conductor install

for Claude Code + Codex

Same work. Up to 80% less plan usage.

Right now every grep and every test file burns your most expensive model. Conductor keeps it for judgment and routes the labor to cheaper tiers. Usually 60-80% less burn. No magic, just routing.

install
$ curl -fsSL https://conductorskill.com/install.sh | bash

Backs up everything it touches. Managed markers. One-command undo. Read the script before you run it.

how it works ↓ 

              
            

          

          
One expensive thinker. Five cheap pairs of hands.

        

      

    

  


  
  

    

      

        
the problem

        
Your best model is doing your worst work.

        
Every grep, every boilerplate edit, every test file runs on your most expensive model and counts against your weekly limit at the highest rate. You are paying top-tier prices to do bottom-tier work. The fix is not a cheaper model. It is the right model for each job. That is what Conductor does.

      

    

  


  
  

    

      

        
how it works

        
You conduct. Cheaper models play.

      


      
    
        
  1. 
          
    You conduct.
    
          
    The session's primary model does only what expensive reasoning is for: intent, decomposition, routing, judgment, synthesis.
    
        
    2. 
        
  2. 
          
    The crew plays.
    
          
    Builders (sonnet) write the code, scouts (haiku) gather facts, critics (sonnet) review, all in parallel.
    
        
    3. 
        
  3. 
          
    Your plan stretches.
    
          
    Weekly limits weight usage by per-token cost, and the labor is the bulk of the tokens. Move the labor down a tier and the same plan does more work.
    
        
    4. 
      


      

        One conductor node fanning out to a builder, a scout, a critic, and an architect worker nodeprimaryplan · judgebuildersonnetscouthaikucriticsonnetarchitectopusepics onlysynthesisback to you

        Conductor stacked above four workers, feeding down into synthesisprimaryplan · judgebuildersonnetscouthaikucriticsonnetarchitectopus · epics onlysynthesisback to you
        
one conductor, four workers, one verified result

      

    

  


  
  

    

      

        
the crew

        
Four agents, pinned to a tier.

      


      

        

          
          
buildersonnet

          
Features, fixes, refactors, tests, scripts, drafts.

        

        

          
          
scouthaiku

          
Greps, inventories, config dumps, status checks. Read-only.

        

        

          
          
criticsonnet

          
Adversarial review panels that try to break the work.

        

        

          
          
architectopus

          
Deep design for epics. Used sparingly.

        

      


      
Models are pinned per agent, in each agent's config file, on Claude Code and Codex alike. A dispatch can never silently burn your primary model. sonnet / haiku / opus resolve to whatever your plan provides.

    

  


  
  

    

      

        
what you get

        
Delegation, built into the session.

      


      

        

          
Every session delegates by default.

          
A managed block in your CLAUDE.md, so it is always on, not a thing you have to remember.

        

        

          
/conductor for the big jobs.

          
The full loop: recon, plan, parallel dispatch, verification rounds, synthesis.

        

        

          
Safe installer.

          
Backs up everything it touches, idempotent, one-command uninstall. It never clobbers a file without a recoverable backup.

        

      

    

  


  
  

    

      

        
the math, honestly

        
Usually 60-80% less. Sometimes more.

        
Weekly plan limits (or your API bill) weight usage by per-token cost. On build-heavy work the execution tokens dwarf the orchestration tokens, so routing the labor to cheaper tiers commonly burns 60-80% less, the same fact as stretching a plan 3-5x longer. Less if your session default is already a cheap model, more if you delegate aggressively. No magic, just routing.

        
          
          
          0%60%80%100%already on a cheap defaultdelegating aggressively
        
      


      

        
install

        
One command. Then forget it's there.

      


      

        

          

            

              

              install
            

            

              

                $
                curl -fsSL https://conductorskill.com/install.sh | bash
                
              

            

          

          
Then open a new session and run: /conductor <your objective> (on Codex: $conductor)

          
Read the script before you run it.


          
Uninstall anytime:

          

            

              

              uninstall
            

            

              

                $
                curl -fsSL https://conductorskill.com/install.sh | bash -s -- --uninstall
                
              

            

          

        


        

          
Requirements

          
    
            
  • 
              
              Claude Code: the sonnet and haiku tiers (any paid plan). opus only for the architect.
            
    • 
            
  • 
              
              Codex CLI: GPT-5.4 and GPT-5.4-mini. GPT-5.5 only for the architect.
            
    • 
          

        

      

    

  


  
  

    

      

        
faq

        
Ask the annoying questions.

      


      

        

          
          

            
Yes. Conductor writes its block between managed markers, backs the file up first, and --uninstall removes exactly that block and nothing else. If the markers ever look tampered with, it refuses to guess and tells you instead.

          

        

        

          
          

            
All of it is visible in the script itself. For each harness it detects, it writes four agent files and one skill folder (under ~/.claude for Claude Code; under ~/.codex and ~/.agents for Codex), appends one clearly marked block to your CLAUDE.md or AGENTS.md, records a per-harness manifest of every file it created, and backs up anything it replaces with a timestamped copy. Only if you say yes when it asks: it can also set your Claude Code default model in settings.json, backed up first and flagged again at uninstall. It makes no network calls beyond fetching itself and never touches your code, your keys, or anything outside those folders.

          

        

        

          
          

            
No. Your primary model still thinks, judges, and verifies. It just stops typing the boilerplate itself.

          

        

        

          
          

            
Any paid Claude Code plan with sonnet and haiku. No Opus needed for the core. On Codex, the same routing applies: GPT-5.5 stays for judgment, GPT-5.4 and mini do the labor, and OpenAI's credit metering rewards it the same way.

          

        

        

          
          

            
No. Install it and keep working. It delegates on its own. Use /conductor when you want the full loop on a big task.

          

        

        

          
          

            
Because then the cheap model does your thinking too. Conductor keeps the judgment expensive and the labor cheap: your primary model plans, routes, and verifies; the cheap tiers type. You could do this by hand with /model. You will not remember to.

          

        

      

    

  


  
  

    

      

        
Your best model has better things to do.

        

          

            

            install
          

          

            

              $
              curl -fsSL https://conductorskill.com/install.sh | bash
              
            

          

        

        
One command. Every session after this one delegates on its own.