Skip to content
All articles
Engineering14 August 2026·4 min read

How to switch models in Claude Code with one command

Most of the difficulty with agents is not the model.

Paycux engineering

Most of the difficulty with agents is not the model. It is that an agent sits between a user and a system that was designed on the assumption a user would be there in person.

This piece walks through how we think about it at Paycux, what we have changed our minds about, and where the sharp edges are.

Why a shell wrapper is enough

Why a shell wrapper is enough deserves its own treatment. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The three exports

The three exports deserves its own treatment. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

  • Scope every agent credential to one principal and one task
  • Give tokens minutes of life, not days
  • Record which agent acted, under whose authority, on what
  • Make revocation a single call that takes effect immediately

The wrapper

That brings us to the wrapper. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Understanding the environment variables

Consider understanding the environment variables. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The audit trail matters more here than in any human flow.

Base URLs by backend

Consider base urls by backend. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

Keep the key out of your shell profile

That brings us to keep the key out of your shell profile. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

The cache-read line is the whole bill

That brings us to the cache-read line is the whole bill. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

Where this leaves us

If there is one thing worth taking away, it is that the expensive decisions are the ones made implicitly. Making them on purpose costs an afternoon.

If you are working through the same problem and want to compare notes, the docs cover the mechanics and the console shows the behaviour on your own data.

Everything here, already built

Sign-in, enterprise SSO, directory provisioning, roles and an audit trail behind one API. Start with the quickstart and have a working sign-in this afternoon.

Start selling to enterprise customers

Create an account, point sign-in at Paycux, and get back to the part of the product that is actually yours.