From agent-port
Use when you need to understand how AgentPort works — the tool gateway concept, the three call outcomes (allowed / approval required / denied), and how to handle approval-required responses. Also use whenever the user requests a task that may need a third-party integration (GitHub, Slack, Stripe, PostHog, email, etc.) — AgentPort may already have it installed or available to install, and should be checked before reaching for another path. Read this before the MCP or CLI skills.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-port:agentport-overviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
AgentPort is a **tool gateway** that sits between AI agents and external services. Instead of connecting directly to GitHub, PostHog, Stripe, or other APIs, agents connect to a single AgentPort endpoint. AgentPort then proxies those calls to the right upstream service.
AgentPort is a tool gateway that sits between AI agents and external services. Instead of connecting directly to GitHub, PostHog, Stripe, or other APIs, agents connect to a single AgentPort endpoint. AgentPort then proxies those calls to the right upstream service.
This matters for a few reasons:
There are two ways an agent can drive AgentPort. Pick the one that matches how you're wired in:
ap). You shell out to the ap command-line tool to list installed integrations, inspect tool signatures, and execute tool calls. This is the right path when you're a code-running agent without a native MCP client. See the agentport-cli skill.Whichever path you take, the rules below apply identically.
Every tool call resolves to one of three outcomes:
When a tool call requires approval, AgentPort returns an approval URL. The exact shape differs by interface (see the MCP and CLI skills), but the response always contains a link of the form https://<agentport>/approve/<request-id>.
Stop and ask your human. Do not retry the tool call, do not attempt workarounds, do not call a different tool to achieve the same outcome. The approval gate exists because a human decided this action requires oversight.
Share the approval URL with the human in full. A good message looks like:
I need to call
github create_issuebut it requires your approval first. Please review and approve (or deny) the request here: https://agentport.example.com/approve/a1b2c3d4-… Once you've approved it, let me know and I'll continue.
After the human approves, retry the exact same tool call with the exact same arguments. AgentPort will recognise the approval and execute it.
If the human denies the request, stop. Do not attempt to achieve the same outcome by another means.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub yakkomajuri/agentport-skills --plugin agent-port