llm-wiki

llm-wiki is a skill for Claude Code, Codex from drvoss/everything-copilot-cli. It costs 35 tokens per session (1,814 once invoked), scanned A, original, MIT.

A persistent, linked Markdown wiki for saving researched domain knowledge and synthesized notes across sessions. It is a supplementary knowledge layer, not the official place for issues, code decisions, or project rules.

In plain words
What is it for?
Use it to collect knowledge about a technology area, product area, or codebase-adjacent domain. It helps preserve research that will be useful beyond a single question.
Why use it?
It prevents the same background research and explanations from being reconstructed every session. It also keeps research knowledge separate from GitHub tasks and committed project guidance.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/drvoss/everything-copilot-cli/llm-wiki
Any agent
npx skills add drvoss/everything-copilot-cli --skill llm-wiki
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

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/drvoss/everything-copilot-cli/llm-wiki.svg)](https://agentmods.dev/skills/drvoss/everything-copilot-cli/llm-wiki)
Your own site
<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/llm-wiki"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/llm-wiki.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01814
Opus 5 $0.00017 $0.00907
Sonnet 5 $0.00007 $0.00363
Haiku 4.5 $0.00003 $0.00181

Measured yesterday against content hash 2fa8951c03dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

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 yesterday.

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.

skills/workflow/llm-wiki/SKILL.md · 203 lines

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.

LLM Wiki

Build a persistent, interlinked markdown wiki for domain knowledge, research notes, and long-lived synthesized context. This follows Andrej Karpathy's LLM Wiki pattern, but keeps the repository boundary clear: the wiki is a supplementary knowledge layer, not the system of record for issues, PRs, shipped decisions, or canonical project rules.

In this repository's philosophy:

  • GitHub stays the system of record for tasks, code review, and shipped artifacts
  • project-specific durable guidance still belongs in .github/copilot-instructions.md, CONTRIBUTING.md, guides, or ADRs
  • the wiki is best for domain knowledge that would otherwise be re-derived every session

When to Use

  • You are researching a domain across many external sources and want the knowledge to compound
  • You want a persistent knowledge base about a technology landscape, product area, or codebase-adjacent domain
  • The same background explanation keeps getting repeated across sessions
  • A query answer would be expensive to reconstruct from raw notes every time

When NOT to Use

Instead of llm-wiki Use
One-off research or a single answer with citations deep-research
Promoting repeated repo-specific lessons into durable project guidance knowledge-curator
Recovering what happened in prior Copilot sessions cross-session-memory
Issue tracking, delivery planning, or implementation state GitHub Issues / PRs / session SQL

Boundary with Other Skills

Skill Best for
llm-wiki Compounding external or domain knowledge in a separate markdown wiki
knowledge-curator Graduating stable repository guidance into committed project docs
deep-research Evidence-heavy investigation that may or may not be worth filing permanently
cross-session-memory Looking up prior local session history and decisions

If a wiki insight becomes a stable repository rule, promote it out of the wiki into the committed docs that future contributors actually depend on.

Read the full file on GitHub · 203 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. yesterday First seen · 203 lines · 35 tokens per session scan A 2fa8951c03dd

Subscribe to this mod's changes

llm-wiki is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 1,814 once invoked, about $0.0002 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 2026-09-03.