Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    EcoRun

    2

    Picks the right Claude model (Haiku, Sonnet, Opus or Fable) and effort level for each task, so you spend fewer tokens without losing quality.

    Free

    1 use5.0 (2 reviews)
    EcoRun

    EcoRun

    Example session with this skill installed

    Migrate this whole React app to TypeScript, then pull the title, author and date out of the 50 PDFs in /docs into a CSV.

    • Read your context and instructions
    • Compiled the ecorun

    EcoRun — before we start

    Task: large refactor (React → TypeScript) + bulk data extraction from 50 PDFs.
    Suggested model: Fable · medium (if you don't have it, Opus · high) for the migration. You're currently on Sonnet.
    Why: a full migration needs architecture-level judgment. A smaller model tends to miss cross-file type issues, and redoing the work costs more than doing it right the first time.

    To continue:

    1. Switch the model with /model fable and reply "continue".
    2. Or reply "stay here" to do it with Sonnet.

    What happens after you choose

    StepWho does itWhy
    Plan and run the TypeScript migrationMain model (Fable or Opus)Needs judgment; edits stay in the main model
    Find every component, prop type and import to updateeco-explorer subagent (Haiku)Searching is cheap and mistakes are easy to spot
    Extract title, author and date from the 50 PDFs into a CSVeco-extractor subagent (Haiku)Repetitive, high-volume, easy to verify
    Check the CSV against a sample and run the buildMain modelVerification before calling it done

    EcoRun stops only on substantial tasks. Short questions get answered right away, and once you choose a model it won't ask again for the same task.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Using the biggest model for everything is comfortable but expensive. Many tasks (searching files, reading logs, extracting data, applying a template) are done just as well by a smaller, faster model. And the opposite is also true: dropping to a small model on a hard task costs more, because you end up redoing it.

    EcoRun applies Anthropic's official model-selection guidance to every task:

    • Haiku: searching, reading logs, extracting, classifying (mistakes are easy to spot)
    • Sonnet: well-scoped work with a clear spec, everyday documents
    • Opus: work that needs judgment, design or hard debugging
    • Fable: the hardest, longest tasks (falls back to Opus at high effort if you don't have access)

    How it works:

    • Before a substantial task, EcoRun classifies it. If another model fits better, it stops, suggests the model and effort level, and waits for you to choose, instead of spending tokens first and recommending later.
    • It never stops on short questions, never asks twice for the same task, and stops asking if you tell it to.
    • The golden rule: when in doubt between saving and quality, quality wins.

    Works in Claude.ai, Cowork and Claude Code. EcoRun is built for Claude models. It responds in your language.

    Claude Code users: install the full plugin, which adds three Haiku subagents (explorer, log reader, extractor) where most of the savings come from: /plugin marketplace add jorge2510/EcoRun /plugin install ecorun@ecorun

    Source, docs and updates: https://github.com/jorge2510/EcoRun License: MIT + Commons Clause. Free to use and modify, including at work. Reselling requires the author's permission.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Requires user to manually change models in UI. Best for tasks long enough to offset the cost of the gatekeeping turn. Cannot force model changes via API without implementation in your own code.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    5.0
    2 reviews
    5
    2
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 1 time.

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed6 days ago

    What's inside

    Frequently Asked Questions

    Before a substantial task, EcoRun checks which Claude model and effort level fit the job. If a cheaper model can do it just as well, it suggests switching before any tokens are spent. If the task needs a stronger model, it says so too, because redoing a failed task costs more than doing it right the first time. In Claude Code, it also sends searching, log reading and data extraction to Haiku subagents.

    Claude.ai, Cowork and Claude Code. EcoRun is built for Claude models only: other agents can load the file, but its recommendations won't apply to them. For apps that call the Claude API, the skill includes guidance on choosing the model in code.

    The skill (SKILL.md), a reference for Claude Code and the API, and a model price table with its verification date. The Claude Code plugin on GitHub also adds three Haiku subagents: eco-explorer, eco-log-reader and eco-extractor. Everything is free.

    EcoRun classifies tasks by model family (Haiku, Sonnet, Opus, Fable), so the rules keep working with newer versions. The price table shows when it was last checked, and EcoRun warns you if it may be outdated. Updates are published on GitHub.

    It helps most with substantial work: code, documents, analysis, migrations and bulk data processing. On short questions it doesn't interrupt: it just answers. If you tell it not to ask, it stops asking.

    New in Prompt & Skill Engineering

    Free