No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by 0xNatoshi · Codex Skill · ★ 80
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jev-codex-router safe to install? View the security audit →
Jev Codex Router Per-turn model routing for Codex, driven by Jev (TypeSafe System One). Every turn is classified by Jev and served by the cheapest model that can handle it, at a thinking depth adapted to the task — instead of running everything on the frontier model. The decision costs ≈ $0.00003 and ≈ 0.6 s per turn. Measured savings: ≈ −60 % vs a full-frontier baseline on a 7-day replay of 237 real turns — protocol, tables and limitations in BACKTEST.md. Installing with an AI agent? Hand it AGENTS.md. This is not a fork of any router: it plugs into an existing local Codex Router installation through its official extension points (a generic provider + a curated model), so router updates never overwrite it. How it works Codex ──▶ Codex Router (:4202) ├─ native models ──────────────▶ ChatGPT backend (your plan) └─ "jev/auto" ─▶ LiteLLM ─▶ API forwarder │ ▼ jevserver.py (127.0.0.1:4319) │ 1. classify the turn with Jev │ 2. apply the routing policy │ (model, reasoning.effort, servicetier) ▼
| Stars | 80 |
| Forks | 8 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.3079396443914/100 |
| Last Updated | 2026-09-17 |
| Created | 2026-09-17 |
| Platforms | codex, python |
| Est. Tokens | ~10k |
These tools work well together with jev-codex-router for enhanced workflows:
Looking for a jev-codex-router alternative? If you're comparing jev-codex-router with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A curated list of official resources and community projects for TypeSafe, System One models, and Jev.
mcp store manager, add & syncs MCP server configurations across clients like Claude code, Cursor💡mcphub
🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
A staged code-review workflow and local dashboard built with TypeSafe Jev.
Explore other popular codex skill tools:
jev-codex-router is Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.. It is categorized as a Codex Skill with 80 GitHub stars.
jev-codex-router is primarily written in Python. It covers topics such as ai, codex, jev.
You can find installation instructions and usage details in the jev-codex-router GitHub repository at github.com/0xNatoshi/jev-codex-router. The project has 80 stars and 8 forks, indicating an active community.
jev-codex-router is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to jev-codex-router on Agent Skills Hub include awesome-typesafe, mcp-linker, awesome-jev. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: