Probabilistic pull-request risk triage using Jev and deterministic review policy.
Coding agents and review — page 6
Coding assistants and review tools that use Jev to choose the next step or judge a change before it lands.
292 active projects in this collection. All collections →
No project description available.
Agent Skill that finds where TypeSafe Jev decision models would pay off in a codebase. Works in Claude Code, Codex, Cursor and other Agent Skills hosts.
1
Turn plain-English engineering rules into pull-request checks
One-command setup that makes Claude Code use fewer tokens: rtk shell compression, stash search index, web-search, codebase-memory, fast-jev-compaction, ponytail, plus Jev skill suggestions and model routing.
1
Jev-routed multi-model orchestration for Claude Code: cheap work to cheap models, hard work to strong ones, verified.
Claude Code plugin that routes skill selection and post-turn code judgment through TypeSafe Jev on OpenRouter
Token-efficient agent memory for Claude Code and Codex, using TypeSafe Jev for typed decisions and a primary LLM for validation.
用 TypeSafe Jev 给 AI coding agent 做持续代码质量 review 的校准审计层。持久化 19 维质量分数，输出趋势矩阵、假阳性置信检测、rubric 漂移与 ECE 校准曲线。Node 22+，零运行时依赖，CLI + GitHub Action，直接消费 jev_review 的 MCP 评估结果。
Claude Code & Codex skills powered by Jev, TypeSafe's System One model. 256 calibrated judgements for $0.0005 in 0.72s — 360x cheaper than Claude Opus 5. Includes the first published Jev calibration curve, measured on 4,995 real agent decisions.
Real-time reflex layer for Claude Code guarded by TypeSafe's Jev System One model: calibrated probabilities in, deterministic allow/warn/block decisions out.
Cursor plugin that routes subagents with TypeSafe Jev and exposes Choice, Score, and Noul as MCP tools.
1
Open lab: Jev (TypeSafe System One) routing in front of Claude Code - measured bugs, patch, and a hard fallback with alerts
Code review filter for AI Agents using TypeSafe Jev model
The doorman for Claude’s context window. JEV-powered model routing and recoverable context filtering for Claude Code.
A Jev (TypeSafe System One) permission gate for the Pi coding agent: judges every bash / write / edit call before it runs
Skill Dash uses Jev to judge Claude Code and Codex skills and plugins: usefulness, redundancy, clarity, duplicates, safety. Local dashboard plus the corpus pipeline behind whichskills.dev. MIT.
Portable agent skill: TypeSafe Jev as a cheap code-review classifier (HTTP + optional jev-review MCP)
Diagnostic plugins for Claude Code and Codex: why a session went wrong, and whether a proposed change is too much or too little for the outcome.
Claude Code mod: Jev-scored context pruning through OpenRouter. Verbatim compaction, an optional gate on oversized tool outputs, tests and evals.
Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API.
A local proxy that sits between Claude Code and the Anthropic API and uses TypeSafe's Jev to route each subagent to the model the task actually needs. Your main conversation keeps whatever model you picked
Real-time quality gate and Art Director Warden for Claude Code powered by TypeSafe Jev 1.13 non-autoregressive decision model
Claude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection in tool results.