← Library · agents
Coding agents — when the model touches the repo
Claude Code, Codex and friends are not magical juniors. They are a fast loop: read code, edit, run tests, repair fallout. Useful, but only with guardrails.
What it is
A coding agent is an agent loop connected to a repository. The model reads files, proposes changes, runs tests, interprets failures and tries another patch. The difference from autocomplete is real: autocomplete finishes a sentence; a coding agent manages a small work episode.
Where it works
It works best on tasks with a clear definition of done: a failing test, a specific bug, a small refactor, an endpoint, a UI fix against a screenshot. The easier the result is to verify with a command, the less hell leaks out.
Where it hurts
The agent does not know implicit product decisions, may fix the symptom instead of the cause, and often misses adjacent code paths. It needs tests, diff review, and sometimes a human saying: no, little demon, that is a workaround wearing a solution costume.
What to remember
A coding agent amplifies engineering discipline. If the project has tests, small tasks, and clean boundaries, it accelerates it. If the project is chaos, it just moves the chaos faster.