auto-model

An automatic routing system that chooses an underlying AI model for each request according to a selected tier. The tiers are frontier, efficient, and free, with different cost and capability goals.

In plain words
What is it for?
Use it by selecting an Auto Model tier before working in modes such as Code, Architect, or Debug. You can inspect the model used and its cost in the expanded model picker.
Why use it?
It removes the need to choose a specific model for every task while letting you prioritize capability, lower cost, or free models.

Agent

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 agents/kilo-org/kilocode/auto-model
Clone the repo
git clone --depth 1 https://github.com/Kilo-Org/kilocode
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,807 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 $0.00013 $0.01807
Opus 5 $0.00006 $0.00903
Sonnet 5 $0.00003 $0.00361
Haiku 4.5 $0.00001 $0.00181

Measured 2d ago against content hash 0681bd318a5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-model 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.

packages/kilo-docs/pages/code-with-ai/agents/auto-model.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Model

Auto Model is a smart routing system that selects an underlying model for each request. Each tier uses its own routing strategy so you can balance cost and capability to fit your needs.

Tier Best For Pricing
kilo-auto/frontier Maximum capability with the best available models Paid
kilo-auto/efficient Lowest cost per task, with capability matched to difficulty Paid
kilo-auto/free The best free models available Free

How It Works

  1. Select an Auto Model tier (e.g. kilo-auto/frontier) in the model dropdown
  2. Start working in any mode (Code, Architect, Debug, etc.)
  3. The system automatically routes your requests to the best model for that task

That's it. No configuration needed.

You can see which underlying models are used, as well as the cost, in the expanded model picker. Model mapping information is also available on the Gateway Model page.

{% callout type="info" title="Models can change" %} The underlying models behind each Auto Model tier are updated server-side as better options become available or as providers change pricing and availability. The tier you select stays the same; the model it routes to may change over time. {% /callout %}

Tiers

  • Frontier — Routes to the latest and most capable paid models. Uses different models for reasoning-heavy tasks (planning, architecture, debugging) versus implementation tasks (coding, building, exploring), pairing the right capability to each type of work.
  • Efficient — Session-aware routing that classifies the difficulty of each request in real time and routes it to the cheapest model proven accurate enough for that task, based on Kilo's continuously-run benchmarks. Routine work stays lean while harder tasks get a more capable model. Because it watches your session in context, it keeps using a model across related turns and only switches when a cheaper option is clearly worth it. If a routing decision can't be made, it falls back to a fixed, cost-effective baseline model, so quality never drops below that baseline. A good default for most developers who want strong AI assistance without paying frontier prices.
  • Free — Routes to the best available free models on OpenRouter, splitting traffic across them. Because free model availability shifts over time as providers change promotional periods, the mapping is updated server-side — you always get the best free option without having to track what's currently available. Quality will be lower than paid tiers, and the models may change over time.

Read the full file on GitHub · 134 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 · 134 lines · 13 tokens per session scan A 0681bd318a5a

Subscribe to this mod's changes

auto-model is an agent published in the GitHub repository Kilo-Org/kilocode (27,119 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,807 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Audit-Commits

Compares HEAD against a tag, identifies user-facing commits, ensures they have linked issues and CHANGELOG entries.

gitkraken/vscode-gitlens · 26 tokens

backseat-dev

Backseat Driver VS Code extension development — ClojureScript shadow-cljs, Ex action/effect framework, MCP socket server, Calva REPL integration, structural editing tools, Datascript output log, skill authoring, REPL-driven interactive programming. Use when: developing Backseat Driver features, debugging extension…

BetterThanTomorrow/calva-backseat-driver · 91 tokens

deep-review-orchestrator

Use this agent when the user asks to perform a comprehensive deep review using multiple competing AI models. Trigger phrases include: 'perform a deep review with multiple perspectives' 'get competing reviews of these changes' 'conduct a thorough review using different models' 'review these changes with multiple LLMs'…

gitkraken/vscode-gitlens · 171 tokens

inspector-driver

Drives the vscode-inspector MCP against a live VS Code + GitLens instance and returns raw evidence (probe values, console/log excerpts, geometry, measurements) as text. Default executor for live-inspection driving so the Opus orchestrator only reasons over distilled results. Returns evidence; does NOT judge, fix, or…

gitkraken/vscode-gitlens · 72 tokens

bd-tester

Agent for testing Backseat Driver tools.

BetterThanTomorrow/calva-backseat-driver · 12 tokens

bootstrap

Mission: Initialize and converge a governed, structured project context for GAAI.

digipulse-engineering/GAAI-framework · 0 tokens