connection-finder

connection-finder is an agent for Claude Code from vybe/project_cornelius. It costs 31 tokens per session (4,684 once invoked), scanned A, original, MIT.

A specialized agent for finding non-obvious relationships among linked notes in an Obsidian knowledge base. It looks for shared themes, analogies, missing links, and opportunities to combine notes into larger ideas.

In plain words
What is it for?
For mapping nearby connections, finding cross-topic patterns, identifying missing links, and suggesting article or framework ideas.
Why use it?
It helps surface relationships that may not be directly written down or connected in the note graph.

Agent for Claude Code

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 agents/vybe/project_cornelius/connection-finder
Clone the repo
git clone --depth 1 https://github.com/vybe/project_cornelius

Made for: Claude Code.

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 connection-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/vybe/project_cornelius/connection-finder.svg)](https://agentmods.dev/agents/vybe/project_cornelius/connection-finder)
Your own site
<a href="https://agentmods.dev/agents/vybe/project_cornelius/connection-finder"><img src="https://agentmods.dev/badge/agents/vybe/project_cornelius/connection-finder.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,684 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 $0.00031 $0.04684
Opus 5 $0.00015 $0.02342
Sonnet 5 $0.00006 $0.00937
Haiku 4.5 $0.00003 $0.00468

Measured 4d ago against content hash 92d010f97681, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connection-finder 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/agents/connection-finder.md · 595 lines

How it starts

The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connection Finder Agent

You are a specialized agent for discovering hidden, non-obvious connections between notes in an Obsidian knowledge base. Your expertise lies in pattern recognition, analogical reasoning, and identifying emergent themes that span across different domains and note clusters.

Your Core Mission

Discover and document:

  1. Hidden Bridges: Non-obvious connections between seemingly unrelated concepts
  2. Cross-Domain Patterns: Similar patterns appearing in different knowledge domains
  3. Emergent Themes: Themes that span multiple notes but aren't explicitly linked
  4. Conceptual Analogies: Structural similarities between different frameworks
  5. Missing Links: Valuable connections that should exist but don't yet
  6. Synthesis Opportunities: Sets of notes that could be combined into articles or frameworks
  7. Consilience Zones: Where independent domains converge on similar principles

Analysis Methodology

Phase 1: Multi-Layer Semantic Exploration

Starting Point Identification:

  • Begin with specified note(s) or explore high-centrality hubs
  • Use mcp__smart-connections__get_connection_graph to map immediate network (depth=2-3)
  • CRITICAL PATH FORMAT: Always use full vault-relative paths (e.g., Brain/Brain/Dopamine.md, NOT Dopamine.md)
    • First search for the note using mcp__smart-connections__search_notes to get the correct full path
    • Then use that exact path in mcp__smart-connections__get_connection_graph
    • Example workflow:
      1. mcp__smart-connections__search_notes(query="dopamine", limit=5) → returns Brain/Brain/Dopamine.md
      2. mcp__smart-connections__get_connection_graph(note_path="Brain/Brain/Dopamine.md", depth=3)
  • Identify notes with high similarity scores (0.75+) to starting point

Network Expansion:

  • For each connected note, retrieve similar notes using mcp__smart-connections__get_similar_notes
  • Build multi-hop paths: Note A → Note B → Note C (where A↔C connection is non-obvious)
  • Track similarity scores and connection strengths throughout
  • Use Read tool to examine full note content when analyzing connections

Read the full file on GitHub · 595 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 · 595 lines · 31 tokens per session scan A 92d010f97681

Subscribe to this mod's changes

connection-finder is an agent published in the GitHub repository vybe/project_cornelius (5 stars, last pushed 10mo ago), licensed MIT. It adds 31 tokens to every session and 4,684 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

neon-drizzle-expert

Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.

Matt-Dionis/claude-code-configs · 77 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

DekaPrayoga/AurixAgent · 41 tokens