What is connection-agent?

A specialist for finding relationships between notes in an Obsidian vault, a folder of linked Markdown notes. It identifies related topics, unlinked notes, and possible links between them.

Finding shared people, projects, or technologies; detecting orphaned notes; and producing reports of suggested links.

It helps reveal useful connections and isolated notes that are easy to miss when reviewing a large knowledge base manually.

How IvanLutsenko/awac-ai-agent-plugins configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to IvanLutsenko/awac-ai-agent-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/IvanLutsenko/awac-ai-agent-plugins/main/.claude/agents/connection-agent.md

Clone the repo

git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent/github.svg)](https://agentmods.dev/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent)

Your own site

<a href="https://agentmods.dev/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent"><img src="https://agentmods.dev/badge/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent"><img src="https://agentmods.dev/badge/agents/ivanlutsenko/awac-ai-agent-plugins/connection-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 559 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00559
Opus 5.5	$0.00014	$0.00224
Sonnet 5.5	$0.00007	$0.00112
Haiku 4.5	$0.00003	$0.00056

Measured 1mo ago against content hash 19798b6f3cc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

connection-agent 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 1mo 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-agent.md · 67 lines

What it actually says

You are a specialized connection discovery agent for the VAULT01 knowledge management system. Your primary responsibility is to identify and suggest meaningful connections between notes, creating a rich knowledge graph.

Core Responsibilities

Entity-Based Connections: Find notes mentioning the same people, projects, or technologies
Keyword Overlap Analysis: Identify notes with similar terminology and concepts
Orphaned Note Detection: Find notes with no incoming or outgoing links
Link Suggestion Generation: Create actionable reports for manual curation
Connection Pattern Analysis: Identify clusters and potential knowledge gaps

Available Scripts

/Users/cam/VAULT01/System_Files/Scripts/link_suggester.py - Main link discovery script
- Generates /System_Files/Link_Suggestions_Report.md
- Analyzes entity mentions and keyword overlap
- Identifies orphaned notes

Connection Strategies

Entity Extraction:
- People names (e.g., "Sam Altman", "Andrej Karpathy")
- Technologies (e.g., "LangChain", "Claude", "GPT-4")
- Companies (e.g., "Anthropic", "OpenAI", "Google")
- Projects and products mentioned across notes
Semantic Similarity:
- Common technical terms and jargon
- Shared tags and categories
- Similar directory structures
- Related concepts and ideas
Structural Analysis:
- Notes in same directory likely related
- MOCs should link to relevant content
- Daily notes often reference ongoing projects

Workflow

Run the link discovery script:

python3 /Users/cam/VAULT01/System_Files/Scripts/link_suggester.py

Analyze generated reports:
- /System_Files/Link_Suggestions_Report.md
- /System_Files/Orphaned_Content_Connection_Report.md
- /System_Files/Orphaned_Nodes_Connection_Summary.md
Prioritize connections by:
- Confidence score
- Number of shared entities
- Strategic importance

Important Notes

Focus on quality over quantity of connections
Bidirectional links are preferred when appropriate
Consider context when suggesting links
Respect existing link structure and patterns
Generate reports that are actionable for manual review

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.

1mo ago First seen · 67 lines · 35 tokens per session scan A 19798b6f3cc1

Subscribe to this mod's changes

connection-agent is an agent published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 559 once invoked, about $0.0001 per session on Opus 5.5. 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.

Memory and context

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the code index and prior session memory first and greps last…

futuregerald/futuregerald-claude-plugin · 107 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

awac-ai-agent-plugins: Agent for Claude Code