
What it actually says
{
"name": "klore",
"description": "LLM Knowledge Compiler — compile raw sources into an Obsidian-compatible wiki with AI-driven editorial judgment",
"version": "0.1.0",
"author": {
"name": "Victor Barsoum"
}
}
What it installs
The manifest is a name and a version. 8 commands, 1 hook travel with it, and installing the plugin installs all of them — 72 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 9 lines scan A 097b27e48fba
klore is a plugin published in the GitHub repository vbarsoum1/llm-wiki-compiler (27 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
obsidian-wiki
Grow an Obsidian second brain with your AI agent: ingest docs, chat history and URLs into interlinked markdown, then query it with citations. Karpathy's LLM Wiki pattern as Claude Code skills.
llm-wiki
Self-maintaining LLM wiki (Karpathy pattern): recall, observe, retro, capture sources, ensure pages, lint, and ingest. 15 tools over MCP.
mb
Karpathy's LLM-Wiki pattern as a Claude Code plugin. Build and maintain a persistent, AI-tended research wiki from sources, capture daily thoughts, query what you know, lint for orphans and contradictions. Operations: /mb:init, /mb:contribute, /mb:build, /mb:ask, /mb:lint, /mb:status, /mb:research, /mb:daily-brief…
kb
Build and maintain LLM-powered knowledge bases as Obsidian wikis with compile, query, lint, and evolve workflows.
llm-wiki
LLM-maintained personal wiki. Claude actively ingests, synthesizes, and cross-links knowledge across all your projects. Based on Karpathy's LLM Wiki pattern.
Pagecraft marketplace
Pagecraft combines a durable wiki control plane with an execution layer for ambiguity control, minimal edits, and verified outcomes. It supports active-memory retrieval through wiki/hot.md, canonical index/log discipline, immutable raw sources, and reusable ingest workflows.