Comment by cronin101
17 hours ago
Anecdotally, in the Opus 4.6 days, it felt like there was something special about using plan mode to discover the approach then clearing the context to execute on it.
A mixture of defending against a disastrous mid-implementation compaction (where suddenly things would veer off the rails) and also allowing the fresh execution to double-check the assumptions and notice any subtle mistakes before context was poisoned.
I’ve found that for large enough changes I still prefer having a parent theorizing about the root cause of issues based on evidence and then dispatching targeted child sessions to fixed based on theories and concrete telemetry examples.
There’s something clean about having sandboxed context and a session you can quiz about architecture while one is heads-down working against a spec.
For me, it was the agent that decided about plan mode, when that happened. Most of the time I didn't invoke it but kept discussing and tweaking and if the context was close to full, make it dump it out to disk and start a new session. I felt like that worked more flexibly for me because I could keep steering and adjusting until it was what I wanted. At that point I made it write a detailed spec. Like my homegrown plan mode.
The "standard" plan mode felt too stifling.