Ttypesafe-aiOfficial

TypeSafe agent skills

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

Explore repositoryVisit website

Agent skills for building with TypeSafe's System One API

How it uses Jev

Agent skills for building with TypeSafe: typed decisions and probabilities from System One models.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to TypeSafe agent skills

Browse all
jev-agent-hooks project preview

jev-agent-hooks

Agent tooling
TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing
OMade byonlyjq042
hermes-jev-skills project preview

hermes-jev-skills

Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
KMade bykerpopule726
jev-browser-skill project preview

jev-browser-skill

Browser & computer use
Let Jev, TypeSafe's ~100ms decision model, drive your browser. A plug-and-play skill for Claude Code and Codex.
ZMade byzurfyx2
TypeSafe MCP project preview

TypeSafe MCP

Agent tooling
Bring typed Jev judgments to your coding assistant through a single MCP server.
IMade byitsmostafa292
LegalForecastBench project preview

LegalForecastBench

Benchmarks & research
LegalForecast-MTD benchmark alpha and official evaluation workflows
JMade byjohnhughes35
jev-skills project preview

jev-skills

Agent tooling
Skills without the context tax. Claude Code and Codex plugin: TypeSafe's Jev decides on every turn which skills the model sees. Always-on context cost: 0 tokens.
EMade byeran-broder2
jev-starter project preview

jev-starter

Benchmarks & research
Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
HMade byhamakyo2
jev-x-kit project preview

jev-x-kit

Benchmarks & research
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.
KMade byKadihx2

Game Plan

Games & simulations
Small game that tests how Jev handles unknown input.
CMade byCommunity contributor