9.6 Coding Agents¶

The archetype every reader runs, read through this reference's own patterns, plus the operating playbook: the instructions file, hooks and permissions, plans, tests, and the injection risk that comes with repo write access.

Also called: coding agents, CLI agents, agentic coding, AI pair programmers.

Stub: scaffolding, not finished writing · planned for a later release. The skeleton below shows the beats this chapter will hit. Contributions welcome.

Why you'd reach for it¶

The problem, what breaks without it, and when you need it. To be written.

What it actually is¶

A crisp definition, the maturity call argued with cited evidence, and how it differs from its neighbours. To be written.

How to do it¶

The mechanics, with public tools named plainly where the reader can verify them; code only where a tested listing earns its place. To be written.

Gotchas¶

The real costs and when not to, feeding the Anti-Patterns Catalog. To be written.

In short¶

A weighted recommendation: what you would actually do. To be written.

Maturity: Standard (as a category) (the most-used agent shape of 2026; the practices around it are still forming) · Grounding: research · Last reviewed: 2026-08

Sources¶

Citations added as the chapter is written. Every non-obvious claim gets a footnote.