Agent Permissions — AI skill for Claude Code
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 ★
- Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★
README
agent-perms
[](https://www.npmjs.com/package/agent-perms) [](LICENSE) [](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
Related Skills
Frostagent
Deny-by-default capability linter for AI agent setups: MCP servers, hooks, permissions, skills. A one-screen p
AI Config Sync Manager
Bidirectional sync for Claude Code and Codex — instructions, skills, agents, MCP servers, hooks, permissions.
Resume Consultant Harness
Tailored-resume Claude Code skill using Planner → Generator → Evaluator harness with Zero AI Slop policy and i
Lithium
Mood stabilizer for your AI bill. Cross-provider LLM-spend aggregator (Anthropic / OpenAI / OpenRouter). Local
BulkheadScope
Sandbox policy reality-check and least-privilege minimizer for AI coding agents. Merges every permission layer
Hook Maker
Windows PowerShell wizard to build, install and manage hooks for Claude Code and Codex CLI - including a cross
Related Agents
Contract Sync
Propaga un cambio del contrato OpenAPI B2B de FreeTicket (/api/v1) a TODOS los clientes del paraguas (cli y mc
MCP Owner
Owns mcp/ — the live MCP brain over stdio and the ai-os CLI. Use for work on the server, the Vault door, the t
Permissions Manager
Manage tool permission rules. Use when user says 'allow', 'deny', or 'ask' for a command, wants to modify perm