Mearman

Agent Permissions — AI skill for Claude Code

AI community

Cross-agent permission policy for AI coding agents.

How to install Agent Permissions

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Mearman/agent-permissions and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Permissions does

Cross-agent permission policy for AI coding agents. MCP sync daemon, CLI, codecs, and evaluator. One .agents/permissions.json for every agent.

Alternatives in AI

Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
Agmsg — Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other 1.5k ★
Skilldock — SkillDock is an AI skill manager and skill management desktop app for Claude Code, Cursor, Codex, Windsurf, Ge 490 ★

README

agent-perms

[![npm version](https://img.shields.io/npm/v/agent-perms.svg)](https://www.npmjs.com/package/agent-perms) [![License](https://img.shields.io/badge/License-Apache--2.0-lightgrey.svg)](LICENSE) [![CI](https://img.shields.io/github/actions/workflow/status/Mearman/agent-permissions/ci.yml?branch=main)](https://github.com/Mearman/agent-permissions/actions)

A vendor-neutral permission policy format for AI coding agents. One file works across Claude Code, OpenAI Codex, OpenCode, Crush, and any agent that adopts the spec.

Quick start

Create `.agents/permissions.json` in your project root:

{
  "$schema": "https://github.com/Mearman/agent-permissions/releases/latest/download/agent-permissions.schema.json",
  "defaultMode": "standard",
  "rules": [
    { "tool": "Bash", "pattern": "sudo:*", "tier": "deny" },
    { "tool": "Read", "pattern": "./.env", "tier": "deny" },
    { "tool": "Bash", "pattern": "npm publish:*", "tier": "deny" },
    { "tool": "Bash", "pattern": "git status", "tier": "allow" },
    { "tool": "Bash", "pattern": "git:*", "tier": "allow" },
    { "tool": "Read", "tier": "allow" },
    { "tool": "Grep", "tier": "allow" },
    { "tool": "Bash", "pattern": "git push:*", "tier": "ask" },
    {
      "tool": "Bash",
      "pattern": "npm run *",
      "tier": "allow",
      "when": { "cwd": "./packages/*" }
    }
  ]
}

Every rule has a `tool`, an optional `pattern`, a `tier` (deny/ask/allow), and optional `when` conditions. Evaluation is deny-first: all deny rules are checked, then ask, then allow. Falls back to `defaultMode` when no rule matches.

**Zero-translation migration:** `jq '.permissions' .claude/settings.json > .agents/permissions.json` still works. The schema accepts Claude Code's `permissions.allow/deny/ask` arrays and the loader normalises them into rules.

Why

Every coding agent has its own permission config. Teams using multiple agents (or migrating between them) maintain separate, often contradictory permiss