Claude Opus 5 works well for coding, but it breaks Compound Engineering workflows
danshipper · x · 2026-07-25
The thread says Claude Opus 5 is useful at a medium-effort coding level, but it also breaks existing agent workflows such as Compound Engineering.
What changed in practice:
- The model works well when people stop relying on heavy skills and giant prompts.
- In an autonomous flow, it repeatedly returns control to the user, which the author finds annoying.
- The team started rewriting Compound Engineering to fit the new model behavior.
- The author also shared a custom skill for retuning their harness/plugin.
So the takeaway is not just that Opus 5 is stronger, but that agent stacks may need to be redesigned around its behavior.
Related event: Claude Opus 5 Excels at Coding but Disrupts Autonomous Workflows(2 posts)→
More from coding & agent
- Study finds async AI coding agents drive far bigger output gains than autocomplete — NathanpmYoung · 2026-07-25
- Open-weight coding-agent router hits 79.8% on Terminal-Bench 2.1 for $76 — kimmonismus · 2026-07-25
- Pokee says its sandbox can connect agents to hundreds of everyday tools — Kyrannio · 2026-07-25
- AI coding tool screenshots a WSL compatibility check, not a feature launch — zeeg · 2026-07-25
- Manning’s new AI codebase book teaches 10 mental models for reading unfamiliar repos — ZacharyHuang12 · 2026-07-25
- drskill adds trace-based auditing for agent loadouts, skills, and MCP triggers — dbreunig · 2026-07-25