# jev-use

> jev-use — shitianfang-jev-use. Use this tool when you need to offload agent steps that don't require text output, leveraging Jev's judgment model to make efficient decisions at a low cost of ~$0.00004 per judgment. It solves problems by streamlining agent workflows and reducing unnecessary text output, accepting input steps and returning judgments as output. Ideal for use cases where rapid, cost-effective decision-making is crucial, such as in automated workflows or large-scale data processing.

Canonical page: https://skillsregistry.net/skills/shitianfang-jev-use  
JSON: https://api.skillsregistry.net/v1/skills/shitianfang-jev-use

## Description

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

## Trust

- **Trust score (0–1):** 0.85
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/shitianfang/jev-use)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shitianfang-jev-use"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shitianfang-jev-use` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shitianfang-jev-use/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt