Claude Code mod

effort-pilot

The right reasoning effort for every turn: plans high, building medium, questions low, picked by a Haiku classifier. Switch the model or the effort by saying it ("switch me to Sonnet at medium"). The model is never changed unless you ask for one or set a plan-mode model, and the prompt cache is kept: where effort is a whole-request setting (Claude 4.x, Fable 5, Bedrock, Vertex), it stands aside.

9 starsPane & dashboard mods Plugin marketplaceValidates on Claude Code 2.1.325 Source

Install

Inside Claude Code
/plugin marketplace add vadympetryshyn/effort-pilot
/plugin install effort-pilot@effort-pilot

Mods install like plugins. Run /reload-plugins or start a new session to load it.

What it can access

Reach
L2Writes or runs: writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, requests an Anthropic credential handle, draws
Sees
classic hooks, every prompt, every skill, every tool call, ExitPlanMode calls, EnterPlanMode calls, Skill calls, Agent calls, subagent spawns
Draws in
PaneAbovePrompt
Hooks
session.startclassic.SessionStartsession.endcommand.runprompt.submitskill.promptclassic.UserPromptSubmittool.callagent.spawnturn.startturn.stepturn.completeui.render

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
plugin
Marketplace
effort-pilot
Author
Vadym Petryshyn
License
MIT
Last updated
15 November 2026

FAQ

What is effort-pilot?

The right reasoning effort for every turn: plans high, building medium, questions low, picked by a Haiku classifier. Switch the model or the effort by saying it ("switch me to Sonnet at medium"). The model is never changed unless you ask for one or set a plan-mode model, and the prompt cache is kept: where effort is a whole-request setting (Claude 4.x, Fable 5, Bedrock, Vertex), it stands aside. It is a mod for Claude Code, from vadympetryshyn/effort-pilot on GitHub.

What can the effort-pilot mod access?

Its widest reach is "writes or runs" (writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, requests an Anthropic credential handle, draws). It sees classic hooks, every prompt, every skill, every tool call, ExitPlanMode calls, EnterPlanMode calls, Skill calls, Agent calls, subagent spawns. It draws in Pane, AbovePrompt. Like any mod, it runs with your permissions.

How do I install effort-pilot?

Inside Claude Code (v2.1.287 or later), run /plugin marketplace add vadympetryshyn/effort-pilot and then /plugin install effort-pilot@effort-pilot.

Is effort-pilot popular?

vadympetryshyn/effort-pilot has 9 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 15 November 2026.

More pane & dashboard mods

Browse the most popular Claude Code mods, all pane & dashboard mods, or the skills and MCP server directories.