If you're building with Claude Code, set it up like this. Same session, staffed properly.
Two lines first:
model = Opus 5.5
advisor = Fable 5.2
Then hand the session this:
Opus 5.5 holds the main thread and writes the code. Everything read-only goes to Haiku 5.5: one subagent maps the repo, one hunts call sites, one runs the suite and reports failures only. Fable 5.2 sits outside the loop as advisor and reads the transcript when called. JEV takes the fast deterministic forks (tool choice, path selection, retries).
Rebuild my setup around that tree:
1. Main session on Opus 5.5, Fable 5.2 as advisor.
2. Three read-only Haiku 5.5 subagents: search (repo map), grep (call sites), test-runner (suite, failures only).
3. One line in CLAUDE.md: call the advisor before a plan locks, after the same error twice, and before a task is marked done.
4. JEV owns the micro-forks.
Diff before any edit. Nothing changes until I say go.
Then check it took: subagents editing files, an advisor that only shows up after the code is written, or JEV missing from the log all mean the tree didn't load.
1
1
70
Replying to @RyanKnuppel @X
Respect! I'm building FounderPing - it lets you meet your users right in your app, lower your churn rate, turn visitor into your user etc.
1
3
Replying to @onchainnotes_ @X
Are you trying to figure out this of your own? I mean, not using coding agent?🤨
4
Replying to @onchainnotes_ @X
Hey, connected from my end! Mainly I'm on JavaScript related like nextJS or typescript
1
14
Replying to @JeromeJob1 @X
Thanks! I'm building FounderPing - it lets you meet your users right in your app, lower your churn rate, turn vistor into your user etc. How about you?
9
I dk why people keep posting game videos to show capabilities of a new model.
Isn't it too off from real developing work? Don't we have a more intuitive way to test Astra or Sol?
1
41
Replying to @StevenHWhite
Thanks and followed! I'm building FounderPing - it lets you meet your users right in your app, lower your churn rate, turn vistor into your user etc.
1
13
Replying to @tiennguyen1403
But do you find openai model doing lots of denfensive coding? And sometimes I need extra 50% energy to understand the words codex say, compared to claude ...
1
1
23
Guys I am looking for your AI subscription suggestions, seriously. Plan to start my first paid plan.
Except Claude(obviously it is the best currently), which is the 2nd you would recommend?
2
2
125
