epistemic-arbitrage

epistemic-arbitrage is a skill for Claude Code from plurigrid/asi. It costs 33 tokens per session (1,815 once invoked), scanned A, original, MIT.

A framework for transferring useful ideas between different fields using connected containers of partial information and deterministic random choices.

In plain words
What is it for?
Use it to model knowledge transfer, build propagating information networks, and explore cross-domain synthesis.
Why use it?
It provides a structured way to combine knowledge from separate domains while keeping parallel results repeatable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the topos-skills plugin — 29 skills shipped together

Good fit Use it to model knowledge transfer, build propagating information networks, and explore cross-domain synthesis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plurigrid/asi/epistemic-arbitrage
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.

Any agent
npx skills add plurigrid/asi --skill epistemic-arbitrage
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code.

Or install topos-skills, the plugin that ships this one along with the rest of its 29 skills.

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 epistemic-arbitrage

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/epistemic-arbitrage/github.svg)](https://agentmods.dev/skills/plurigrid/asi/epistemic-arbitrage)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/epistemic-arbitrage"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/epistemic-arbitrage/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.

agentmods 80×15 button for epistemic-arbitrage

Your own site · 80×15
<a href="https://agentmods.dev/skills/plurigrid/asi/epistemic-arbitrage"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/epistemic-arbitrage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,815 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.01815
Opus 5 $0.00016 $0.00907
Sonnet 5 $0.00007 $0.00363
Haiku 4.5 $0.00003 $0.00181

Measured 9d ago against content hash fa16bf24b9f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

epistemic-arbitrage 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.

ies/music-topos/.claude-marketplaces/topos-skills/plugins/topos-skills/skills/epistemic-arbitrage/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epistemic Arbitrage: Propagator-Based Knowledge Synthesis

Epistemic arbitrage exploits knowledge differentials between domains. When concept A in domain X is well-understood, but its isomorphic counterpart A' in domain Y is mysterious, we can arbitrage by transferring understanding.

Core Architecture

Propagator Networks (Radul/Sussman)

A propagator network consists of:

┌─────────┐     ┌─────────────┐     ┌─────────┐
│  Cell A │────▶│ Propagator  │────▶│  Cell B │
│ (known) │     │  (transfer) │     │(derived)│
└─────────┘     └─────────────┘     └─────────┘
  • Cells: Containers for partial information
  • Propagators: Functions that combine/transform information
  • Merging: Monotonic accumulation (information only increases)

SplitMixTernary RNG

For parallel propagation with determinism:

class SplitMixTernary
  GOLDEN = 0x9e3779b97f4a7c15  # Golden ratio constant
  
  def initialize(seed)
    @state = seed
  end
  
  def next_ternary
    # Advance state (SplitMix64)
    @state = (@state + GOLDEN) & 0xFFFFFFFFFFFFFFFF
    z = @state
    z = ((z ^ (z >> 30)) * 0xbf58476d1ce4e5b9) & 0xFFFFFFFFFFFFFFFF
    z = ((z ^ (z >> 27)) * 0x94d049bb133111eb) & 0xFFFFFFFFFFFFFFFF
    z = z ^ (z >> 31)
    
    # Map to ternary: -1, 0, +1
    (z % 3) - 1
  end
  
  def split(index)
    # Create independent child stream
    child_seed = @state ^ (index * GOLDEN)
    SplitMixTernary.new(child_seed)
  end
end

Arbitrage Patterns

Pattern 1: Domain Transfer

# Knowledge in domain A
cell_a = Cell.new(:music, :circle_of_fifths)
cell_a.add_info(:structure, :cyclic_group_12)
cell_a.add_info(:generator, :perfect_fifth)

# Unknown in domain B
cell_b = Cell.new(:number_theory, :modular_arithmetic)

# Propagator transfers structure
propagator = Propagator.new(:domain_transfer) do |source, target|
  if source.has?(:structure)
    target.merge(:structure, source.get(:structure))
    target.merge(:insight, "Z/12Z isomorphic to circle of fifths")
  end
end

propagator.connect(cell_a, cell_b)
propagator.fire!

Read the full file on GitHub · 249 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. 9d ago First seen · 249 lines · 33 tokens per session scan A fa16bf24b9f8

Subscribe to this mod's changes

epistemic-arbitrage is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,815 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens