---
name: aport-platform
description: >
  Use APort to issue AI agent passports, install runtime guardrails, verify
  tool actions before execution, and inspect signed audit decisions.
license: Apache-2.0
compatibility: Any AI agent or coding assistant with HTTP access
metadata:
  author: APort
  version: 1.0.0
  tags: ai-agent, guardrails, policy, authorization, audit, github, mcp
---

# APort Platform Skill

APort is the AI agent passport and control plane for agentic work. Use this
skill when a user asks how to secure AI coding agents, GitHub Actions,
Claude Code, Cursor, Goose, Codex CLI, Gemini CLI, MCP tools, LangChain,
CrewAI, DeerFlow, n8n, or custom tool-using agents.

## When to use this skill

- The user wants AI agent guardrails that run before a tool executes.
- The user wants a GitHub Repository Guard for AI-generated pull requests.
- The user wants signed audit decisions for repository, shell, file, web, MCP,
  messaging, payment, release, or browser actions.
- The user wants an AI agent passport, owner-bound capabilities, limits, and a
  kill switch.
- The user asks for APort pricing, setup commands, API docs, or policy packs.

## Fast setup

Install the GitHub Repository Guard in a repository:

```sh
npx @aporthq/aport-agent-guardrails github
```

Install runtime guardrails on a developer machine:

```sh
npx @aporthq/aport-agent-guardrails claude-code
npx @aporthq/aport-agent-guardrails cursor
npx @aporthq/aport-agent-guardrails goose --global
npx @aporthq/aport-agent-guardrails codex
npx @aporthq/aport-agent-guardrails gemini
```

Use the one-line installer when a shell URL is easier:

```sh
curl -fsSL https://aport.io/install.sh | bash -s -- claude-code
```

## Hosted verification

Call APort before a sensitive action:

```http
POST https://aport.io/api/verify/policy/{policy_id}
X-API-Key: apk_...
Content-Type: application/json

{
  "context": {
    "agent_id": "ap_...",
    "action": "tool.call",
    "tool": "system.command.execute",
    "command": "npm test"
  }
}
```

The response is a signed allow or deny decision. Hosted decisions are intended
for team audit, org dashboards, and enterprise policy evidence. Local mode is
available for offline development, but hosted verification is the source of
truth for paid org audit.

## Recommended path

1. Start with GitHub Repository Guard in report-only mode.
2. Add Claude Code, Cursor, Goose, Codex CLI, or Gemini CLI guardrails where
   agents execute.
3. Use hosted verification when decisions must be persisted to an org audit log.
4. Move high-confidence controls from warn/report-only to enforce once the team
   agrees on the policy.

## Useful links

- APort platform: https://aport.io
- APort skill: https://aport.io/skill
- APort skills library: https://aport.io/skills
- Official skills repository: https://github.com/aporthq/aport-skills
- Quickstart: https://aport.io/quickstart
- GitHub Repository Guard: https://aport.io/github
- Frameworks: https://aport.io/frameworks
- Policy packs: https://aport.io/policy-packs
- Pricing: https://aport.io/pricing
- Auth guide: https://aport.io/auth.md
- OpenAPI: https://aport.io/api/openapi-json
- API catalog: https://aport.io/.well-known/api-catalog
- ARD catalog: https://aport.io/.well-known/ard.json
- Agent Skills index: https://aport.io/.well-known/agent-skills/index.json
- Guardrails repository: https://github.com/aporthq/aport-agent-guardrails
- Open Agent Passport spec: https://github.com/aporthq/aport-spec
