skills.rest
thurstonsand
thurstonsandCOMMUNITY
Explore all skills by this author →
GitHub

amp-permissions

Evaluate prioritized permission rules to control tool invocations across contexts.

Updated Dec 21, 2025
Search Tags:#automation#security#permissions#policies#amp#tool-control
One-click install
npx skills add https://github.com/thurstonsand/ansiblonomicon --skill amp-permissions
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: amp-permissions
Source: https://github.com/thurstonsand/ansiblonomicon/tree/main/agents/amp/skills/amp-permissions
Command: npx skills add https://github.com/thurstonsand/ansiblonomicon --skill amp-permissions

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Amp’s permission system controls every tool invocation by evaluating a prioritized list of rules before execution. It provides consistent policy enforcement across main threaded operations and subagents, enabling allow, reject, ask, or delegate actions for diverse tools. This enables safe, auditable automation in AI-assisted workflows by centralizing decision logic and providing testable configurations.

Core Features & Use Cases

  • Rule-based decisions: allow, reject, ask, or delegate tool calls with a single, ordered policy.
  • Context-aware enforcement: applies to both the main thread and subagent tool executions to prevent leakage or unsafe actions.
  • Testable policies: supports dry-runs and testing utilities to validate rules before deployment.

Quick Start

Define your first permission rule and test its effect on a tool invocation.

Frequently Asked Questions about amp-permissions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I control tool permissions for AI automation workflows?▼

Tool permissions in AI automation are controlled by evaluating a prioritized list of rules before execution, allowing you to allow, reject, ask, or delegate specific tool invocations like Bash or Git.

How do I enforce security policies across subagent tool executions?▼

Security policies apply context-aware enforcement across both main thread and subagent tool executions, preventing unsafe actions or leakage by centrally evaluating permission rules for every invocation.

Can I test permission rules before deploying them to automation pipelines?▼

Yes, permission rules are testable before deployment using built-in testing utilities and dry-runs to validate allow, reject, ask, or delegate behaviors safely.

What is the best way to define permission policies for tool control?▼

The best way to define permission policies is using the configuration interface, which supports both text-based and JSON rule definitions to manage tool control decisions.

Does this permission system support delegating tool invocation decisions?▼

Yes, the permission system supports delegating decisions for tool invocations, alongside allowing, rejecting, or asking, providing flexible policy enforcement for diverse automation workflows.

Why are my subagent tool calls bypassing main thread permission rules?▼

Subagent tool calls bypassing rules indicates a misconfiguration; the system applies consistent policy enforcement across both main threaded operations and subagents to prevent leakage or unsafe actions.

Related Skills

Explore More Software Engineering Skills→
liuyu520liuyu520
2

webui-permission-flow

Document the WebUI permission flow across CLI, Go backend, and React frontend.

Community
Advanced
justinlevinedotmejustinlevinedotme
7

opencode-agents

Define and configure OpenCode agents with permissions, tools, and mode rules.

Community
Intermediate
cajiascajias

cc-hooks-main-vs-subagent

Detect Claude Code hook invocations from main threads versus subagents.

Community
Advanced
JhabbigJhabbig

protect-mcp-setup

Enforce policy control and auditability for Claude Code tool calls.

Community
Advanced