A knowledge-base management plugin for keeping project information in a shared, structured wiki. It can ingest project changes, answer questions across projects, check pages and links, detect stale information, and synchronise updates.

Use it to build or update a project wiki, search an inventory of projects, check its structure and links, find outdated pages, and refresh pages after project changes.

It reduces the need to reconstruct project context from scattered files. Checks help reveal broken links, outdated pages, and formatting problems in the knowledge base.

llm-wiki — Plugin by lacolaco

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.

Claude Code

/plugin marketplace add lacolaco/claude-plugins

agentmods

npx agentmods add plugins/lacolaco/claude-plugins/llm-wiki

Clone the repo

git clone --depth 1 https://github.com/lacolaco/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

llm-wiki 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.

llm-wiki/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "llm-wiki",
  "description": "Knowledge base management skills for the LLM Wiki pattern (Karpathy-style). Provides ingest (project manifest changes → wiki pages), query (cross-project inventory questions), lint (OKF v0.1 conformance, broken links, staleness detection), and sync (re-ingest stale pages). The KB lives at ~/.knowledge/ with a raw/wiki two-layer OKF v0.1 layout.",
  "version": "1.0.0",
  "author": {
    "name": "Suguru Inatomi"
  },
  "repository": "https://github.com/lacolaco/claude-plugins",
  "license": "MIT",
  "keywords": ["knowledge-base", "llm-wiki", "okf", "ingest", "lint", "karpathy"]
}

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.

2d ago First seen · 12 lines scan A 3496e7c7023a

Subscribe to this mod's changes

llm-wiki is a plugin published in the GitHub repository lacolaco/claude-plugins (5 stars, last pushed 6d 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 2026-08-31.

Code review Data and AI Memory and context

llm-wiki

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

humanizer

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc