Agent Permissions

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 permission files. This spec provides:

• One policy, many agents: write once, convert to any agent's native format
• Zero-translation migration: Claude Code's permissions block is valid input
• Superset coverage: expresses features from all supported agents (sandboxing, named profiles, per-agent overrides, conditional rules)
• IDE support: JSON Schema for autocomplete and validation (on SchemaStore)

File location

| File | Purpose | Git | |---|---|---| | .agents/permissions.json | Team-shared policy | Committed | | .agents/permissions.local.json | Personal overrides | Gitignored |

Both files are merged at load time. Deny rules from any source short-circuit before allow rules.

Installation

As an MCP server

CLI shorthand

Some agent harnesses provide a one-command install:

Claude Code (MCP):

claude mcp add agent-perms -- npx -y agent-perms-mcp

Claude Code (plugin marketplace):

/plugin marketplace add https://github.com/Mearman/agent-permissions.git
/plugin install agent-perms@agent-perms

OpenAI Codex:

codex mcp add agent-perms -- npx -y agent-perms-mcp

Manual configuration

For harnesses that use config files, add the following to the mcpServers section:

{
  "agent-perms": {
    "command": "npx",
    "args": ["-y", "agent-perms-mcp"]
  }
}

| Harness | Config file | Config key | |---|---|---| | Claude Code | .mcp.json (project) / ~/.claude.json (user) | mcpServers | | Codex | ~/.codex/config.toml | [mcp_servers.agent-perms] | | Gemini CLI | ~/.gemini/settings.json | mcpServers | | Crush | .crush.json / ~/.config/crush/crush.json | mcp | | Cline | .cline/mcp.json | mcpServers | | Cursor | .cursor/mcp.json | mcpServers |

The MCP server is a background sync daemon. It exposes no tools, reads config from .agents/permissions.json, and keeps native agent config files in sync.

As a library

pnpm add agent-perms

Exports

The package uses wildcard exports: import only what you need.

Programmatic API (agent-perms/api)

Side-effect-free functions for use as a library:

import { convert, validate, check, detectFormat } from "agent-perms/api";

// Convert between formats (auto-detects source)
const result = convert(undefined, "canonical", claudeCodeJson);
result.output;   // canonical object
result.from;     // "claude-code" (detected)
result.ruleCount; // 3

// Validate a policy
const { valid, errors } = validate(json);

// Evaluate a tool call
const { decision } = check("Bash", "sudo rm -rf /", policy, { branch: "main" });
// decision: "allow" | "deny" | "ask"

// Detect format from structure
const format = detectFormat(json); // "claude-code" | "crush" | "kiro" | ...

Other modules

// Zod schemas (single source of truth)
import { AgentPermissionPolicy } from "agent-perms/schema";

// Deny-first evaluator
import { evaluate } from "agent-perms/evaluate";

// Multi-layer policy loader
import { loadPolicy } from "agent-perms/loader";

// Bidirectional codecs for each agent
import { claudeCodeCodec } from "agent-perms/compat/codecs";

// SDK enum alignment checks
import { claudeCodeModes } from "agent-perms/compat/enums";

// Sync filesystem configs
import { sync } from "agent-perms/sync";

Schema overview

import { type AgentPermissionPolicy } from "agent-perms/schema";

// All fields are optional. A valid policy can be as minimal as `{}`.
interface AgentPermissionPolicy {
  $schema?: string;

  // Default mode: standard | autonomous | restricted | readonly
  // Also accepts Claude Code modes: plan | dontAsk | acceptEdits | bypassPermissions
  defaultMode?: PermissionMode;

  activeProfile?: string;

  // Permission rules (deny-first evaluation)
  rules?: Array;

  // Claude Code compat: string rule arrays (normalised to rules on load)
  permissions?: {
    allow?: string[];
    deny?: string[];
    ask?: string[];
    additionalDirectories?: string[];
    defaultMode?: PermissionMode;
  };

  profiles?: Record;

  delegation?: {
    maxDepth?: number;
    nonDelegable?: string[];
    bubbleUp?: boolean;
    agents?: Record;
  };

  sandbox?: {
    mode?: "readonly" | "workspace-write" | "full-access";
    writableRoots?: string[];
    networkAccess?: boolean;
  };

  network?: {
    enabled?: boolean;
    domains?: Record;
  };

  env?: Record;
}

Rule syntax

Rules use Tool(pattern) strings inside permissions arrays, compatible with Claude Code's permission format. In the unified rules array, the tool and pattern are separate fields:

