Claude Code Effort Levels

2026-09-27T17:41:28.64279+13:00

This is a nice dive into effort levels. It is specific to Claude Code and Opus 5.5 and Fable 5.1, but it should loosely generalise to other models too.

WHAT IS EFFORT?

At a high level, effort gives the model an approximation of how much compute you want it to spend on the task. It’s somewhat related to your modeling of the difficulty of the task.

Think of it this way, if someone asked you to do something in 12 hours straight, you might assume they just want you to do it and try very hard. If someone asked you to do the same task in 1 hour, you’d try to get them the best version that meets their task and then expect to iterate from there.

Or, you might push back and say the task requires at least 3 hours and then work for 3 hours to deliver it.

You should think of effort in the same way. Claude will always try and do your task reasonably, but higher effort will involve Claude taking more independent action for judgement and verification.

Thariq also dives into several examples, things he built, with visual examples, and also comparing how Claude performed against different tasks in the Terminal-Bench 3.0, a community-sourced benchmark using different effort levels.

Most of this seems intuitive: higher effort levels think more and solve problems better where lower effort offers lower quality output most of the time, more so on more complex tasks. But is context dependent and not always true.

One example stood out to me is that with tasks that are very well specified, performance didn’t differ that much across the different effort levels. Let’s say there is a clear spec for a large feature, if it’s well defined, using a low effort level will run a lot faster and likely still do a really good job compared to higher effort levels as less assumptions need to be made and less edge cases thought of, as the spec should cover these already. So low effort level could be a good workhorse, then use a higher effort level for adversarial and security reviews.

For regular software engineering, particularly new feature work, the effort level depends a lot on how in the loop I want to be. Low effort allows Claude to respond quickly with a starting point, higher effort levels will get more work done but Claude will also make more assumptions on my behalf.

A particularly fruitful loop for feature development I’ve been using is:

Give Claude a spec and ask it to interview me about any details I’m missing

Implement it on low effort

Review to make sure it got the gist of it correct, iterate on low effort as needed

Verify and test on high effort

Some of this is probably somewhat subjective and will vary wildly depending on context and complexity of tasks. But definitely worth more experimentation with these latest models to get a good feel for how to best utilise effort levels.

I can be a little lazy with this at times, if I have the quota available I tend to just use higher effort levels and the strongest model, usually high or xhigh for most tasks. I say lazy, but really it’s about just wanting the highest quality output first time, especially for high stakes software. I do like the idea of being able to use low effort for a much faster build with a well defined task to speed up build time, and then review and verify with say xhigh.

Claude Code Finally Supports AGENTS.md

2026-09-19T13:37:06.292896+12:00

Claude Code Finally Supports AGENTS.md

AGENTS.md has been the industry standard for a while now, to provide context and memory to every agent session in a particular folder. Anthropic have long held out supporting the standard in preference for their own CLAUDE.md.

From today they support the standard.

People have been losing their minds for a while about this. I never quite got why though. I’ve always just had both files in my repos and just added @AGENTS.md in the CLAUDE.md file, with nothing else, so there was never any duplication. This has always worked a well with no issues.

Guess we can just switch to AGENTS.md now and have one less file in the repo.

Loosely Coupled Thoughts — tagged thariq-shihipar

Claude Code Effort Levels

Claude Code Finally Supports AGENTS.md