setup-models

setup-models is a command for Claude Code from proticom/gnosys. It costs 0 tokens per session (597 once invoked), scanned A, original, MIT.

A setup command for choosing the default AI provider and model used by Gnosys. It can test the provider with an API call after saving the settings.

In plain words
What is it for?
Use it to select hosted or local providers such as OpenAI, Anthropic, xAI, Ollama, or LM Studio, and choose the model name they should use.
Why use it?
It puts provider and model selection in one place and can reveal connection problems during setup.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/proticom/gnosys/setup-models
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup-models

README.md
[![agentmods](https://agentmods.dev/badge/commands/proticom/gnosys/setup-models.svg)](https://agentmods.dev/commands/proticom/gnosys/setup-models)
Your own site
<a href="https://agentmods.dev/commands/proticom/gnosys/setup-models"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/setup-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 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 5.1 $0.00000 $0.00597
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 2d ago against content hash 75c51c2e8582, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

setup-models 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.

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.

docs/commands/setup-models.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gnosys setup models

Update the default LLM provider and model, optionally validate provider connectivity with a test API call.

Usage

gnosys setup models
gnosys setup models --provider xai --model grok-4.20
gnosys setup models --provider ollama --model llama3.2 --no-validate
gnosys setup models -p anthropic -m claude-sonnet-4-20250514

Options

  • -p, --provider <name> — Set provider directly: anthropic, openai, xai, groq, mistral, openrouter, ollama, lmstudio, or custom.
  • -m, --model <name> — Set model name for the chosen provider.
  • --no-validate — Skip the test API call after configuration.

Behavior

  • Runs the interactive models setup flow when no flags are passed.
  • With --provider and/or --model, applies configuration non-interactively.
  • By default, validates the provider with a test API call unless --no-validate is set.
  • Writes provider and model settings to the active Gnosys config (~/.gnosys/gnosys.json).

Writes and side effects

  • Updates LLM provider and model in config.
  • May store or read provider API keys from the platform secure store or ~/.config/gnosys/.env.
  • OpenRouter: provider openrouter calls https://openrouter.ai/api/v1 with your OpenRouter API key. The setup wizard lists :free models (e.g. nvidia/nemotron-3-super-120b-a12b:free) plus paid tiers from the live catalog.
  • May print shell-profile or env-file hints when keys are missing.

Platform notes

macOS

  • API keys: macOS Keychain (recommended), environment variables, or ~/.config/gnosys/.env
  • Shell profile: ~/.zshrc or ~/.bash_profile for manual export ANTHROPIC_API_KEY=... (provider-specific)

Linux

  • API keys: GNOME Keyring when secret-tool is available, environment variables, or ~/.config/gnosys/.env
  • Shell profile: ~/.bashrc or ~/.zshrc for manual env vars

Windows

  • API keys: Environment variables or ~/.config/gnosys/.env
  • Shell profile: PowerShell profile ($PROFILE) or System Properties → Environment Variables

Read the full file on GitHub · 57 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 · 57 lines · 0 tokens per session scan A 75c51c2e8582

Subscribe to this mod's changes

setup-models is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 597 tokens. 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 2026-09-03.