| Rule object | permissions string | Type | Matches | |---|---|---|---| | { tool: "Read" } | Read | Bare | All invocations of Read | | { tool: "Bash", pattern: "git status" } | Bash(git status) | Exact | Exactly git status | | { tool: "Bash", pattern: "npm:*" } | Bash(npm:*) | Prefix | npm + space + anything | | { tool: "Bash", pattern: "git commit *" } | Bash(git commit *) | Wildcard | git commit + anything | | { tool: "Bash", pattern: "domain:evil.com" } | Bash(domain:evil.com) | Domain | Commands containing evil.com | | { tool: "mcp__github" } | mcp__github | MCP server | All tools from github MCP server |

Evaluation order

deny rules → ask rules → allow rules → defaultMode

Deny short-circuits: if any deny rule matches, the tool is blocked regardless of allow rules from any source.

Escape sequences

| Escape | Meaning | |---|---| | \( | Literal ( in pattern | | \) | Literal ) in pattern | | \* | Literal * (not a wildcard) | | \\ | Literal \ |

Evaluator

import { evaluate, type PermissionPolicy, type EvaluationContext } from "agent-perms/evaluate";

const policy: PermissionPolicy = {
  defaultMode: "standard",
  rules: [
    { tool: "Bash", pattern: "sudo:*", tier: "deny" },
    { tool: "Bash", pattern: "git:*", tier: "allow" },
    { tool: "Read", tier: "allow" },
  ],
};

// Returns "deny" | "ask" | "allow"
evaluate(policy, "bash", "git status"); // "allow"
evaluate(policy, "bash", "sudo rm -rf /"); // "deny"
evaluate(policy, "bash", "npm install"); // "ask" (falls through to defaultMode)

// With context for conditional rules
const ctx: EvaluationContext = { cwd: "./packages/api", branch: "main" };
evaluate(policy, "bash", "npm run build", ctx);

Tool names are matched case-insensitively (Bash matches bash).

Converting string rules

import { normaliseStringRule } from "agent-perms/evaluate";

// Convert Claude Code-style string rules to structured rules
const rule = normaliseStringRule("Bash(npm:*)", "allow");
// → { tool: "Bash", pattern: "npm:*", tier: "allow" }

Policy loader

import { loadPolicy } from "agent-perms/loader";

const policy = await loadPolicy({ cwd: process.cwd() });

Walks up from cwd looking for .agents/permissions.json and native agent configs. The policy file itself controls discovery via with, without, and up fields:

{
  "with": ["claude-code", "opencode"],
  "up": 3,
  "rules": [...]
}

• with: only load these native configs (default: canonical only)
• without: load all except these
• up: how many parent directories to walk (default: "all")

Loads and merges layers in order (outermost-first, last-defined-wins for defaultMode):

1. .agents/permissions.json (team-shared, discovered via walk-up)
2. .agents/permissions.local.json (personal overrides, discovered via walk-up)
3. Native agent configs (.claude/settings.json, opencode.json, etc.), if with/without enables them

The loader normalises all permissions string arrays into structured rules. Deny rules from any layer short-circuit. Allow rules are additive.

Agent compatibility

Bidirectional codecs convert between the canonical format and each agent's native config:

import { claudeCodeCodec, codexCodec } from "agent-perms/compat/codecs";

// Decode agent-native → canonical
const policy = claudeCodeCodec.decode(claudeSettings.permissions);

// Encode canonical → agent-native
const codexConfig = codexCodec.encode(canonicalPolicy);

| Agent | Native format | Codec | Fidelity | |---|---|---|---| | Claude Code | Tool(pattern) rule strings in .claude/settings.json | claudeCodeCodec | Lossless | | OpenCode | Per-tool ask/allow/deny objects in config.json | opencodeCodec | Near-lossless¹ | | Codex | Named profiles + sandbox in TOML config | codexCodec | Near-lossless² | | Crush | Tool allowlist in config.json | crushCodec | Lossy³ |

¹ OpenCode's agent-specific tools have no canonical equivalent. Per-agent markdown overrides must be handled by the caller.

² Codex's on-failure approval policy and granular approval config have no canonical equivalent. TOML serialisation is the caller's responsibility; the codec works on parsed JS objects.

³ Crush has no deny, no patterns, no modes, only a bare tool allowlist. Pattern rules and deny rules are lost on encode.

Zero-translation migration from Claude Code

jq '.permissions' .claude/settings.json > .agents/permissions.json

This works because the canonical spec accepts Claude Code's rule syntax, mode values, and defaultMode placement unchanged. The loader normalises permissions arrays into structured rules.

