A skill that creates the initial folder structure for a Karpathy-style LLM wiki, with separate raw sources and curated notes. It also creates starter index, log, and instruction files.

Use it when starting a project wiki that will collect sources and turn them into structured notes through later ingestion and editing.

It gives a new wiki a consistent place for original material, organized knowledge, and ongoing records.

wiki-init — Skill for Claude Code by flsteven87

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 flsteven87/llm-wiki-mcp --skill wiki-init

Clone the repo

git clone --depth 1 https://github.com/flsteven87/llm-wiki-mcp

Made for: Claude Code.

Or install llm-wiki-skills, the plugin that ships this one along with the rest of its 4 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/flsteven87/llm-wiki-mcp/wiki-init/github.svg)](https://agentmods.dev/skills/flsteven87/llm-wiki-mcp/wiki-init)

Your own site

<a href="https://agentmods.dev/skills/flsteven87/llm-wiki-mcp/wiki-init"><img src="https://agentmods.dev/badge/skills/flsteven87/llm-wiki-mcp/wiki-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/flsteven87/llm-wiki-mcp/wiki-init"><img src="https://agentmods.dev/badge/skills/flsteven87/llm-wiki-mcp/wiki-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 947 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00232	$0.00947
Opus 5	$0.00116	$0.00474
Sonnet 5	$0.00046	$0.00189
Haiku 4.5	$0.00023	$0.00095

Measured 9d ago against content hash a65ce3f5503c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiki-init 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 9d 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.

src/llm_wiki_mcp/skills/wiki-init/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-init

Scaffold a Karpathy-style LLM wiki so the user can start ingesting sources immediately. The pattern is described in https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f — this skill produces the minimal scaffold it implies.

What you create

<project>/
  raw/             # immutable source archive (sibling, outside MCP's view)
  wiki/            # THIS folder is what --wiki-root points at
    CLAUDE.md      # the schema, co-evolved with the user
    index.md       # catalog, organized by category
    log.md         # append-only chronological record
    pages/         # LLM-authored pages live here

raw/ is a project-level sibling of wiki/ — MCP never touches it, but wiki-ingest reads from it via host Read when processing a new source. wiki/ is owned entirely by the LLM; wiki/CLAUDE.md is the only file the user regularly edits. MCP's --wiki-root points at <project>/wiki/, NOT at <project>/.

Intake

Ask the user three things, in order:

Path — where to create the wiki. Default ./wiki-root. This is the <project> path; suggest ~/wikis/<topic> if the user keeps multiple wikis.
Topic — one sentence describing what this wiki is about.
Primary language — the language wiki pages will be written in (default: English).

If <project>/wiki/CLAUDE.md already exists, stop and tell the user the wiki exists. Do not overwrite.

Scaffold

This skill does not require the llm-wiki-mcp server to be running — it creates the directory the server will later point at. Use the standard Write and Bash tools.

Create <project>/raw/ and <project>/wiki/pages/.
Write <project>/wiki/CLAUDE.md from templates/CLAUDE.md.template, substituting {{TOPIC}} and {{LANGUAGE}}.
Write <project>/wiki/index.md from templates/index.md.template, substituting {{TOPIC}}.
Write <project>/wiki/log.md from templates/log.md.template, substituting {{DATE}} (today, YYYY-MM-DD) and {{TOPIC}}.
Print the contents of templates/mcp-wiring.md with {{ABSOLUTE_PATH}} substituted to the absolute path of <project>/wiki (NOT <project>).
Tell the user the wiki is ready and suggest they restart their MCP client, then say ingest <first-source> to trigger wiki-ingest.

Read the full file on GitHub · 70 lines

Files

What ships with it

5 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.

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.

9d ago First seen · 70 lines · 232 tokens per session scan A a65ce3f5503c

Subscribe to this mod's changes

wiki-init is a skill published in the GitHub repository flsteven87/llm-wiki-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 232 tokens to every session and 947 once invoked, about $0.0012 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.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

wiki-init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

wiki-init

What you create

Intake

Scaffold

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

systematic-debugging

local-ai-agents

next-cache-components-adoption

insight-error-page

next-cache-components-optimizer

next-partial-prefetching-adoption