Borrowing it
Nothing to install: this file belongs to frankchu91/mindbase-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankchu91/mindbase-llm-wiki/main/CLAUDE.mdgit clone --depth 1 https://github.com/frankchu91/mindbase-llm-wikiWrote 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/instructions/frankchu91/mindbase-llm-wiki/claude-md)<a href="https://agentmods.dev/instructions/frankchu91/mindbase-llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/frankchu91/mindbase-llm-wiki/claude-md/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/instructions/frankchu91/mindbase-llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/frankchu91/mindbase-llm-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03400 | $0.03400 |
| Opus 5 | $0.01700 | $0.01700 |
| Sonnet 5 | $0.00680 | $0.00680 |
| Haiku 4.5 | $0.00340 | $0.00340 |
Grade A, and why
mindbase-llm-wiki CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MindBase — North Star for Claude Code
If you're an agent working on this codebase, read in this order:
docs/pivot-plan-2026-05-25.md— the CURRENT canonical plan. We are pivoting from "AI second brain" to "AI research analyst that builds a wiki." Everything before this date is legacy direction.docs/llm-wiki.md— Karpathy's pattern, our foundational thesis.- This file — what's built, what's missing, hard contracts, repo conventions.
If a change conflicts with the pivot plan, the pivot plan wins. If a change preserves a feature the pivot plan kills (chat-as-home, daily journal, SRS UI surface, generic "PKM" framing), push back.
Product thesis (one paragraph)
MindBase implements Andrej Karpathy's LLM-Wiki pattern (docs/llm-wiki.md),
turned into a product for users who can't or won't run claude-code + obsidian + a hand-written CLAUDE.md themselves. The LLM incrementally builds and maintains
a persistent wiki from your raw sources — not RAG-retrieves at query time.
The wiki is a compounding artifact: cross-references are pre-baked,
contradictions pre-flagged, synthesis pre-written. The LLM owns the wiki layer;
the user owns sources, exploration, and asking the right questions.
This is NOT another Notion / Obsidian / NotebookLM. Specifically:
- Notion is a passive container — you organize, it stores.
- NotebookLM is RAG — knowledge is re-derived per query, never accumulates.
- Obsidian is a markdown editor — humans do all the maintenance.
- MindBase is the active maintainer that gardens your knowledge for you.
The 3-layer architecture (from Karpathy)
| Layer | Owner | In MindBase |
|---|---|---|
| Raw sources — articles, PDFs, web clips, captures. Immutable. | User curates; LLM reads. | ~/mindbase-data/raw/<date>/<id>.{md,meta.json,original.pdf} |
| The wiki — markdown concept pages, entity pages, summaries. | LLM writes & maintains. | ~/mindbase-data/wiki/{concepts,notes,sources,attachments}/ |
| The schema — conventions, page formats, ingest workflow. | User and LLM co-evolve. | ⚠️ Currently hard-coded in prompts. Should become a per-project user-editable file. |
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 · 214 lines · 3,400 tokens per session scan A c142b7fb2dd2
mindbase-llm-wiki CLAUDE.md is an instructions file published in the GitHub repository frankchu91/mindbase-llm-wiki (97 stars, last pushed 15d ago), licensed MIT. It adds 3,400 tokens to every session, about $0.0170 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.