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 bisimulation-gamegit 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/bisimulation-game)<a href="https://agentmods.dev/skills/plurigrid/asi/bisimulation-game"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/bisimulation-game.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01785 |
| Opus 5 | $0.00014 | $0.00892 |
| Sonnet 5 | $0.00006 | $0.00357 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
bisimulation-game 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 5d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bisimulation Game Skill
"Two systems are bisimilar if they cannot be distinguished by any observation."
Overview
The bisimulation game provides a framework for:
- Resilient skill dispersal across multiple AI agents
- GF(3) conservation during state transitions
- Observational bridge types for version-aware synchronization
- Self-rewriting capabilities via MCP Tasks protocol
Game Rules
Players
| Player | Role | Trit | Color |
|---|---|---|---|
| Attacker | Tries to distinguish systems | -1 | Blue |
| Defender | Maintains equivalence | +1 | Red |
| Arbiter | Verifies conservation | 0 | Green |
Moves
┌─────────────────────────────────────────────────────────────┐
│ Round n: │
│ │
│ 1. Attacker chooses: system S₁ or S₂ │
│ 2. Attacker makes: transition s₁ →ᵃ s₁' │
│ 3. Defender responds: matching transition s₂ →ᵃ s₂' │
│ 4. Arbiter verifies: GF(3) conservation │
│ │
│ If Defender cannot respond → Attacker wins (distinguishable)│
│ If game continues forever → Defender wins (bisimilar) │
└─────────────────────────────────────────────────────────────┘
Implementation
Hy (DiscoHy) Implementation
;;; bisimulation_game.hy
(import [splitmix_ternary [SplitMixTernary]])
(defclass BisimulationGame []
(defn __init__ [self system1 system2 seed]
(setv self.s1 system1
self.s2 system2
self.rng (SplitMixTernary seed)
self.history []))
(defn attacker-move [self choice transition]
"Attacker chooses system and transition."
(setv trit (self.rng.next-ternary))
(.append self.history {:role "attacker"
:choice choice
:transition transition
:trit trit})
trit)
(defn defender-respond [self matching-transition]
"Defender provides matching transition."
(setv trit (self.rng.next-ternary))
(.append self.history {:role "defender"
:response matching-transition
:trit trit})
trit)
(defn arbiter-verify [self]
"Arbiter checks GF(3) conservation."
(setv recent-trits (lfor m (cut self.history -3 None) (get m "trit")))
(setv conserved (= (% (sum recent-trits) 3) 0))
(.append self.history {:role "arbiter" :conserved conserved :trit 0})
conserved))
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.
- 5d ago First seen · 254 lines · 28 tokens per session scan A deac1b2bd30c
bisimulation-game is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,785 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 2026-09-01.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.