models-preset

models-preset is a command for Claude Code from EZotoff/ez-omo-config. It costs 9 tokens per session (597 once invoked), scanned A, original, MIT.

A command that reads OpenCode configuration files and displays model assignments in four Markdown tables.

In plain words
What is it for?
It is for checking current agent and category model settings without changing the configuration.
Why use it?
It provides a readable view of which models and fallback models are assigned to agents and categories.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions OpenCode.

Good fit It is for checking current agent and category model settings without changing the configuration.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ezotoff/ez-omo-config/models-preset
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.

Clone the repo
git clone --depth 1 https://github.com/EZotoff/ez-omo-config

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 models-preset

README.md
[![agentmods](https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/models-preset/github.svg)](https://agentmods.dev/commands/ezotoff/ez-omo-config/models-preset)
Your own site
<a href="https://agentmods.dev/commands/ezotoff/ez-omo-config/models-preset"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/models-preset/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for models-preset

Your own site · 80×15
<a href="https://agentmods.dev/commands/ezotoff/ez-omo-config/models-preset"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/models-preset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 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. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00009 $0.00597
Opus 5 $0.00005 $0.00298
Sonnet 5 $0.00002 $0.00119
Haiku 4.5 $0.00001 $0.00060

Measured 6d ago against content hash b0d3c5850cc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

models-preset 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 6d 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.

commands/models-preset.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read these files and do not modify them:

  1. ~/.config/opencode/oh-my-openagent.json
  2. ~/.config/opencode/opencode.json

If both files and required keys are present, output exactly four markdown tables, in this order:

Agents

Read the agents object from ~/.config/opencode/oh-my-openagent.json.

Use columns:

Agent Model Variant Fallback Models
  • Include one row for every key under agents.
  • Model comes from agents.<name>.model.
  • Variant comes from agents.<name>.variant.
  • Fallback Models comes from agents.<name>.fallback_models.
  • If variant or fallback_models is missing, show .
  • Format fallback model arrays as comma-separated values.

Categories

Read the categories object from ~/.config/opencode/oh-my-openagent.json.

Use columns:

Category Model Variant Fallback Models
  • Include one row for every key under categories.
  • Model comes from categories.<name>.model.
  • Variant comes from categories.<name>.variant.
  • Fallback Models comes from categories.<name>.fallback_models.
  • If variant or fallback_models is missing, show .
  • Format fallback model arrays as comma-separated values.

Compaction

Compaction has no pinned model — agent.compaction.model is intentionally unset in ~/.config/opencode/opencode.json, so compaction runs on the triggering session's model (which the chat-level fallback machinery keeps healthy). On compaction-mode provider failures, provider-connect-retry.mjs retries compaction through the compaction_fallback_models chain in ~/.config/opencode/retry-errors.json.

Use columns:

Setting Value
Compaction model follows session model
Compaction fallback chain ...
  • Read the chain from compaction_fallback_models in ~/.config/opencode/retry-errors.json; format as comma-separated entries.
  • Output exactly these two rows for compaction.

Read the full file on GitHub · 76 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. 6d ago Changed · +2 lines b0d3c5850cc8
  2. 10d ago First seen · 74 lines · 9 tokens per session scan A 04cf324a1119

Subscribe to this mod's changes

models-preset is a command published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 597 once invoked, about $0.0000 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 2026-08-31.