setup

A setup guide for connecting several AI models that can review the same material. It explains how to configure Codex, OpenCode, OpenRouter, and Gemini, while assuming the reader is not technical.

In plain words
What is it for?
Onboarding users, configuring AI judges or reviewers, and connecting the supported model backends. It is also used when a setup check finds that some backends are missing.
Why use it?
Using several reviewers can reveal disagreement that one model would not point out. The guide helps identify missing connections and explains the setup one step at a time.

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

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00084 $0.01995
Opus 5 $0.00042 $0.00997
Sonnet 5 $0.00017 $0.00399
Haiku 4.5 $0.00008 $0.00199

Measured 2d ago against content hash ea27ce9a1c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

setup scanned grade C with 2 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.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://opencode.ai/install | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://opencode.ai/install | bash
skills/setup/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connect the judges

!sh -c 'for p in "$CLAUDE_PLUGIN_ROOT/scripts" "$HOME/.claude/skills/multi/scripts" "./.claude/skills/multi/scripts"; do [ -x "$p/probe.sh" ] && { "$p/probe.sh"; echo "scripts-dir: $p"; exit 0; }; done; echo "probe: NOT FOUND — locate scripts/probe.sh in this plugin and run it yourself"'

$SCRIPTS is whatever the probe printed as scripts-dir:. The probe already ran above — read it, do not run it again.

The user here is not assumed technical. No jargon, no walls of text, one step at a time, and never make them feel behind for not having done this already.

What this plugin actually is, in plain words

Say this first, briefly, before touching any config:

This plugin asks several different AI models to look at the same thing instead of just one. When they agree, that is a real signal. When they disagree, that disagreement is the whole point — one model alone can't tell you it might be wrong, three models can.

The lineup:

  • Claude — already here, always available, nothing to configure.
  • GPT, through the Codex CLI — needs a ChatGPT account.
  • DeepSeek, through OpenCode — free, works out of the box once installed.
  • Gemini, through its own CLI — needs a free API key.
  • OpenRouter — the bonus one. A single key unlocks many other model families at once. Free models by default, or any specific model with --backend name:model (e.g. --backend openrouter:z-ai/glm-5.2:free).

Fix one thing at a time

Look at the probe output above. For each backend that is missing or not configured, offer the fix — one at a time, not all four in a list. Start with the most valuable one that's missing. Codex comes first if it's missing: /multi:code-review refuses to run at all without it, the others just get weaker.

Order to work through, skipping each install or login fix already OK. The OpenCode model-choice check below always runs, even when OpenCode is OK:

  1. Codex missing or not logged in
    codex login
    
    Needs a ChatGPT account. This opens a browser to sign in — nothing to type here.

Read the full file on GitHub · 176 lines

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 · 176 lines · 84 tokens per session scan C ea27ce9a1c3d

Subscribe to this mod's changes

setup is a skill published in the GitHub repository szarkans/multi (8 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,995 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.