explaingit

nanako0129/pilotfish

Analysis updated 2026-05-18

527PythonAudience · developerComplexity · 2/5Setup · easy

TLDR

A configuration-only setup for Claude Code that routes planning to a top model and routine work to cheaper models to save usage limits.

Mindmap

mindmap
  root((pilotfish))
    What it does
      Splits work by model tier
      Defines eight AI roles
      Verifies with fresh context
    Tech stack
      Claude Code config
      Markdown role files
      JSON settings
    Use cases
      Save subscription usage
      Cheaper mechanical edits
      Global install across projects
    Audience
      Claude Code users
      Cost conscious developers
    Notes
      No runtime code
      Sibling projects for other agents

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Reduce how fast a Claude Code subscription's usage limits are consumed on routine coding tasks.

USE CASE 2

Automatically route mechanical edits and searches to cheaper models while keeping planning on the top model.

USE CASE 3

Install a global multi-model policy once and apply it across every project.

USE CASE 4

Get fresh-context verification of finished work instead of a model reviewing its own output.

What is it built with?

Claude CodeMarkdownJSON

How does it compare?

nanako0129/pilotfishkappaemme-git/codex-complexity-optimizerautomatic1111/stable-diffusion-webui-promptgen
Stars527528531
LanguagePythonPythonPython
Last pushed2023-07-20
MaintenanceDormant
Setup difficultyeasyeasyeasy
Complexity2/52/52/5
Audiencedeveloperdevelopervibe coder

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

One-prompt install writes config files under the Claude Code home directory, no runtime code to run.

In plain English

Pilotfish is a configuration setup for Claude Code, the AI coding assistant, that changes how it splits work between different AI models to save money and usage limits. Instead of running every task on the most powerful and most expensive model, pilotfish sets things up so a top tier model handles planning, decision making, and reviewing, while cheaper models handle the routine, mechanical parts of a coding session, such as searching through files or making straightforward edits. A separate model then double checks the finished work before it counts as done. The project explains that heavy duty AI sessions can burn through a subscriber's usage limits quickly, especially when a lot of that usage is spent on simple, repetitive tasks that a cheaper model could handle just as well. Pilotfish is built entirely out of configuration files rather than new code you run. It defines eight named roles, each pinned to a specific model and a specific job, such as a low effort scout role for read only lookups, a mechanical executor role for fully specified repetitive work, and a verifier role that checks finished work with a fresh perspective rather than reviewing its own output. Installation places these configuration files under a hidden folder in your home directory that Claude Code already reads from, so the setup applies globally across all of your projects at once rather than needing to be configured per project. The README also links to two sibling projects, one that adapts a similar approach for a different AI model provider without permanently changing your main Claude Code setup, and another that ports the same role based approach to a different coding agent entirely. The README backs its cost saving claims with references to official documentation and third party benchmark experiments showing that splitting a top tier planning model with cheaper worker models can reach a large majority of full performance for meaningfully less cost. It also documents a known quirk in how a recent Claude Code version handles its own built in search feature, and how pilotfish overrides that behavior to avoid unexpectedly expensive searches. The full research notes with sources are included in the project's documentation folder.

Copy-paste prompts

Prompt 1
Walk me through installing pilotfish and what files it adds under my home directory.
Prompt 2
Explain the eight roles pilotfish defines and which model each one uses.
Prompt 3
Help me understand how pilotfish's fallback behaves when the top tier model is unavailable.
Prompt 4
What does pilotfish change about Claude Code's built in Explore subagent, and why?

Frequently asked questions

What is pilotfish?

A configuration-only setup for Claude Code that routes planning to a top model and routine work to cheaper models to save usage limits.

What language is pilotfish written in?

Mainly Python. The stack also includes Claude Code, Markdown, JSON.

How hard is pilotfish to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is pilotfish for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.