MCP sync server

import { startMcpServer } from "agent-perms/mcp";

A background sync daemon that keeps native agent config files bidirectionally synced with .agents/permissions.json. Exposes no tools; purely filesystem sync. Configured via the sync field in the policy file:

{
  "sync": {
    "mode": "watch",
    "backup": true
  }
}

• mode: "sync": one-shot sync on startup
• mode: "watch": continuous sync via fs.watch
• mode: false: disabled

Also available as the agent-perms-mcp binary.

CLI

The agent-perms binary converts, validates, syncs, and serves permission configs.

All flags, no positionals. Format names resolve to default config file locations. Use - for stdin/stdout.

claude-code  →  .claude/settings.json
canonical    →  .agents/permissions.json
opencode     →  opencode.json
kiro         →  .kiro/permissions.json
codex        →  codex.toml
crush        →  .crush.json

convert

# Format name → reads/writes default config locations
agent-perms convert --from claude-code --to canonical

# File paths: auto-detects format from contents
agent-perms convert --from .claude/settings.json --to crush

# Piping with -
cat settings.json | agent-perms convert --from - --to canonical --output -

# Write to specific file
agent-perms convert --from claude-code --to canonical --output my-policy.json

| Flag | Short | Aliases | Description | |------|-------|---------|-------------| | --from | -f | --input, --in | Source (format, file, or - for stdin) | | --to | -t | | Target format or file (required) | | --output | -o | --out | Output file (overrides --to path), or - for stdout | | --compact | -c | | Single-line JSON | | --verbose | -v | | Show decode/encode summary on stderr |

validate

agent-perms validate --input canonical
agent-perms validate --input .agents/permissions.json
echo '...' | agent-perms validate --input -

| Flag | Short | Aliases | Description | |------|-------|---------|-------------| | --input | -i | --in | Policy file (format, file, or - for stdin) |

Exits 0 if valid, 2 with error details if not.

check

agent-perms check --tool Bash --input "git status" --policy-file canonical
agent-perms check --tool Bash --input "git status" --policy-file .agents/permissions.json

| Flag | Description | |------|-------------| | --tool | Tool name (required) | | --input | Tool input string (required) | | --policy-file | Policy file (format, file, or - for stdin) | | --cwd, --branch | Evaluation context |

Exits 0 with allow or 1 with deny.

sync

agent-perms sync
agent-perms sync --dry-run
agent-perms sync -w claude-code -w opencode
agent-perms sync -x codex

| Flag | Short | Description | |------|-------|-------------| | --working-dir | -d | Starting directory (default: cwd) | | --up | -u | Ascend n parent directories (default: all) | | --with | -w | Only sync these agents (repeatable) | | --without | -x | Sync all except these agents (repeatable) | | --yes | -y | Apply without prompting | | --dry-run | | Show changes only, never write | | --create | -c | Create config files that don't exist | | --verbose | -v | Show rule provenance | | --backup | -b | Write .bak files before overwriting |

Sync merges rules with deny-first semantics (deny > ask > allow for same tool+pattern). Most restrictive defaultMode wins.

mcp

agent-perms mcp

Starts the MCP sync daemon on stdio. No flags; all config comes from .agents/permissions.json via the sync field. Typically invoked by agent harnesses via npx agent-perms-mcp, not run directly.

JSON Schema for IDE support

The schema is included in SchemaStore. Editors that support it (VS Code, JetBrains, neovim) will automatically provide autocomplete and validation for .agents/permissions.json and .agents/permissions.local.json files with no configuration.

To explicitly reference the schema:

{
  "$schema": "https://github.com/Mearman/agent-permissions/releases/latest/download/agent-permissions.schema.json"
}

Or reference locally:

{
  "$schema": "./node_modules/agent-perms/agent-permissions.schema.json"
}

The schema file ships with the package at agent-perms/agent-permissions.schema.json.

Examples

Minimal: allow safe tools, deny secrets

{
  "rules": [
    { "tool": "Bash", "pattern": "git status", "tier": "allow" },
    { "tool": "Bash", "pattern": "git diff:*", "tier": "allow" },
    { "tool": "Read", "tier": "allow" },
    { "tool": "Grep", "tier": "allow" },
    { "tool": "Read", "pattern": "./.env", "tier":

…

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Mearman](https://github.com/Mearman)
- **Source:** [Mearman/agent-permissions](https://github.com/Mearman/agent-permissions)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.