model-advisor

A guide for choosing among Claude models based on the task's complexity, capabilities needed, and cost. Claude models are different versions of the same AI service, suited to different kinds of work.

In plain words
What is it for?
Use it to select a model for complex reasoning, coding, analysis, classification, simple questions, or high-volume work.
Why use it?
It helps avoid using an unnecessarily expensive model or choosing one that is too limited for the 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/apiliumcode/mayros/model-advisor
Any agent
npx skills add ApiliumCode/mayros --skill model-advisor
Clone the repo
git clone --depth 1 https://github.com/ApiliumCode/mayros

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 330 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 $0.00018 $0.00330
Opus 5 $0.00009 $0.00165
Sonnet 5 $0.00004 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured 2d ago against content hash c30fe86f93b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-advisor 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.

The scan reads SKILL.md. This mod also ships 3 executable files (skill.test.ts, skill.ts, types.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/official/model-advisor/SKILL.md · 38 lines

What it actually says

model-advisor

Recommends the optimal Claude model based on task requirements, complexity analysis, and cost efficiency.

When to Use

Use when choosing between Claude models for a specific task, when optimizing API costs, or when you need guidance on which model best fits a workload profile.

Supported Models

Model Input Output Best For
Opus 4.6 $15/MTok $75/MTok Complex reasoning, research, multi-step analysis, code architecture, creative writing
Sonnet 4.6 $3/MTok $15/MTok Coding, general tasks, data analysis, moderate complexity
Haiku 4.5 $0.80/MTok $4/MTok Classification, extraction, simple Q&A, high volume, low latency

Instructions

  1. Recall any previous model recommendations with skill_memory_context
  2. Analyze the task description from query results for complexity indicators
  3. Match task keywords against model strengths to determine the best fit
  4. Return the recommended model with rationale and cost comparison
Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 38 lines · 18 tokens per session scan A c30fe86f93b3

Subscribe to this mod's changes

model-advisor is a skill published in the GitHub repository ApiliumCode/mayros (12 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 330 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.