llm-wiki

llm-wiki is a skill for Claude Code, Codex from moltis-org/moltis. It costs 37 tokens per session (4,075 once invoked), scanned B, a copy of llm-wiki, MIT.

A persistent, linked collection of Markdown notes for building knowledge about large language models. It ingests sources, connects related notes, answers questions from the stored material, and checks the collection for inconsistencies.

In plain words
What is it for?
Use it to start or update a wiki, add sources, query existing notes, and lint or audit the knowledge base for consistency.
Why use it?
It reduces repeated research by keeping findings, cross-references, and flagged contradictions in one maintained knowledge base.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Good fit Use it to start or update a wiki, add sources, query existing notes, and lint or audit the knowledge base for consistency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moltis-org/moltis/llm-wiki
About the project

Moltis is a persistent personal agent server written in Rust that runs on hardware controlled by its user. It provides an AI agent with sandboxed command execution, model-provider connections, memory, voice, scheduling, messaging integrations, browser automation, and MCP tools. Its catalogue add-ons extend the agent’s workflows and available tools.

moltis-org/moltis · 2,847 stars · on GitHub · moltis.org

Install

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.

Any agent
npx skills add moltis-org/moltis --skill llm-wiki
Clone the repo
git clone --depth 1 https://github.com/moltis-org/moltis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for llm-wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/moltis-org/moltis/llm-wiki/github.svg)](https://agentmods.dev/skills/moltis-org/moltis/llm-wiki)
Your own site
<a href="https://agentmods.dev/skills/moltis-org/moltis/llm-wiki"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/llm-wiki/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.

agentmods 80×15 button for llm-wiki

Your own site · 80×15
<a href="https://agentmods.dev/skills/moltis-org/moltis/llm-wiki"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/llm-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 83% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.04075
Opus 5 $0.00018 $0.02037
Sonnet 5 $0.00007 $0.00815
Haiku 4.5 $0.00004 $0.00407

Measured 7d ago against content hash 8bad1aaf8f22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

llm-wiki scanned grade B with 1 finding 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo loginctl enable-linger $USER
Origin

This is a copy

83% identical to llm-wiki — 91 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

crates/skills/src/assets/research/llm-wiki/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Karpathy's LLM Wiki

Build and maintain a persistent, compounding knowledge base as interlinked markdown files. Based on Andrej Karpathy's LLM Wiki pattern.

Unlike traditional RAG (which rediscovers knowledge from scratch per query), the wiki compiles knowledge once and keeps it current. Cross-references are already there. Contradictions have already been flagged. Synthesis reflects everything ingested.

Division of labor: The human curates sources and directs analysis. The agent summarizes, cross-references, files, and maintains consistency.

When This Skill Activates

Use this skill when the user:

  • Asks to create, build, or start a wiki or knowledge base
  • Asks to ingest, add, or process a source into their wiki
  • Asks a question and an existing wiki is present at the configured path
  • Asks to lint, audit, or health-check their wiki
  • References their wiki, knowledge base, or "notes" in a research context

Wiki Location

Location: Set via WIKI_PATH environment variable (e.g. in your environment).

If unset, defaults to ~/wiki.

WIKI="${WIKI_PATH:-$HOME/wiki}"

The wiki is just a directory of markdown files — open it in Obsidian, VS Code, or any editor. No database, no special tooling required.

Architecture: Three Layers

wiki/
├── SCHEMA.md           # Conventions, structure rules, domain config
├── index.md            # Sectioned content catalog with one-line summaries
├── log.md              # Chronological action log (append-only, rotated yearly)
├── raw/                # Layer 1: Immutable source material
│   ├── articles/       # Web articles, clippings
│   ├── papers/         # PDFs, arxiv papers
│   ├── transcripts/    # Meeting notes, interviews
│   └── assets/         # Images, diagrams referenced by sources
├── entities/           # Layer 2: Entity pages (people, orgs, products, models)
├── concepts/           # Layer 2: Concept/topic pages
├── comparisons/        # Layer 2: Side-by-side analyses
└── queries/            # Layer 2: Filed query results worth keeping

Read the full file on GitHub · 449 lines

Changes

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.

  1. 7d ago First seen · 449 lines · 37 tokens per session scan B 8bad1aaf8f22

Subscribe to this mod's changes

llm-wiki is a skill published in the GitHub repository moltis-org/moltis (2,847 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 4,075 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 83% identical to llm-wiki, differing in 91 lines, and is treated as a copy.