Harness engineering setup for Opus 5.5: model tiering, context hygiene and progress files that persist
Arindam_1729 · x · 2026-10-24
A practical harness engineering setup for Claude Code with Opus 5.5: control effort via /effort medium (high only for deep reasoning/verification); tier models — Opus for complex implementation, Haiku for lookups returning evidence with file paths; practice context hygiene (keep CLAUDE.md short, load skills on demand, compact tool output, full logs on disk); and persist progress via featurelist.json and claude-progress.txt. The companion article details a 5-layer shared-memory setup across Claude Code, Codex, Cursor and OpenCode.
More from coding & agent
- Lee Rob's 45-minute masterclass explains how always-on AI agents work — Saboo_Shubham_ · 2026-10-24
- Prompt engineering is 'dead', long live prompt engineering: a cyclist-recipe prompt shows the craft persists — chrisalbon · 2026-10-24
- Few-shot prompting trick: turn examples into a list the system completes — mmitchell_ai · 2026-10-24
- Rewriting the world in Rust: nearly 1T tokens and 50k+ commits per month — doodlestein · 2026-10-24
- NeurIPS paper OAT: attribute agent failures by learning only from success flows — SharonYixuanLi · 2026-10-24
- Claude writes its own parallel-agent prompt and nails the brief, screenshot goes viral — hewarsaber · 2026-10-24