User repository on GitHub
Claude Code mod that routes each prompt's effort level via TypeSafe's Jev. Fork of jev-router.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jeffort — vntrungld
A 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.
- Stars
- 2
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- vntrungld
- Last verified
- Oct 2026
Works forJev for Routing
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- Routes each prompt's effort via Jev, then sends every request of that turn at that effort; the model is never changed.
- Off by default; enable it with /jev on. A fork of jjjjjjjjjjjjjjjjacob/jev-router from commit 50d7e40 (2026-09-27).
- Questions, level policy and the eval set are kept from upstream; the effort application and data filtering were rewritten.
- A turn.step mod writes effort into each request, so turns that call no tools are still routed, unlike upstream's skill approach.
- Masks code blocks, secrets, URLs, e-mails, IPs and absolute paths before sending data to TypeSafe; highest effort is xhigh.
Watch out
README and GitHub metadata reviewed 2026-10-17; the digest excerpts the differences table but not the install steps or configuration keys, and the upstream eval set it keeps was not independently reviewed here.
Questions about this entry
Short answers drawn from the linked project or page.
A Claude Code mod that asks Jev (TypeSafe) how much effort each prompt needs and then sends every request of that turn at that effort, without changing the main loop's model.
It is off by default; the README says turn it on with the /jev on command.
It applies effort with a turn.step mod instead of blocking tool calls until a skill loads, still routes turns that call no tools, skips notification and peer turns, masks sensitive data, and tops out at xhigh.
The questions sent to Jev (hooks/lib/questions.ts), the level policy (hooks/lib/policy.ts) and the eval set are kept from jjjjjjjjjjjjjjjjacob/jev-router, taken from commit 50d7e40 on 2026-09-27.
The prompt with pasted blocks removed and head/tail truncated, as upstream does, plus masking of code blocks, secrets, URLs, e-mails, IPs and absolute paths.
Only prompts you type are routed; turns from notifications, peers and plugins are skipped, per the differences table.
MIT, with 2 stars, created and pushed 2026-10-05; it is a fork of jjjjjjjjjjjjjjjjacob/jev-router's MIT code and keeps parts of it unchanged.
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
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
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.
Jev Tools & CLIs#community#github#claude-code
More Jev resources like this
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.
Jev Tools & CLIs#community#github#claude-code
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 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.