What is ohmyjev and what does it add to coding agents?

A TypeScript tool that brings Jev to Claude Code, Codex, pi and omp: it answers routine permission prompts, trims long output, speeds up compaction and blocks irreversible actions until you approve them.

How does Jev make the permission decisions in ohmyjev?

Jev decides which commands are safe enough to skip the prompt; the README badge says 'decided by Jev'. The digest truncates the README before the settings and privacy sections, so the question set is not evidenced.

What counts as a destructive command in ohmyjev?

The repository description names rm -rf and force push, plus data exfiltration, as things that are stopped until you say yes. Other categories are not enumerated in the digest.

Which coding agents does ohmyjev support?

Claude Code (2.1.287+), Codex, pi and omp, per the README badge and text. The digest does not document per-agent differences beyond that list.

How do I install ohmyjev?

The digest truncates the README before the Install section, so no command is shown; the package is published on npm as ohmyjev and the project site is ohmyjev.xyz.

What settings can I change in ohmyjev?

The README table of contents lists Settings and Privacy sections, but the digest cuts off before their content, so the configurable behaviour is not evidenced here.

Who maintains ohmyjev and what license does it use?

The novacon GitHub account, under the MIT license, with 2 stars, created 2026-10-08 and pushed 2026-10-15. Repository topics include agent-security and prompt-injection.

Jev directory

CommunityJev Tools & CLIs

Ohmyjev

Jev, batteries included, for Claude Code, Codex, pi and omp: safe commands skip permission prompts, long output is trimmed, and destructive commands such as rm -rf or force push are stopped until you say yes.

See highlights Open github.com

Stars: 2
Language: TypeScript
License: MIT
Reading time: 2 min
Published by: Community
Author: novacon
Last verified: Oct 2026

novacon/ohmyjev

User repository on GitHub

View on GitHub

Jev, batteries included, for Claude Code, Codex, pi and omp: no permission prompts for safe commands, long output trimmed, the right skill loaded, and destructive commands (rm -rf, force push) or data exfiltration stopped until you say yes.

Forks: 1
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github claude-code codex security

Works forJev for Decision gating

Used inJev for Software & DevTools Jev for Security & Privacy

Languages: TypeScript
Platforms: CLI
Capabilities: Open source

Highlights

A Jev-powered layer for Claude Code, Codex, pi and omp that makes routine permission prompts disappear for safe commands.
Long output gets cut down and compaction takes a second, per the README.
Destructive commands (rm -rf, force push) or data exfiltration are stopped until you explicitly say yes.
Installed from npm as ohmyjev with a project site at ohmyjev.xyz and an MIT license.
Targets Claude Code 2.1.287+; repo created 2026-10-08 and pushed 2026-10-15 with 2 stars.

Watch out

README and GitHub metadata reviewed 2026-10-17; the digest truncates the README at the table of contents, so the install steps, settings and privacy sections are not evidenced here.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

YouTube: Kubernetes admission control with a decision model, fail-closed.

Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.

2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker News

X: Jev and Laya on security queries

X: Testing Jev for prompt injection

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Ohmyjev

Highlights

Questions about this entry

What is ohmyjev and what does it add to coding agents?

How does Jev make the permission decisions in ohmyjev?

What counts as a destructive command in ohmyjev?

Which coding agents does ohmyjev support?

How do I install ohmyjev?

What settings can I change in ohmyjev?

Who maintains ohmyjev and what license does it use?

Reactions & coverage

More Jev resources like this

From the Jev guides

From the Jev AI model community