104-analogy-transfer

104-analogy-transfer is a cursor rule for coding agents from hamzaamjad/cursor-rules. It costs 2,316 tokens per session, scanned C, original, MIT.

A problem-solving rule that uses similarities between different fields to generate and test solutions. For example, it can compare how an immune system responds to threats with how a distributed computer system handles failures.

In plain words
What is it for?
It helps identify related source fields, map how their parts interact, state what does not transfer, and test the comparison against unusual cases.
Why use it?
It provides a structured way to find useful ideas from familiar subjects while checking which parts of the comparison are actually valid.

Cursor rule

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 rules/hamzaamjad/cursor-rules/104-analogy-transfer
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules

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 104-analogy-transfer

README.md
[![agentmods](https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/104-analogy-transfer.svg)](https://agentmods.dev/rules/hamzaamjad/cursor-rules/104-analogy-transfer)
Your own site
<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/104-analogy-transfer"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/104-analogy-transfer.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,316 This file is loaded in full into every session.
When invoked 2,316 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02316 $0.02316
Opus 5 $0.01158 $0.01158
Sonnet 5 $0.00463 $0.00463
Haiku 4.5 $0.00232 $0.00232

Measured 4d ago against content hash da3869c67e0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

104-analogy-transfer scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

* Maintain "analogy debt" log for mappings that may break <!-- TODO: Create monitoring system -->
rules/100-cognitive/104-analogy-transfer.mdc · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

analogy-transfer.mdc

  • Purpose: To enable systematic cross-domain problem-solving by mapping relational structures from familiar source domains to novel target problems. This rule operationalizes analogical reasoning as a formal problem-solving tool, emphasizing structural over surface similarity. Empirical Impact: Meta-analysis shows effect size d=0.50 for improved problem-solving outcomes. Stigmergic patterns (indirect environmental signaling) show 22% latency reduction and 34% faster convergence on optimal solutions.

  • Requirements:

    • Source Domain Selection:
      • Identify 2-3 potential source domains with structural similarity
      • Prioritize domains with well-understood causal relationships
      • Include at least one "distant" domain for creative insights
    • Structural Mapping Process:
      • Explicitly map relationships, not attributes
      • Identify: entities, relationships, higher-order relations
      • Use template: "In [source], [A relates to B]. In [target], [X relates to Y similarly]"
    • Mapping Validation:
      • Verify causal relationships preserve across domains
      • Explicitly state what does NOT transfer
      • Test mapping with edge cases
    • Analogy Repository:
      • Nature patterns (ant colonies, river networks, immune systems)
      • Engineering systems (highways, power grids, supply chains)
      • Organizational structures (military, orchestras, sports teams)
      • Abstract systems (music theory, game mechanics, economic markets)
      • Stigmergic Systems (environmental coordination patterns):
        • Ant pheromone trails → Cache warming patterns
        • Termite mound building → Distributed consensus algorithms
        • Wikipedia editing → Collaborative documentation
        • Key Insight: Indirect coordination through environment modification
    • Integration Requirements:
      • Present mapping during DIVERGENCE phase of divergence-convergence
      • Include confidence score for structural fit (low/medium/high)
      • Provide fallback if primary analogy fails
  • Validation:

    • Check: Are relationships (not attributes) explicitly mapped?
    • Check: Is causal structure preserved across domains?
    • Check: Are limitations/non-transfers clearly stated?
    • Check: Does the analogy enable specific problem-solving insights?
    • Check: Is structural similarity score provided?
  • Examples:

    • Scenario: Design distributed system resilience

      • Source Selection: "Evaluating source domains: 1) Immune system (high fit), 2) Forest fire management (medium fit), 3) Jazz improvisation (creative fit)"
      • Structural Mapping:
        IMMUNE SYSTEM → DISTRIBUTED SYSTEM
        - Antibodies → Error handlers (recognize specific threats)
        - T-cells → Circuit breakers (kill compromised components)
        - Memory cells → Incident patterns database
        - Inflammation → Rate limiting (temporary protection)
        - Fever → System-wide defensive mode
        
        CAUSAL PRESERVATION:
        - Pathogen exposure → Memory cell creation
        - System intrusion → Pattern recording
        
        DOES NOT TRANSFER:
        - Physical proximity effects
        - Biological evolution timescales
        
      • Applied Solution: "Implement 'immune memory' - system learns from failures and pre-positions defenses"
    • Scenario: Optimize team communication

      • Source Selection: "1) Neural networks (high fit), 2) Highway systems (medium fit), 3) Beehive waggle dance (creative fit)"
      • Structural Mapping:
        NEURAL NETWORK → TEAM COMMUNICATION
        - Neurons → Team members
        - Synapses → Communication channels  
        - Action potential → Message priority threshold
        - Neurotransmitters → Message types/protocols
        - Plasticity → Channel optimization over time
        
      • Applied Solution: "Implement 'synaptic strengthening' - frequently used communication paths get dedicated channels/tools"

Read the full file on GitHub · 202 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 · 202 lines · 2,316 tokens per session scan C da3869c67e0a

Subscribe to this mod's changes

104-analogy-transfer is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 2,316 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.