Lately I'm trying a variation on this: Have the main agent make a phased implementation plan, then for each phase, have it start an implementation subagent with a focused prompt, then review that agent's work in the main session. The theory being that the main session still contains all the research, but it can review just the diff rather than have the entire implementation session in context as well.

The post doesn't include a review in the cost comparison, but I find that immediately doing a review catches lots of mistakes.

▲

sgc 14 hours ago | parent | next [-]

Actually it does include an important level of review. They say "init a TODO list with a validation step for each item", and then the last several sections of the execution are within the TODO - where it is validating the code.

To me that was the heart of the article and of what they did - create a self-validating todo list that deterministically forces the agents to stay on task, and then trim out just the right extraneous context (the actual planning) without messing with the read-file context which is where they found subagents burning most of their tokens.

Just a few days ago I was speculating about forking context to implement instead of spawning subagents here on hn. This is similar to that just several more steps more sophisticated. You could even fork the trimmed context here for very large tasks.

	▲	wrs 24 minutes ago \| parent [-]
		It wasn’t clear to me (and still isn’t, after slogging through the inhuman article again) that the verification here is done by a separate agent from the implementation. That’s a second trimming step, but in reverse: at that point you want the new code in the context, but not the implementation reasoning.

▲

bensyverson 13 hours ago | parent | prev | next [-]

Yes, this is a core part of my workflow; use the smartest model (e.g. Fable) to generate a large hierarchical implementation plan, then clear the context and have a lesser model (e.g. Sonnet) track and execute the plan [0], often in parallel.

It all depends on how much work you're doing; if it's a simple task, there's virtually no need for plans at all; just have the smart agent do it. But if the work is going to take 5, 10 or 100 sessions, there's real value in the "smart agent plans, cheap agent executes" model.

[0]: https://github.com/bensyverson/jobs

▲

wrs 21 minutes ago | parent | next [-]

My main point was not about the implementation stage, but the verification stage. Letting the smarter agent verify the work of the cheap agent finds a lot of little oversights and sloppiness that I used to have to find myself. So I’d be interested in that cost comparison.

▲

ricardobeat 12 hours ago | parent | prev [-]

This is exactly what the post argues against though, as it leads to higher overall cost.

▲

bensyverson 5 hours ago | parent [-]

Yes, and I'm arguing that the post is over-simplifying. As I mention, for small plans, it's probably easier to have the big model just do it. But for large, multi-session plans, it's cheaper to let smaller models execute the bulk of the work.

	▲	markust 2 hours ago \| parent [-]
		Perhaps, there's a small change that might work better here - if we use a different agent (by creating custom agents) for plan and implementation, then the switch to the implementation agent wouldn't end up re-reading a lot as the new agent would have fresh empty context. I implemented this[1] from one of the posters on HN and I think it'd work well with this problem too. Would be great if you could point out if my understanding is wrong. [1]: https://www.stavros.io/posts/how-i-write-software-with-llms/

▲

pqdbr 16 hours ago | parent | prev [-]

I’m using Claude code dynamic workflow like this. I tell Fable to use a workflow. He is the planner, orchestrator and reviewer. Opus agents are implementers. Works unbelievably well.

▲

tern 4 hours ago | parent | next [-]

I do the same, but delegate to codex instead via the /smux skill. It's expensive, but I get one long-running Claude context window and one frequently compacting codex, and this saves me from needing to re-gather context all the time.

Per the OP's technique, I'll use Fable for intensive planning moments, then switch back to opus when things are going well.

▲

oliver236 10 hours ago | parent | prev | next [-]

can you explain this in a bit more detail? super interested

▲

danielciocirlan 15 hours ago | parent | prev [-]

“He”

	▲	brabel 7 hours ago \| parent \| next [-]
		In many languages that’s the only way to express that since there is no “it”. It doesn’t mean speakers of such languages anthropofy everything and I think that’s the case here.
	▲	llbbdd 14 hours ago \| parent \| prev [-]
		I call him "my son"