User repository on GitHub
Jeffort: scores each prompt with TypeSafe Jev and sets Claude's effort level, never touching the model
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jeffort — andrewstephenson-v1
A Claude Code mod that scores each prompt with TypeSafe Jev and sets Claude's effort level for that turn, mapping four narrow questions, reasoning depth, scope, stakes and ambiguity, onto an effort level without ever touching the model.
- Stars
- 2
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- andrewstephenson-v1
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jeffort — vntrungld.
Works forJev for Routing
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- Sets Claude Code's effort level automatically each turn; the model itself is never touched.
- TypeSafe Jev scores the prompt on four narrow questions: reasoning depth, scope, stakes and ambiguity.
- A fifth question detects prompts that only approve the previous one ('yes, go ahead'), keeping the prior level.
- The README argues a Jev call costs very little next to the output tokens it can save.
- MIT-licensed TypeScript repo, 2 stars, created 2026-10-03 and pushed 2026-10-06.
Watch out
README and GitHub metadata reviewed 2026-10-17; the digest truncates the README after the motivation section, so the install steps, configuration keys and the effort-level scale are not evidenced here.
Questions about this entry
Short answers drawn from the linked project or page.
A Claude Code mod that sets Claude's effort level for each turn automatically: TypeSafe Jev scores your prompt on four narrow questions, and Jeffort maps the result onto an effort level for that turn.
Jev scores the prompt on four narrow questions, reasoning depth, scope, stakes and ambiguity, and a fifth question asks whether the prompt only approves the previous one, in which case the previous level stands.
No. The README is explicit that the model is never touched; Jeffort only chooses the effort level per turn based on Jev's answers about the prompt.
The digest truncates the README after the motivation section, so install and configuration steps are not evidenced here. The repo is TypeScript, MIT-licensed, with 2 stars, created 2026-10-03 and pushed 2026-10-06.
The README argues that too-high effort burns tokens on easy turns while too-low effort causes rework that costs more, and that a Jev call costs very little next to the output tokens it can save.
The README warns that Jeffort will pick higher levels quite often for complex projects, and that this is not overspending but a response to the prompt; the digest truncates the reasoning that follows.
The andrewstephenson-v1 GitHub account publishes it under MIT. Digest metadata shows 2 stars, created 2026-10-03 and last pushed 2026-10-06.
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 routes each request to haiku, sonnet or opus with a reasoning effort and confidence score using local heuristics, and can optionally let Jev (TypeSafe System One) pick the tier instead. Adds a live status band above the prompt.
Jev Tools & CLIs#community#github#claude-code
Community
visualife/ClaudeRouterTypeScript
visualife/ClaudeRouterTypeScriptA Claude Code mod that asks Jev (TypeSafe) how much effort each prompt needs and sends every request of that turn at that effort, never changing the main loop's model. Off by default; a fork of jjjjjjjjjjjjjjjjacob/jev-router.
Jev Tools & CLIs#community#github#claude-code
Community
vntrungld/jeffortTypeScript
vntrungld/jeffortTypeScriptA Claude Code plugin that routes each request to the right model and effort — Haiku for quick lookups, Sonnet for well-specified changes, Opus for investigation or design — by asking TypeSafe Jev three questions about the request: reasoning depth, whether it starts a new task, and whether it is high-risk.
Jev Tools & CLIs#community#github#typescript
Community
wide3751/sommelierTypeScript
wide3751/sommelierTypeScriptA TypeScript/Bun launcher that routes coding-agent user turns through JEV, the TypeSafe classifier, with model and reasoning-effort selection: codex-jev wraps the Codex CLI, claude-jev wraps Claude Code, and a Pi extension adds a jev/auto virtual model.
Jev Tools & CLIs#community#github#cli
Claude Code plugin and CLI that runs Claude Code on Opus 5.5 and has Jev re-decide the reasoning effort when a prompt arrives and after every tool batch, sending each change as a per-message effort statement inside one unbroken prompt cache.
Jev Tools & CLIs#community#claude-code#routing
Community
WXK-AI/jev-opusTypeScript
WXK-AI/jev-opusTypeScriptA Claude Code plugin that sends every Agent spawn through JEV (TypeSafe), which picks the model (haiku, sonnet, opus), the effort and the tool profile of each subagent. It fails open to sonnet at medium effort, accepts a TypeSafe or OpenRouter key, and ships plan and run skills.
Jev Agents & MCP#community#github#claude-code
Community
hiyoku/jev-orcTypeScript
hiyoku/jev-orcTypeScriptFrom 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.