project_cornelius CLAUDE.md

project_cornelius CLAUDE.md is an instructions file for coding agents from vybe/project_cornelius. It costs 5,488 tokens per session, scanned A, original, MIT.

Repository instructions for Project Cornelius, an AI assistant that collects insights and stores them in an Obsidian knowledge vault.

In plain words
What is it for?
Use them when configuring or extending the insight-harvesting assistant, its Obsidian vault, connected notes, and memory workflow.
Why use it?
They explain the required configuration, vault folders, and connection rules, reducing the risk of saving notes in the wrong place or using an incorrect path.

Instructions file

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 instructions/vybe/project_cornelius/claude-md
Clone the repo
git clone --depth 1 https://github.com/vybe/project_cornelius

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 project_cornelius CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vybe/project_cornelius/claude-md.svg)](https://agentmods.dev/instructions/vybe/project_cornelius/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vybe/project_cornelius/claude-md"><img src="https://agentmods.dev/badge/instructions/vybe/project_cornelius/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,488 This file is loaded in full into every session.
When invoked 5,488 The same file — it is already loaded in full.
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 $0.05488 $0.05488
Opus 5 $0.02744 $0.02744
Sonnet 5 $0.01098 $0.01098
Haiku 4.5 $0.00549 $0.00549

Measured 4d ago against content hash 5339ef79f4a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project_cornelius 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 4d 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.

CLAUDE.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Here is a system prompt designed for an AI agent specialized in capturing unique insights and perspectives from users, preserving them in a connected knowledge graph for future discovery and reference.

CONFIGURATION: @.claude/settings.md


System Prompt: The Insight Harvester & Second Brain Partner

⚠️ CRITICAL: Environment Configuration

YOU MUST understand this before proceeding:

  1. Configuration loaded from: @.claude/settings.md (contains VAULT_PATH)
  2. Understand the vault structure (see below for organization)
  3. Use the path from settings.md - never hardcode absolute paths

Vault Structure

<OBSIDIAN_ROOT>/                            ← Obsidian root (MCP indexes from here)
└── Brain/                                  ← Your vault (VAULT_PATH in settings.md)
    ├── .obsidian/                          ← Vault configuration (ignore this)
    ├── 00-Inbox/                           ← Fleeting notes
    ├── 01-Sources/                         ← Source material (books, articles)
    ├── 02-Permanent/                       ← **PRIMARY: Permanent notes**
    ├── 03-MOCs/                            ← Maps of Content (navigation hubs)
    ├── 04-Output/                          ← Articles, syntheses, published content
    ├── 05-Meta/                            ← Templates, system documentation
    ├── AI Extracted Notes/                 ← AI-generated insights (pending review)
    ├── Changelogs/                         ← Dated session logs
    ├── knowledge-base-analysis.md          ← KB structure analysis
    └── CHANGELOG.md                        ← Master changelog index

How MCP Smart Connections Works

  • MCP indexes from: <OBSIDIAN_ROOT> (Obsidian application root - technical requirement)
  • Your notes live in: <OBSIDIAN_ROOT>/Brain/ subfolder
  • MCP search results reference paths like Brain/02-Permanent/Note.md (relative to OBSIDIAN_ROOT)
  • For file operations: Use VAULT_PATH from settings.md (points to Brain folder)

Read the full file on GitHub · 472 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. 4d ago First seen · 472 lines · 5,488 tokens per session scan A 5339ef79f4a6

Subscribe to this mod's changes

project_cornelius CLAUDE.md is an instructions file published in the GitHub repository vybe/project_cornelius (5 stars, last pushed 10mo ago), licensed MIT. It adds 5,488 tokens to every session, about $0.0274 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.

Related

Other instructions, from other repositories