agentconnect-setup

An interactive guide for installing, configuring, and checking the self-hosted AgentConnect open-source stack, a group of services run on your own machine or server.

In plain words
What is it for?
Use it for Docker Compose setup, local no-login evaluation, Logto authentication, public access through a tunnel or reverse proxy, and production configuration.
Why use it?
It helps select the right authentication, network exposure, and deployment setup before services are made accessible.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentconnect-md/agentconnect/agentconnect-setup
Any agent
npx skills add agentconnect-md/agentconnect --skill agentconnect-setup
Clone the repo
git clone --depth 1 https://github.com/agentconnect-md/agentconnect

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.01284
Opus 5 $0.00046 $0.00642
Sonnet 5 $0.00018 $0.00257
Haiku 4.5 $0.00009 $0.00128

Measured 2d ago against content hash 7d87379643f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentconnect-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-local.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/agentconnect-setup/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set Up AgentConnect

Guide the user one checkpoint at a time. Select one deployment mode, load only its relevant references, verify each checkpoint from evidence, and keep a short progress checklist throughout the tutorial.

Establish the session

  1. Determine the AgentConnect checkout or deployment directory. Prefer the current directory when it contains compose.yaml; otherwise ask for or locate the checkout.
  2. Ask whether access is loopback-only, LAN-only, or through stable public domains using Cloudflare Tunnel or another reverse proxy. Never assume localhost. If anything is externally reachable, read references/network-topology.md and collect the final topology before continuing.
  3. Determine the target mode:
    • no-auth: loopback-only local evaluation;
    • local-logto: local evaluation with the bundled Logto OSS overlay;
    • cloud-logto: a locally or single-hosted Compose stack using Logto Cloud.
  4. Determine whether the user wants only the core stack or also Google, GitHub, Slack, a daemon, and production hardening.
  5. Read references/deployment-modes.md plus references/local-logto.md or references/cloud-logto.md only when that mode is selected. Read references/integrations.md only for requested providers. Read references/operations.md for upgrades, reset, remote-daemon networking, or troubleshooting.
  6. Inspect the checkout's compose.yaml, optional compose.logto.yaml, and available environment template before issuing commands. If the checkout differs from the bundled references, follow the checkout and current official documentation, and explain the difference.

For an external topology, obtain these values before starting authentication or provider setup:

  • the final public Web, API, Relay HTTP, and daemon Relay WebSocket origins;
  • the Logto sign-in, admin, issuer, and Management API locations;
  • the tunnel/proxy provider, whether its hostname is stable, and its local origin mappings;
  • whether daemons run on the Compose host, LAN, or Internet;
  • whether an access gateway, WAF, or path rewrite sits in front of any callback or WebSocket endpoint.

Read the full file on GitHub · 72 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 72 lines · 92 tokens per session scan A 7d87379643f2

Subscribe to this mod's changes

agentconnect-setup is a skill published in the GitHub repository agentconnect-md/agentconnect (868 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,284 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.