User repository on GitHub
JEV（TypeSafe）判斷模型等級與分類／打分／是非判斷的 Claude Code 外掛
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Jev for Claude Code — ricky94511
A Claude Code plugin that asks Jev, TypeSafe's System One model, which model tier each prompt needs — haiku, sonnet or opus — and switches automatically, and routes classification, scoring and yes/no judgments to Jev via scripts/jev.py.
- Stars
- 0
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- ricky94511
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev for Claude Code — pachelbel23.
- Languages
- TypeScriptPython
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- Uses Jev for two jobs: choosing the Claude model tier per prompt, and classification, scoring and yes/no judgments via scripts/jev.py.
- Tier switches: haiku picks claude-haiku-5-5 at confidence 0.7+ within 300k tokens; sonnet only on a new conversation's first prompt; opus upgrades always.
- Toggle per project via a switch above the input box or /jev on|off|status; state lives in ~/.claude/jev/.
- Each answer appends a notification line, because the app's cloud conversation cannot show plugin toasts.
- Requires Claude Code 2.1.29x+ for function hooks and python3; ask --image additionally needs ffmpeg.
Watch out
README reviewed 2026-10-17; the captured text is largely intact but the install JSON example is truncated and no licence is listed in the digest metadata. The tier table and switch rules are the project's own design, and no benchmarks appear in the capture.
Questions about this entry
Short answers drawn from the linked project or page.
It asks Jev, TypeSafe's System One model, which model tier each prompt needs — haiku, sonnet or opus — and switches automatically, and routes classification, scoring and yes/no judgments through scripts/jev.py.
Per the README table: a haiku suggestion switches to claude-haiku-5-5 when confidence is at least 0.7 and the conversation is under 300k tokens; sonnet only switches on a new conversation's first prompt; opus upgrades are unconditional.
There is a switch above the input box or the command /jev on|off|status; the setting is per project and stored under ~/.claude/jev/.
Claude Code 2.1.29x or later for function hooks plus python3, and a TYPESAFE_API_KEY; the ask --image script additionally needs ffmpeg.
claude-haiku-5-5, claude-sonnet-5-5 and claude-opus-5-5, with the version written in MODEL_ID in hooks/register.tsx; subagents and conversations on other models are left untouched.
Yes, per-project files are optional: .claude/jev_rules.md lists which steps go to Jev and is attached to every prompt, and .claude/jev_tiers.json overrides the three tier descriptions so Jev classifies more accurately.
The digest shows a TypeScript repository with 0 stars, created and pushed 2026-10-16, and no licence listed; the install section is truncated in the captured text.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
A Claude Code mod that asks Jev one Noul question per skill for every prompt, ranks the skills above the threshold and passes them to the model as a suggestion. It never loads a skill itself, and a timeout, outage or missing key only skips the routing.
Jev Integrations & Adapters#community#github#claude-code
Community
gecm0/skill-router-modTypeScript
gecm0/skill-router-modTypeScriptA Claude Code plugin that picks Haiku, Sonnet or Opus and a reasoning effort for every prompt, step and subagent, with an effort cap, a prompt-cache guard and a status band; the repo is named jev-router and tagged typesafe.
Jev Integrations & Adapters#community#github#typescript
Community
dominicrico/jev-routerTypeScript
dominicrico/jev-routerTypeScriptA Claude Code mod that sends each prompt to Jev through OpenRouter and turns the returned 0-3 score into a reasoning effort level, from low to xhigh. Shadow mode is on by default, so it only logs what it would set until you turn it off.
Jev Integrations & Adapters#community#github#claude-code
Community
gebeer/jev-effortTypeScript
gebeer/jev-effortTypeScriptA session-aware, OpenAI-compatible gateway that routes chat completions across provider pools by cost, quality, and capability rules, optionally asks configured decision providers typed choice questions with a deterministic fallback, and records requests, decisions, and outcomes in SQLite.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
texasoct/jev-gatewayTypeScript
texasoct/jev-gatewayTypeScriptThe Vercel AI SDK provider for OpenRouter, including openrouter.decisionModel for typesafe/jev-1.13 evaluations with providerMetadata answers.
Jev Integrations & Adapters#community#typescript#openrouter
CLI-installed Gmail classifier that runs 24/7 on user-owned Google Apps Script: the worker asks Jev for three typed judgments per thread (requires_action, is_important, bucket), applies labels, stars, and optional archiving, and routes ambiguous or low-confidence mail to a Review label.
Jev Integrations & Adapters#community#gmail#email
Community
vynnlee/jev-mailTypeScript
vynnlee/jev-mailTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.