Field notes · coding agents in daily use

The Agent Field Guide

Coding agents are easy to demo and hard to rely on. The gap between the two is where this site lives: what holds up under daily use, what quietly does not, and how to tell the difference before it reaches production.

Three kinds of thing here:

  1. A long-form guide to one agent and more to come in the future.
  2. Research where the workings are shown rather than summarised.
  3. The small tools that keep an agent’s blast radius smaller than your machine.

Start with the Claude Code guide Read the research

01 · Guides

Long-form, one agent at a time

A guide earns its length by being specific to one tool and one version, which is also why each one gets its own section instead of crowding this page.

  1. Free · 29 chapters The Claude Code Field Guide How to give Claude Code context worth having, when to let it run, when to stop it, and how to catch the confident mistakes before they ship. Six parts, five appendices, verified against a named version so you can judge how stale it is.

One guide today. The next agent gets a section of its own here rather than a rewrite of this page.

04 · Provenance

How this is written

Everything here is checked before it ships, and the checking is the interesting part. An earlier edition of the guide drifted far enough in four months that three of its examples were broken as printed — hook scripts that blocked silently, permissions examples that were inert config, and a gate the text promised would stop a write and which never fired.

So each guide names the version it was verified against, each report carries the data behind its numbers, and each tool is public so you can read what it actually does rather than trust a description of it.

Agents ship roughly weekly. If anything here disagrees with your terminal, believe your terminal.