System prompts beat user prompts: taming verbose Claude Opus 5
IndyDevDan · youtube · 2026-08-17
IndyDevDan argues Claude Opus 5 is one of the best models ever but one of the worst to talk to — verbose, stuffed with filler, torching output tokens. His fix isn't a new model but prompt engineering, focused on the system prompt rather than user prompts.
Key techniques:
- Positive + negative patterns: state exactly what to replicate and what to avoid (no "load bearing", em-dash chains)
- Reference points: D1/R1/F1-style codes build a shared shorthand and cut repeated tokens
- Hard operational boundaries: deliver only what was requested — no scope creep or surprise refactors
- Aliases: SCR/ELI/FOC micro-skills that expand into full instructions on demand
- In-context distillation: real do/don't examples to lock in communication patterns
The system prompt applies across every exchange, making it the highest-leverage place to control verbosity, cost and quality regardless of which SOTA model ships next. The fix repo is open on GitHub.
More from coding & agent
- Using LLMs to Auto-Fill Forms and Streamline Onboarding — threepointone · 2026-08-17
- Build a Listener Agent with Claude Code for Audience Insights and Competitor Analysis — EXM7777 · 2026-08-17
- How to Decide What to Use Grok Bot For: Core Agent Workflows Explained — alex_verem · 2026-08-17
- Built a Deepgram Flux voice testing studio in 30 minutes with Claude Code — CodeByPoonam · 2026-08-17
- Google's A2A Protocol Joins AAIF to Standardize Cross-Framework Agent Communication — iamKierraD · 2026-08-17
- Zapier report: Automation reduces AI costs by up to 90% in workflows — TawohAwa · 2026-08-17