Best use case
open-games is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Open Games Skill (ERGODIC 0)
Teams using open-games should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/open-games/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How open-games Compares
| Feature / Agent | open-games | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Open Games Skill (ERGODIC 0)
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Open Games Skill (ERGODIC 0)
> Compositional game theory via Para/Optic structure
**Trit**: 0 (ERGODIC)
**Color**: #26D826 (Green)
**Role**: Coordinator/Transporter
## Core Concept
Open games are morphisms in a symmetric monoidal category:
```
┌───────────┐
X ──→│ │──→ Y
│ Game G │
R ←──│ │←── S
└───────────┘
```
Where:
- **X → Y**: Forward play (strategies)
- **S → R**: Backward coplay (utilities)
## The Para/Optic Structure
### Para Morphism
```haskell
Para p a b = ∃m. (m, p m a → b)
-- Existential parameter with action
```
### Optic (Lens Generalization)
```haskell
Optic p s t a b = ∀f. p a (f a b) → p s (f s t)
-- Profunctor optic for bidirectional data
```
### Open Game as Optic
```haskell
OpenGame s t a b =
{ play : s → a
, coplay : s → b → t
, equilibrium : s → Prop
}
```
## Composition
### Sequential (;)
```
G ; H = Game where
play = H.play ∘ G.play
coplay = G.coplay ∘ (id × H.coplay)
```
### Parallel (⊗)
```
G ⊗ H = Game where
play = G.play × H.play
coplay = G.coplay × H.coplay
```
## Nash Equilibrium via Fixed Points
```haskell
isEquilibrium :: OpenGame s t a b → s → Bool
isEquilibrium g s =
let a = play g s
bestResponse = argmax (\a' → utility (coplay g s (respond a')))
in a == bestResponse
```
### Compositional Equilibrium
```
eq(G ; H) = eq(G) ∧ eq(H) -- under compatibility
```
## Integration with Unworld
```clojure
(defn opengame-derive
"Transport game through derivation chain"
[game derivation]
(let [; Forward: strategies through derivation
forward (compose (:play game) (:forward derivation))
; Backward: utilities through co-derivation
backward (compose (:coplay game) (:backward derivation))]
{:play forward
:coplay backward
:equilibrium (transported-equilibrium game derivation)}))
```
## GF(3) Triads
```
temporal-coalgebra (-1) ⊗ open-games (0) ⊗ free-monad-gen (+1) = 0 ✓
three-match (-1) ⊗ open-games (0) ⊗ operad-compose (+1) = 0 ✓
sheaf-cohomology (-1) ⊗ open-games (0) ⊗ topos-generate (+1) = 0 ✓
```
## Commands
```bash
# Compose games sequentially
just opengame-seq G H
# Compose games in parallel
just opengame-par G H
# Check Nash equilibrium
just opengame-nash game strategy
# Transport through derivation
just opengame-derive game deriv
```
## Economic Examples
### Prisoner's Dilemma
```haskell
prisonersDilemma :: OpenGame () () (Bool, Bool) (Int, Int)
prisonersDilemma = Game {
play = \() → (Defect, Defect), -- Nash
coplay = \() (p1, p2) → payoffMatrix p1 p2
}
```
### Market Game
```haskell
market :: OpenGame Price Price Quantity Quantity
market = supplyGame ⊗ demandGame
where equilibrium = supplyGame.eq ∧ demandGame.eq
```
## Categorical Semantics
```
OpenGame ≃ Para(Lens) ≃ Optic(→, ×)
Composition:
(A ⊸ B) ⊗ (B ⊸ C) → (A ⊸ C) -- via cut
Tensor:
(A ⊸ B) ⊗ (C ⊸ D) → (A ⊗ C ⊸ B ⊗ D)
```
## References
- Ghani, Hedges, et al. "Compositional Game Theory"
- Capucci & Gavranović, "Actegories for Open Games"
- Riley, "Categories of Optics"
- CyberCat Institute tutorialsRelated Skills
testing-for-open-redirect-vulnerabilities
Identify and test open redirect vulnerabilities in web applications by analyzing URL redirection parameters, bypass techniques, and exploitation chains for phishing and token theft.
performing-open-source-intelligence-gathering
Open Source Intelligence (OSINT) gathering is the first active phase of a red team engagement, where operators collect publicly available information about the target organization to identify attack s
performing-authenticated-scan-with-openvas
Configure and execute authenticated vulnerability scans using OpenVAS/Greenbone Vulnerability Management with SSH and SMB credentials for comprehensive host-level assessment.
openscad-bci-hardware
Parametric OpenSCAD models for BCI electrode holders, paste adapters, headset hooks, pogo combs, fNIRS housings, and eurorack frames. Use when designing, modifying, or 3D-printing brain-computer interface hardware.
opennirscap-build
Build an OpenNIRScap 24-channel fNIRS brain cap from open-source hardware — Altium conversion, BOM sourcing, PCB fab, assembly, firmware flash
implementing-taxii-server-with-opentaxii
Deploy and configure an OpenTAXII server to share and consume STIX-formatted cyber threat intelligence using the TAXII 2.1 protocol for automated indicator exchange between organizations.
implementing-policy-as-code-with-open-policy-agent
This skill covers implementing Open Policy Agent (OPA) and Gatekeeper for policy-as-code enforcement in Kubernetes and CI/CD pipelines. It addresses writing Rego policies, deploying OPA Gatekeeper as a Kubernetes admission controller, testing policies in development, and integrating policy evaluation into deployment pipelines.
cybernetic-open-game
Cybernetic Open Game Skill
configuring-certificate-authority-with-openssl
A Certificate Authority (CA) is the trust anchor in a PKI hierarchy, responsible for issuing, signing, and revoking digital certificates. This skill covers building a two-tier CA hierarchy (Root CA +
collecting-open-source-intelligence
Collects and synthesizes open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack campaigns using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Use when investigating external threat actor infrastructure, performing pre-engagement reconnaissance for authorized red team assessments, or enriching CTI reports with publicly available adversary context. Activates for requests involving Maltego, Shodan, OSINT framework, SpiderFoot, or infrastructure reconnaissance.
building-ioc-enrichment-pipeline-with-opencti
OpenCTI is an open-source platform for managing cyber threat intelligence knowledge, built on STIX 2.1 as its native data model. This skill covers building an automated IOC enrichment pipeline using O
jaxlife-open-ended
JaxLife open-ended agentic simulator for emergent behavior, tool use, and cultural accumulation. Use for artificial life simulations, emergent agent behavior, and open-ended evolution research.