multi-model-strategy

Guidance for choosing an AI model for a coding task. It compares model choices by cost, speed, available context, and depth of reasoning.

In plain words
What is it for?
Use it to choose automatic or manual model selection, match models to different steps, assign models to sub-agents, and balance quality with cost.
Why use it?
It helps avoid using an expensive, slow model for simple exploration or an unsuitable model for complex or security-sensitive work. You can also compare models on the same task.

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/drvoss/everything-copilot-cli/multi-model-strategy
Any agent
npx skills add drvoss/everything-copilot-cli --skill multi-model-strategy
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,638 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 $0.00036 $0.02638
Opus 5 $0.00018 $0.01319
Sonnet 5 $0.00007 $0.00528
Haiku 4.5 $0.00004 $0.00264

Measured 2d ago against content hash a7db217c6596, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-model-strategy 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.

skills/copilot-exclusive/multi-model-strategy/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Model Strategy

Why This is Copilot-Exclusive

Copilot CLI provides a broad model selection that can be switched at any time via the /model command or per-agent via the model parameter. This lets you mix premium review models, code-focused implementation models, and fast/cheap exploration models in one workflow instead of forcing every step through the same model family.

When to Use

  • Deciding whether Copilot Auto should handle model choice or whether to override it manually
  • Matching model strengths to task requirements
  • Optimizing cost for high-volume operations (use cheaper models for exploration)
  • Using premium models for security-critical or architecturally complex work
  • Running different models for different sub-agents in the same session
  • A/B testing model quality on the same task
  • Pairing implementation and review models on the same workflow

Workflow

Auto Model Selection

Auto model selection is available in Copilot CLI. When you choose Auto, Copilot selects an appropriate supported model based on your plan and policies, and shows which model was used for each response in the terminal.

/model
# Select Auto

Use Auto when:

  • the task mix is broad and you do not want to hand-tune each step
  • you want lower mental overhead for everyday work
  • the session may shift between exploration, implementation, and review

Prefer a manual override when:

Scenario Why override Auto Suggested path
High-stakes security or architecture work You want a guaranteed premium model choose a premium model explicitly
Strict reproducibility matters Auto can route to different supported models over time lock a specific model
You are comparing two models intentionally A/B testing requires a stable choice pick exact model names

Model Tiers and Strengths

Premium Tier (Deep Reasoning)
Model Best For
claude-opus-4.7 Frontier reasoning, most capable Claude
claude-opus-4.6 Complex architecture, security analysis
claude-opus-4.5 Deep reasoning, nuanced code review

Read the full file on GitHub · 267 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 · 267 lines · 36 tokens per session scan A a7db217c6596

Subscribe to this mod's changes

multi-model-strategy is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 2,638 once invoked, about $0.0002 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 skills, from other repositories

prompt-writer

Use when creating, reviewing, or revising prompts, system prompts, developer instructions, agent policies, prompt templates, eval prompts, or skill files consumed by LLMs and AI agents. Routes to OpenAI, Anthropic/Claude, or generic prompt-writing guidance based on the target model/provider.

SNIKO/agent-skills · 64 tokens

context-fundamentals

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…

muratcankoylan/Agent-Skills-for-Context-Engineering · 125 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

gpt-5-4-prompting

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin.

openai/codex-plugin-cc · 40 tokens