cross-domain-thinking

cross-domain-thinking is a skill for Claude Code from legacybridge-tech/claude-plugins. It costs 34 tokens per session (2,017 once invoked), scanned A, original, MIT.

A method for finding useful similarities between different areas of knowledge, such as software, biology, economics, or everyday life. It provides structured ways to compare their underlying patterns.

In plain words
What is it for?
Use it to explore analogies, relate concepts across disciplines, identify repeating structures, and suggest applications of an idea in a new field.
Why use it?
It helps turn ideas from one field into insights or possible solutions in another when the connection is not obvious.

Skill for Claude Code

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

Part of the akashicrecords plugin — 7 skills, 2 commands, 1 agent shipped together

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 skills/legacybridge-tech/claude-plugins/cross-domain-thinking
Any agent
npx skills add legacybridge-tech/claude-plugins --skill cross-domain-thinking
Clone the repo
git clone --depth 1 https://github.com/legacybridge-tech/claude-plugins

Made for: Claude Code.

Or install akashicrecords, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 1 agent.

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 cross-domain-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/legacybridge-tech/claude-plugins/cross-domain-thinking.svg)](https://agentmods.dev/skills/legacybridge-tech/claude-plugins/cross-domain-thinking)
Your own site
<a href="https://agentmods.dev/skills/legacybridge-tech/claude-plugins/cross-domain-thinking"><img src="https://agentmods.dev/badge/skills/legacybridge-tech/claude-plugins/cross-domain-thinking.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,017 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 $0.00034 $0.02017
Opus 5 $0.00017 $0.01009
Sonnet 5 $0.00007 $0.00403
Haiku 4.5 $0.00003 $0.00202

Measured 6d ago against content hash 28aefe5e604c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cross-domain-thinking 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.

akashicrecords/skills/cross-domain-thinking/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Domain Thinking

A methodological toolkit for discovering and articulating connections across disciplines.

When to Invoke This Skill

  • User explores a concept that has structural parallels elsewhere
  • User asks "how does X relate to Y" across different fields
  • User seeks novel applications of an idea
  • Discussion would benefit from unexpected analogies
  • User explicitly requests cross-domain analysis
  • Keywords: "connections between", "analogy", "isomorphic", "parallel", "transfer"

Four Modes of Connection

1. Isomorphic Patterns

Identify structural similarities that transcend domain boundaries.

Process:

  • Abstract the core structure from Domain A (strip domain-specific details)
  • Identify the same structure appearing in Domain B
  • Articulate what the isomorphism reveals about both domains

Examples:

  • Feedback loops: thermostats, market equilibrium, homeostasis, habit formation
  • Network effects: epidemics, viral content, neural activation, social movements
  • Emergence: ant colonies, market prices, consciousness, language evolution

Output format:

"The structure here is [abstract pattern]. This same structure appears in [Domain B] as [concrete manifestation]. What this reveals: [insight about the deeper principle]."

2. Conceptual Bridges

Use a principle from one field to illuminate another.

Process:

  • Identify a well-developed concept in Domain A
  • Find a less-understood phenomenon in Domain B
  • Apply A's conceptual framework to generate new understanding of B

Examples:

  • Entropy (physics) -> Information theory -> Organizational decay
  • Natural selection (biology) -> Memetics -> Algorithm design
  • Margin of safety (engineering) -> Portfolio theory -> Decision-making under uncertainty

Output format:

"In [Domain A], [concept] works by [mechanism]. Applying this lens to [Domain B]: [new interpretation]. This suggests [actionable insight or prediction]."

3. Novel Applications

Transfer solutions or techniques across contexts.

Read the full file on GitHub · 242 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 · 242 lines · 34 tokens per session scan A 28aefe5e604c

Subscribe to this mod's changes

cross-domain-thinking is a skill published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,017 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 skills, from other repositories