When To Use Claude
Opus 5 vs Fable 5

CLAUDE MODEL CHEAT SHEET, which one to open THE ONE RULE: don't pick the "best" model, pick the right one for the job. Capability costs money, so match it to the stakes. FABLE 5, the deep thinker ($10 / $50 per million tokens). Reach for it when the problem is genuinely hard, the reasoning is long, or the decision is high-stakes and you'd want your smartest advisor in the room. Strategy, tough analysis, gnarly code, research you can't afford to get wrong. OPUS 5, the workhorse ($5 / $25, the same price as Opus 4.8). Reach for it when you're producing real work day to day: coding, research, spreadsheets, writing across documents, running agents. It gets you close to Fable-level quality at half the price, and it's the one I keep open by default. SONNET 5, the fast, cheap one ($3 / $15). Reach for it when you're doing high-volume or repetitive work where speed and cost matter more than peak brainpower. Great for drafting, quick edits, and running lots of tasks. HAIKU 4.5, the speed demon ($1 / $5). Reach for it when the task is simple and you want it instant and cheap: quick lookups, sorting, tidying text. (Yes, it's still 4.5, there is no Haiku 5.) MY DEFAULT SETUP: - Live in Opus 5 for almost everything. - Escalate to Fable 5 the moment I'm stuck, the stakes are high, or the first answer isn't good enough. - Drop to Sonnet 5 or Haiku 4.5 for bulk, boring, or speed-critical work. HONEST NOTE: "Fable decides, Opus executes" is my shortcut, but both models can reason AND do the work. The real choice is top capability (Fable) versus best value (Opus). When in doubt, start on Opus 5 and only pay up for Fable when the problem earns it.

MY FAVORITE CLAUDE HACKS 1. ASK FOR 3 OPTIONS. End any request with "give me three versions: safe, bold, and weird." You go from one flat answer to a real range in one shot. 2. MAKE IT INTERVIEW YOU. "Before you answer, ask me the 5 questions you most need answered to do this well." Claude gathers context instead of guessing. 3. SHOW IT A GOLD STANDARD. Paste an example of great work and say "match this quality and format." Claude copies excellence far better than it follows adjectives. 4. TELL IT WHO TO BE. "You are a [specific expert] with 20 years of experience in [niche]." A specific role pulls a sharper answer than a blank prompt. 5. SLOW IT DOWN. "Think through this step by step before you answer." For anything with logic or numbers, this alone lifts the quality. 6. RUN A RED TEAM. "Try to prove me wrong. Where does this fall apart?" Turns Claude from a cheerleader into a pressure-tester. 7. USE PROJECTS FOR ANYTHING YOU REPEAT. Put your context, rules, and examples in a Claude Project once, and every chat inside it already knows your world. 8. BUILD A SKILL FOR ANY REPEATED TASK. If you explain the same process twice, turn it into a Skill so you never explain it again. 9. LET IT SEE. Paste a screenshot and ask "what's off here?" Claude reads design, dashboards, and error messages straight from an image. 10. KEEP A MEMORY FILE. Keep a running note of how you work and your preferences, and paste it at the top of big tasks so Claude sounds like you, not like a stranger. WHICH MODEL FOR THESE: run the everyday hacks on Opus 5, escalate the hard ones to Fable 5.