model-usage

model-usage is a skill for Claude Code, Codex from aaronnat23/disp8ch. It costs 0 tokens per session (113 once invoked), scanned A, original, MIT.

A guide for choosing an AI model or provider based on the kind of work, such as coding, research, voice, or batch processing. It considers quality, speed, cost, and setup effort.

In plain words
What is it for?
Use it to compare providers, decide between hosted and local models, and troubleshoot workflows with cost or latency problems.
Why use it?
It helps avoid using a model that is unnecessarily expensive, slow, or poorly suited to 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/aaronnat23/disp8ch/model-usage
Any agent
npx skills add aaronnat23/disp8ch --skill model-usage
Clone the repo
git clone --depth 1 https://github.com/aaronnat23/disp8ch

Made for: Claude Code, Codex.

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 model-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronnat23/disp8ch/model-usage.svg)](https://agentmods.dev/skills/aaronnat23/disp8ch/model-usage)
Your own site
<a href="https://agentmods.dev/skills/aaronnat23/disp8ch/model-usage"><img src="https://agentmods.dev/badge/skills/aaronnat23/disp8ch/model-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 113 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 $0.00000 $0.00113
Opus 5 $0.00000 $0.00056
Sonnet 5 $0.00000 $0.00023
Haiku 4.5 $0.00000 $0.00011

Measured 4d ago against content hash 9f5a1eb26bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-usage 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 4d 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.

optional-skills/model-usage/SKILL.md · 14 lines

What it actually says

Model Usage

Explain model choice, provider tradeoffs, and cost or latency implications in practical terms.

Use when

  • A user asks which model/provider should be used for a task.
  • A workflow is slow, expensive, or mismatched to the job.

Workflow

  1. Identify the actual task shape: chat, coding, research, voice, or batch execution.
  2. Compare quality, speed, and setup friction.
  3. Prefer the simplest provider that satisfies the job.
  4. Call out when local models or gateway routing make more sense.
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. 4d ago First seen · 14 lines · 0 tokens per session scan A 9f5a1eb26bd5

Subscribe to this mod's changes

model-usage is a skill published in the GitHub repository aaronnat23/disp8ch (98 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 113 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 2026-08-30.

Related

Other skills, from other repositories

tiktok-video

一句话需求 → 成品竖屏短视频:写分镜、自动搜免费素材、TTS 配音、逐字卡拉OK字幕、BGM、ffmpeg 合成 1080x1920 MP4(零 API key 可用).

Fangyuan025/Chaty · 59 tokens

netllm-swarm

Configure multi-machine LAN mesh for swarm-llm (netllm). Use when the user asks to set up a swarm, connect multiple machines (macOS, Linux, Windows), enable LAN routing, find peers via mDNS, configure a gateway, or invokes /netllm-swarm. Covers init --swarm, netllm join, swarm-token pairing, localspillover load…

matthewdcage/llm-swarm-router · 100 tokens

netllm-connect-editor

Wire AI coding tools (Cursor, Claude Code, Codex, VS Code Copilot, Honcho, Hermes Agent) to a running netllm agent at http://127.0.0.1:11400/v1. Use when the user asks to connect Cursor to netllm, use local LLM in Claude Code or Codex, point an editor at the swarm router, or invokes /netllm-connect. Requires netllm…

matthewdcage/llm-swarm-router · 113 tokens

netllm-doctor

Troubleshoot swarm-llm (netllm) misconfigurations. Use when netllm is broken, no models appear, the agent is unreachable, mDNS fails, PATH is wrong, or the user invokes /netllm-doctor. Runs netllm doctor and structured checks for providers, listen address, and global vs repo-local CLI.

matthewdcage/llm-swarm-router · 81 tokens

netllm-setup

First-time install and bootstrap of swarm-llm (netllm) from a repo checkout. Use when the user asks to install swarm-llm, set up netllm, get the router running, clone and configure llm-swarm-router, or invokes /netllm-setup. Runs uv sync, netllm init (--single or --swarm), discover, serve verification, and prints…

matthewdcage/llm-swarm-router · 118 tokens

prompt-reframe

Tighten user prompts before they reach a model — strip conversational filler, drop fragments, dedupe sentences, rank by relevance, and compose a short, declarative system prompt that doesn't waste context. CPU-only, deterministic, dependency-free. Use it whenever a request is long, rambling, or covered in pleasantries…

greyok00/slimtoken · 88 tokens