conon.ai

conon.ai/Tips

Match The Model To The Chore

Limits are shared, so burning the flagship model on renaming files is how you hit the 5-hour wall by lunch. Live on the workhorse model; switch up consciously for architecture, gnarly bugs, and review — or use opus-plan mode: expensive model plans, cheap model executes, switching itself.

IntermediateWORKFLOWClaude Code

Why it works

Your plan's limits are shared across every model, and the 5-hour window on Pro is unforgiving: burn the flagship model renaming files at breakfast and you're locked out by lunch. Matching model to chore is the entire game — the workhorse for routine, the heavyweight summoned deliberately, and opus-plan mode when you want the split handled for you.

How to do it

  1. Open the model picker next to the prompt field; learn what's in it once.
  2. Default to the fast workhorse (Sonnet-class) for edits, texts, and routine builds.
  3. Escalate deliberately for architecture, stubborn bugs, and final review — then come back down.
  4. Or ask for opus-plan mode: the expensive model plans, the cheap one executes, switching itself.
  5. Watch the usage ring by the prompt field like a fuel gauge; /usage gives the detailed view.
  6. Near the limit? Downshift the model and tighten prompts instead of stopping work.

Copy this

prompt
Switch to opus plan mode for this task: plan with the strong model, execute with the fast one.

What to watch for

  • 'Always use the best model' is how you rent a surgeon to peel potatoes — capability is wasted on tasks below its floor, and the bill arrives at 2pm as a locked session.
  • Chasing model-of-the-week names is noise; the picker always has a workhorse and a heavyweight, whatever they're called this quarter.

Sources

Original: conon.ai

Read next

Make It Review Its Own Diff
'Done' is a claim, not a fact. Before accepting changes say: 'check these changes before I accept — look for real errors, not formatting'. The agent regularly finds its own bugs, and the closing phrase stops it nitpicking commas instead of logic.
Claude Code
Show A Screenshot, Skip Adjectives
Words like 'modern and minimalist' mean nothing — every ugly site's brief said that. Saw a style you like? Screenshot it into the prompt with 'in this spirit'. A picture transfers taste that three paragraphs of adjectives never will.
Claude Code
Explanatory Style For Month One
Ask for the explanatory output style and the agent narrates why it chose what it chose as it works — the black box becomes a running commentary. When the explanations start to annoy you, that's your graduation signal: switch back to default.
Claude Code
More Effort, Or A Bigger Model?
Bad result? Diagnose before you rage-quit to another tool. Skipped files, no self-check, quit halfway — that's low effort: raise the effort level. Read everything and still confidently wrong — that's the model's ceiling: escalate the model. This one question settles 95% of 'the AI got dumber' complaints.
Claude Code

We build and operate the systems behind tips like this one — agents, automations and internal tools, shipped into production. See what the studio does →