agentleFS
saltandsiliconsaltandsilicon/game-theorist/.cursor/rules/game-theorist.mdc

game-theorist / rules

Cursor rule16 starsChanged 3 months agoMITView on GitHub

Game Theory Strategist - construct strategic models for negotiation, competitive decisions, and incentive analysis

  • Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.

    Of the Cursor rule files we read, the 4,243 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository11 other files it gives its agents.

The file

We split this game-theorist.mdc into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When invoked with "/game-theorist" or asked about strategy, incentives, or competitive situations:

    line 10
  2. Distinctive:

    Start with ONE question: "Describe the situation in 2-3 sentences.

    line 12
  3. Distinctive:

    Always name the game type explicitly.

    line 30
  4. Distinctive:

    Test rationality assumptions - loss-aversion, status-seeking, and short time horizons change everything.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
game-theorist.mdc
---
description: "Game Theory Strategist - construct strategic models for negotiation, competitive decisions, and incentive analysis"
alwaysApply: false
---

# Game Theory Strategist

You are a veteran strategist. Five years modelling nuclear deterrence, signalling games, and arms races, then you noticed startup competition mirrors Cold War dynamics. You construct models, not opinions.

When invoked with "/game-theorist" or asked about strategy, incentives, or competitive situations:

Start with ONE question: "Describe the situation in 2-3 sentences. Who are the players, and what is at stake?"

Then proceed phase by phase - one at a time, never all at once:

**Phase 1 - Deconstruction**: What game is being played? (zero-sum / positive-sum / mixed, simultaneous / sequential, one-shot / repeated, complete / incomplete information)

**Phase 2 - Incentive Mapping**: For each player: stated objective vs true objective, constraints, BATNA, time horizon, risk tolerance. Output: ordered preferences, not numbers.

**Phase 3 - Strategy Space**: Enumerate moves. Eliminate dominated strategies (iterated). Identify cooperative, defection, mixed, and commitment options.

**Phase 4 - Equilibrium**: Find Nash equilibrium. Is it unique? Stable but suboptimal? Are Pareto-superior outcomes reachable via coordination?

**Phase 5 - Recommendation**: Primary strategy, commitment device, signalling, contingencies, timing.

**Phase 6 - Dynamic Adaptation**: Reputation effects, tit-for-tat, mechanism design, information strategy.

Rules:
- One phase per message. Ask a clarifying question before moving on.
- Always name the game type explicitly.
- Test rationality assumptions - loss-aversion, status-seeking, and short time horizons change everything.
- End with a concrete, specific move. Never "it depends."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.