jev-pilot

Description

TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to xhigh, raised to max mid-turn when tool calls keep failing), each subagent's model, whether to split the work across subagents, and the one skill the prompt needs. Brings in custom OpenRouter models (a junior coder reviewed by Opus, or cheap bulk work) and Codex or OpenCode as reviewers, in modes you choose, each health-checked. Reads the prompt with recent context, records every decision, and suggests its own tuning. Backends: OpenRouter, TypeSafe's API, the Vercel AI Gateway, or Claude Code's built-in classifier. Built on claude-code-templates' jev-model-router and jev-skill-suggestion.

What it can do

Reach level 3 — network What does this mean? →

Can see: every prompt · every tool call · compaction · the jev-pilot:report skill · subagent spawns · the jev-pilot:setup skill · every skill · /"(?:)"/ calls

Raw API calls (26) +

• $.agent.list
• $.agent.register
• $.clock.after
• $.clock.every
• $.clock.now
• $.clock.sleep
• $.command.list
• $.command.register
• $.env.get
• $.fs.exists
• $.fs.list
• $.fs.read
• $.fs.write
• $.http.fetch
• $.model.classify
• $.process.run
• $.session.cwd
• $.session.messages
• $.store.delete
• $.store.get
• $.store.set
• $.tool.list
• $.ui.invalidate
• $.ui.log
• $.ui.resolve
• $.ui.status

Static check passed on Claude Code 2.1.302.

Install

Check the repo for the exact name.

Details

Repository

akramovic1/jev-pilot

Path in repo

.

License

Unknown

Last updated

Sep 30, 2026

First seen

Oct 4, 2026

Last scanned

Oct 19, 2026

Related mods — reach level 3

• ruflo-console ★ 76,337
• ruflo-goals ★ 76,337
• ruflo-agentdb ★ 76,337
• ruflo-graph-intelligence ★ 76,337