jevvy

# Jevvy

**Fast probabilistic judgments inside coding-agent workflows**

A plugin collection powered by TypeSafe's [System One model](https://typesafe.ai).

</div>

## Jevvy Permissions

<p>
  <a href="https://www.npmjs.com/package/@jevvy/permissions"><img alt="npm version" src="https://img.shields.io/npm/v/%40jevvy%2Fpermissions?style=flat&labelColor=000000&color=000000" /></a>
  <a href="https://www.npmjs.com/package/@jevvy/permissions"><img alt="npm downloads" src="https://img.shields.io/npm/dm/%40jevvy%2Fpermissions?style=flat&labelColor=000000&color=000000" /></a>
</p>

The permissions plugin auto-approves harmless shell permission requests. Anything uncertain continues through your agent's normal permission flow.

### OpenCode (v2)



### Claude Code



## Quickstart

Node.js 22.19 or newer is required.

```bash
npx @jevvy/permissions init
```

## Manual setup

### OpenCode

```bash
opencode plugin add @jevvy/permissions
```

### Claude Code

```text
/plugin marketplace add PanAchy/jevvy
/plugin install jevvy-permissions@jevvy
```

## How it works

Each coding agent evaluates its own permission policy first. Existing allow and deny decisions stay final. Jevvy Permissions reviews only unresolved shell approval requests. It approves only the current action when every inquiry passes. Otherwise it abstains, leaving the agent's remaining permission flow unchanged.

```mermaid
flowchart TD
    rules[Coding agent permission policy]
    rules -->|Allow| run[Run the command]
    rules -->|Deny| block[Block the command]
    rules -->|Approval request| review[Jevvy Permissions reviews]
    review -->|Every inquiry passes| approve[Approve this action]
    review -->|Anything else| remaining[Continue the remaining permission flow]
    approve --> proceed[Coding agent continues