polyvers

A tool for checking whether a new version of a state machine can work with state already used by a live system. It can also create a migration when the stored state shape changes.

In plain words
What is it for?
Use it to classify state-machine changes, run checks against fleet snapshots, and produce migrations for changed state shapes.
Why use it?
It helps find compatibility problems before deploying code that must read or update existing state.

Skill for Claude CodeCodex

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 skills/cognitive-fab/polygraph/polyvers
Any agent
npx skills add cognitive-fab/polygraph --skill polyvers
Clone the repo
git clone --depth 1 https://github.com/cognitive-fab/polygraph

Made for: Claude Code, Codex.

Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00184 $0.01789
Opus 5 $0.00092 $0.00894
Sonnet 5 $0.00037 $0.00358
Haiku 4.5 $0.00018 $0.00179

Measured 2d ago against content hash a62fad402826, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

polyvers 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 2d 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.

skills/polyvers/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

polyvers — version a state machine with mechanical gates

The fourth engine: Polygraph audits, polygen authors, polyrun executes, polyvers EVOLVES. The premise (from ${CLAUDE_PLUGIN_ROOT}/docs/VERSIONING.md): state outlives code, so every deploy is a compatibility event against the live fleet — and "compatible" is not one question but several, each with its own mechanical check. Everything here is deterministic, local, and needs no API key.

The CLI is ${CLAUDE_PLUGIN_ROOT}/polyvers/bin/polyvers.mjs; an artifact dir holds contract.json + the SAM v2 module + optional invariants.mjs, effects.manifest.json, effects.cjs, migrate.cjs — what polygen emits.

Disclosure (same as the whole plugin). This is experimental, unproven technology, and these gates are consistency checks, not proofs. They are exactly as good as the invariants the artifacts state — semantic drift the invariants do not mention is invisible to every gate — and every "exhaustive" gate is exhaustive over the declared finite (action, data) domains, not over unbounded real data. Versioning maturity is invariant-writing maturity.

Step 1 — Classify before running anything

node ${CLAUDE_PLUGIN_ROOT}/polyvers/bin/polyvers.mjs classify --old <dir> --new <dir>

The lanes and what fires them: shape (contract stateKeys), vocabulary (actions, reject reasons, effect kinds, terminal states), intent (invariants — state or transition), semantic (the module changed), migration (migrate.cjs added/edited), composition (effects.cjs changed — gated by polyrun check-effects for emissions plus polyvers matrix/polyvers product for the cross-machine surface; the report says so as NOT RUN rows). "No lane fired" on differing artifacts means a cosmetic edit; say so rather than inventing risk.

Step 2 — Choose the snapshot corpus honestly

The gates run against fleet states, and provenance is part of the verdict:

  1. fleet exports (--snapshots <dir|file>; polyrun archive output, bare ndjson, or a .json array) — the honest tier. "Live" means a FRESH polyrun archive/export of the fleet fed to this flag; polyvers never connects to a database.
  2. --synthesize — BFS-reachable states of the OLD machine: the weakest tier, because it contains only states the old MODEL says are reachable, which is exactly the assumption a landmine violates.

Read the full file on GitHub · 137 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. 2d ago First seen · 137 lines · 0 tokens per session scan A a62fad402826

Subscribe to this mod's changes

polyvers is a skill published in the GitHub repository cognitive-fab/polygraph (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 184 tokens to every session and 1,789 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

electron-node-upgrade

Guide for performing Node.js version upgrades in the Electron project. Use when working on the roller/node/main branch to fix patch conflicts during e sync --3. Covers the patch application workflow, conflict resolution, analyzing upstream Node.js changes, building, running the Node.js test suite, and proper commit…

electron/electron · 69 tokens

lint-js

Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).

denoland/deno · 29 tokens

Shade dropdown surface contract

DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.

TryGhost/Ghost · 54 tokens

Shade ShadCN install

Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.

TryGhost/Ghost · 72 tokens

Shade use primitives

Replace bare divs that only carry flex/grid/gap utilities with Shade primitives (Stack, Inline, Box, Grid, Container, Text). Use semantic gap="md" instead of gap-4. Trigger when editing TSX in Shade-consuming apps.

TryGhost/Ghost · 54 tokens

geometry-and-math

Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.

phaserjs/phaser · 64 tokens