Claude Opus 5 works better after an agent workflow is stripped back
thedealdirector · x · 2026-07-26
A reaction to the Claude Opus 5 launch says the model is hard to love at first: it argued with instructions, stopped before finishing work, and did not fit existing skills and plugins well in an internal agent workflow.
The author says things changed after deleting the workflow stack and starting over from scratch:
- Opus 5 got much better without the old layers of skills and plugins.
- It showed flashes of brilliance in coding, writing, and knowledge-work tasks.
- Their first impression was negative, but the model seemed to prefer a cleaner setup.
The takeaway is less about raw benchmark strength and more about how much agent performance depends on the surrounding workflow.
Related event: Claude Opus 5 Tests: Unlocking Monster Potential via Multi-Agent Workflows(10 posts)→
More from coding & agent
- Ben Bajarin: Frontier AI is becoming the enterprise cyber-defense stack — BenBajarin · 2026-10-26
- Building AI bots on raw APIs? Devs say models are 'dumb without the harness' — madeofAjala · 2026-10-26
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Microsoft demos intent-classifying agents built with Copilot App and Foundry, deployable across Teams and Outlook — marlene_zw · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26
- The identity crisis in software engineering: multiagent systems demand a new problem set — rakyll · 2026-10-26