use-premium-models-efficiently

use-premium-models-efficiently is a skill for Claude Code from patrickdappollonio/claude-plugins. It costs 78 tokens per session (1,049 once invoked), scanned A, original, MIT.

A way to divide large coding tasks between a more capable model that coordinates and judges the work and less expensive models that handle bounded research, coding, testing, or summaries.

In plain words
What is it for?
Use it to coordinate repository research, code patches, test runs, and final review when a task is too large or token-heavy for one model to handle efficiently.
Why use it?
It reduces the amount of expensive model time spent on repetitive or well-defined tasks while keeping one model responsible for the overall result. The exact model names depend on the provider and may change.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the use-premium-models-efficiently plugin — 1 skill shipped together

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/patrickdappollonio/claude-plugins/use-premium-models-efficiently
Any agent
npx skills add patrickdappollonio/claude-plugins --skill use-premium-models-efficiently
Clone the repo
git clone --depth 1 https://github.com/patrickdappollonio/claude-plugins

Made for: Claude Code.

Or install use-premium-models-efficiently, the plugin that ships this one along with the rest of its 1 skill.

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 use-premium-models-efficiently

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/use-premium-models-efficiently.svg)](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/use-premium-models-efficiently)
Your own site
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/use-premium-models-efficiently"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/use-premium-models-efficiently.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 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 5.1 $0.00078 $0.01049
Opus 5 $0.00039 $0.00524
Sonnet 5 $0.00016 $0.00210
Haiku 4.5 $0.00008 $0.00105

Measured 6d ago against content hash bddeebfd2446, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

use-premium-models-efficiently 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.

plugins/use-premium-models-efficiently/skills/use-premium-models-efficiently/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Premium Models Efficiently

The premium model is the orchestrator, architect, synthesizer, and final judge. Cheaper subagents do the token-heavy research, coding, testing, and summarization that doesn't require its full judgment.

flowchart TB
    input["User goal<br>repo context<br>constraints"] --> premium["Premium model<br>orchestrator + judge<br>plan, tradeoffs, synthesis"]
    premium --> result["Integrated result<br>final review<br>user answer + next action"]
    premium <--> research["Lighter agents<br>research scans<br>docs, APIs, repo map"]
    premium <--> coding["Lighter agents<br>bounded coding<br>patches, refactors"]
    premium <--> testing["Lighter agents<br>testing passes<br>scripts, browser, logs"]

Which Models Are Which

The split is by relative cost within whatever provider you're running, not by brand. As of mid-2026:

Provider Premium (orchestrator + judge) Cheaper (subagents)
Anthropic Claude Fable, Claude Opus Claude Sonnet, Claude Haiku
OpenAI GPT-5.6 Sol GPT-5.6 Terra, GPT-5.6 Luna

Model families evolve; when these names are stale, apply the same rule — the most expensive available model takes the judgment seat, the cheaper tiers take the bounded heavy lifting.

Keep with the Premium Model

  • Decomposing ambiguous work into clean parallel slices.
  • Architecture, product, and safety tradeoffs.
  • Reading conflicting subagent reports and deciding what matters.
  • Integrating partial implementations into one coherent result.
  • Final review, risk assessment, and user-facing synthesis.

Delegate to Cheaper Subagents

  1. Spot the heavy lifting — you can't predict token counts, but you can recognize the shapes that always burn them: large repo search, long logs, broad docs, repetitive edits.
  2. Split independent work into subagents before reading everything yourself.
  3. Use cheaper models for research scans, inventory, search summaries, narrow bug hunts, browser/testing passes, test-output reduction, and bounded code edits.
  4. Ask subagents for concise evidence: files, line references, commands run, diffs, uncertainties, and stop conditions they hit.
  5. Spend premium tokens on the decision layer: compare results, resolve conflicts, choose the implementation path, review the final patch.

Read the full file on GitHub · 101 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 First seen · 101 lines · 78 tokens per session scan A bddeebfd2446

Subscribe to this mod's changes

use-premium-models-efficiently is a skill published in the GitHub repository patrickdappollonio/claude-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,049 once invoked, about $0.0004 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.