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.
npx skills add plurigrid/asi --skill open-gamesgit clone --depth 1 https://github.com/plurigrid/asiWrote 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.
[](https://agentmods.dev/skills/plurigrid/asi/open-games)<a href="https://agentmods.dev/skills/plurigrid/asi/open-games"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/open-games/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.
<a href="https://agentmods.dev/skills/plurigrid/asi/open-games"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/open-games.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.01074 |
| Opus 5 | $0.00006 | $0.00537 |
| Sonnet 5 | $0.00003 | $0.00215 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
open-games 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
Para p a b = ∃m. (m, p m a → b)
-- Existential parameter with action
Optic (Lens Generalization)
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
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
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
(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 ✓
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.
- 6d ago First seen · 161 lines · 13 tokens per session scan A f4b56dc4e3b1
open-games is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,074 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…