# Claude Code Is a Chainsaw

> Source: <https://mechanicalsurvival.com/blog/claude-code-is-a-chainsaw/>
> Published: 2026-06-15 14:23:17+00:00

# Claude Code is a chainsaw

*
*

*“Wood, chainsaw, tree” by pb826 on Pixabay*

I first picked up a chainsaw two summers ago.

I was staying with a friend at his farm on Dartmoor. We spent a drizzly afternoon splitting logs with a hatchet, clunking and thunking our way through the pile until the time came to carve up a bigger section. He said “I’ll tell you what”, grinned, disappeared into an outbuilding and came back brandishing a green and white chainsaw with a long black blade. Battery-powered, unfortunately.

To use it, he showed me, you first flip up the guard then gun it in the log’s direction, cutting the air before the wood. Once it bites, the course is set and your arms must keep it moving.

More than once I got stuck because I underestimated the force required. I had expected the work to become suddenly trivial, but the system of cutting, for all the chainsaw’s speed, was not fundamentally different from how it had been with the hatchet. It was still knotty fibres and fast-moving steel. Except now with chewing rather than slicing, some extra danger, and different muscles required.

I recognised this feeling when I recently took up Claude Code Max to do business-critical work with it.

## Cutting

Claude Code Max is a chainsaw.

I’ve used Claude Code’s Pro tier before, so I have an idea of what I’m doing. I took time to flip the guard up, so to speak: I gave it a grounding in my preferred architectural patterns and a strict testing regime. I then got it to proceed on my domain, one user story at a time.

The real chainsaw did better the faster you could get it to cut. And as I made my first fast, confident cuts with Claude I marvelled at how it ate tirelessly and tastefully through every task I threw at it. But in Claude’s case too, I found new muscles were required.

One way of going wrong is like getting the saw stuck. Claude Code eats and eats until it finds a knot (really, some problem that it can’t deal with) and the knot just will not yield. But the blade still mindlessly turns, blunting itself as the context window (and the codebase) fills with rubbish.

What happens after I stop cutting is also new, but more interesting. Here the risk is not so much stopping progress as the whole piece of work falling apart. In the wake of Claude’s chainsaw there’s sloppy microcopy, UI jank, and various kinds of subtle incoherence—a security vulnerability here, an oddity in the data model there—that can undermine the whole product.

Unfinished work is now my enemy, and it accumulates very quickly under the blade. My instinct is to take very deliberate cuts, usually user-story-sized, and force myself to put down the chainsaw to finish each one properly.

## Finishing

Finishing is not “reviewing the AI’s work”. That’s a cliché that treats AI like a person, and the activity as no more than a stage-gate.

But finishing isn’t checking. It’s wielding the sander; it’s its own discipline. It’s realising that the user management screen you’ve just sawed contains a bizarre assumption about what non-admins will see and then having to redesign it there and then because all the new curves in your product were made by a tool that just wanted to go in a straight line.

When finishing, I rarely begin with code. Revisiting Claude’s first rugged cuts, I actually use the software itself. This is strange to me—in the past I’d know it inside out by the time I completed a piece of work. I have to learn it anew through each change. I explore the design, code structure, and every other small aspect of the system that falls under the scope of the story I’m working on.

Then I return again and again to the tool to make ever-smaller changes. When it’s smooth, I start again.

This takes time, but if I skip these finishing phases I feel like I’m losing my grip: scope continually expands just beyond reach, and the fear of something going wrong never leaves me.

## Life and limb

When the chainsaw gets out of control, kinetic and spectacular injuries ensue.

The faster and further I cut the faster I must decide and the more decisions I make. I can easily rack up more than I can finish before I must cut again to keep moving. That cost compounds in technical debt: less splatter, but no less lethal.

Holding the nerve to keep stopping and stopping when the tool just wants to eat is hard. And I don’t like that much of the time it’s just me and the single-minded agent. Working one-to-one with it feels like a lot of responsibility for me as individual, and somewhat disrespectful of its seductive power.

So I find myself wanting other people physically beside me at the console to bring alternative perspectives and keep us honest. I crave, I think, multidisciplinary mob programming? With only one chainsaw in operation at a time.
