Its easy when you spawn a couple of subagents in a homelab with a rack with 5+ servers.

This is how one of my claude code session looks like right now, one prompt from yesterday:

  ◯ lean-tracks  ▰▰▰▰▰▰▰▰▰▰▰▱▱▱▱▱▱▱▱▱  7/12 · 18h35m · ↓ 3.1m tokens
  ◯ lean-tracks  ▰▰▰▰▰▰▰▰▰▰▰▰▱▱▱▱▱▱▱▱  6/10 · 17h47m · ↓ 2.6m tokens
  ◯ lean-tracks  ▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱  0/1 · 4h49m · ↓ 275.9k tokens
  ◯ lean-tracks  ▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱  0/1 · 4h30m · ↓ 395.0k tokens
 ◯ lean-tracks  ▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱▱  0/1 · 3h50m · ↓ 490.3k tokens

▲ imdsm an hour ago | parent | next [-]

Not sure if this will help you but it helped me. I was using subagents and workflows for lots of long running tasks, and part of that work included running tests. If tests took longer than 5 minutes, the cache expired, and the whole thing was then being processed as uncached input.

I created a skill to better manage agents, including a way to keep the caches valid, and it has decreased my usage considerably. I now struggle to use my 100% each week and I hit claude hard. I have a reset expiring in 5 days and I'm trying to burn down the tokens (68% with 3d 8h left) quickly so I can use my reset before it expires.

Token efficiency just means understanding the way the system works. Best person to help with that... my old friend claude.

▲

wolfy1993 2 minutes ago | parent | next [-]

Don't suppose you would be happy to share the skill? Or is it fairly unique to your work flow?

I think the tests problem is really having an impact for me. Hadn't considered it before so thanks for flagging.

▲

dotancohen 8 minutes ago | parent | prev | next [-]

After I stopped letting Claude run tests, my token usage went from "gone by Wednesday" to "what can I automate this Saturday so my tokens won't go to waste".

▲

iamflimflam1 39 minutes ago | parent | prev | next [-]

Some to think about with both Claude and skills.

Can you invert things. What’s deterministic and what needs “thinking”?

Can you create a script that runs things chaining together the deterministic parts with calling out to Claude for glue that needs “thinking”.

▲

olavgg an hour ago | parent | prev | next [-]

Yeah, I should see if I can create a similar skill. The tests do spend some time to complete.

Claude: Confirmed: 195M of the 212M cache tokens (92%) come from full re-writes after 5+ minute gaps, accounting for 77% of relative cost. Now I'll check the existing wrappers so the skill builds on them.

▲

oblio 11 minutes ago | parent | prev | next [-]

> my old friend claude.

Awfully new old friend.

	▲	dotancohen 7 minutes ago \| parent [-]
		Google is the ex, Altavista is the high school sweetheart who tragically passed at a young age.

▲

raylad an hour ago | parent | prev | next [-]

How do you keep the caches valid?

	▲	entrope 20 minutes ago \| parent \| next [-]
		Not OP, but I typically ask it to report status of whatever is running; it can run a background task that reports to it every N minutes. With Claude Code in VS Code and a Pro subscription, it seems like the one-hour cache is the default, making it an issue less often.
	▲	j45 41 minutes ago \| parent \| prev [-]
		Ask Claude, it's pretty wild to see.

▲

nextaccountic 28 minutes ago | parent | prev [-]

> including a way to keep the caches valid

Maybe doing bogus small requests to prevent the cache from expiring?

I mean in the API you can set the cache expiration time right? But I guess claude code can't do this

▲ devtor 18 minutes ago | parent | prev | next [-]

As a dev who hasn't used LLMs as an embedded part of their work, and uncertain about it all, i'd be curious to know:

- How long do you reckon it would take a human to do the task?

- What percentage of features/ feature-extensions you add would have been done at all if you didn't have agentic assistance? Is there a tension between llm productivity gains and 'because we can' feature additions?

- Are many of the tasks for throwaway v1 features, exploratory tries?

- How speced out is the work you give it, eg did this task have pages of specs, how long did the spec take to write?

- How deeply will you manually review the work and how much time will it take? Will you read all the code / review at a high level and interrogate with llm / have the llm review and self iterate?

▲ olavgg an hour ago | parent | prev [-]

[flagged]