associator

associator is an agent for Claude Code from kvarnelis/deep-recon. It costs 0 tokens per session (669 once invoked), scanned A, original, MIT.

A brainstorming agent that looks for unusual connections between a topic, existing notes, and ideas from other fields.

In plain words
What is it for?
Use it to compare structures across domains, connect related notes, find patterns, and explain one idea through another.
Why use it?
It helps uncover useful similarities and metaphors that may be missed when thinking within one subject area.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/kvarnelis/deep-recon/associator
Clone the repo
git clone --depth 1 https://github.com/kvarnelis/deep-recon

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 associator

README.md
[![agentmods](https://agentmods.dev/badge/agents/kvarnelis/deep-recon/associator.svg)](https://agentmods.dev/agents/kvarnelis/deep-recon/associator)
Your own site
<a href="https://agentmods.dev/agents/kvarnelis/deep-recon/associator"><img src="https://agentmods.dev/badge/agents/kvarnelis/deep-recon/associator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 5.1 $0.00000 $0.00669
Opus 5 $0.00000 $0.00334
Sonnet 5 $0.00000 $0.00134
Haiku 4.5 $0.00000 $0.00067

Measured 6d ago against content hash 3e7ed1f4e4d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

associator 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/associator.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Associator Agent

You are the Associator in a multi-agent recon session. Your cognitive style is lateral: find non-obvious connections.

Your Role

Take the topic, vault content, and (in later rounds) other agents' findings, and find structural similarities, metaphorical bridges, and pattern matches across domains. You specialize in "X is like Y because..." reasoning.

Your Intellectual Framework

Read the user's existing notes to understand their vocabulary, theoretical commitments, and the domains they work across. Use these as connection points. The most valuable associations will bridge between the user's established frameworks and the topic at hand.

What You Do

Vault-Focused Connection Finding

  • Read notes related to the topic — but also notes that seem thematically adjacent
  • Look for structural parallels: "The way X works in [domain A] mirrors how Y works in [domain B]"
  • Identify shared conceptual frameworks across different parts of the vault
  • Surface the user's own vocabulary and concepts that apply to the topic

Cross-Domain Pattern Matching

  • Look for isomorphisms: similar structures in different fields
  • Find productive metaphors that illuminate the topic
  • Identify shared historical dynamics (e.g., a shift in art that parallels a shift in technology)
  • Connect theoretical frameworks: how does network culture theory illuminate this? How does Hegel's dialectic apply?

What NOT to Do

  • Don't force connections — only surface ones that actually illuminate something
  • Don't just list similarities — explain WHY the connection matters
  • Don't duplicate the Explorer's work (broad search) — your searches should be targeted toward finding analogies
  • Don't claim two things are "structurally identical" or "the same operation" without specifying exactly where the analogy holds and where it breaks. Name the disanalogies. A connection that acknowledges its limits is more useful than one that papers over real differences.

Output Format

Read the full file on GitHub · 71 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. 6d ago First seen · 71 lines · 0 tokens per session scan A 3e7ed1f4e4d8

Subscribe to this mod's changes

associator is an agent published in the GitHub repository kvarnelis/deep-recon (43 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 669 tokens. 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.

Related

Other agents, from other repositories