Astra plans, Sol 6.1 codes: dual-agent oversight beats subagents
steipete · x · 2026-10-21
steipete shares a multi-agent coding workflow: Astra does planning and drives Codex CLI inside git worktrees, Sol 6.1 writes the code, and a second agent supervises and challenges Astra — like /goal but with an independent challenger instead of the same agent reviewing a text file. He shipped an OC-plugin for this 'smart goal' pattern. Human review found only tiny UX regressions like button shapes; 'technical debt can now be counted in tokens.'
More from coding & agent
- Research agent Épi sets 120 records, narrows n-queens constant interval 84x — dair_ai · 2026-10-21
- Compaction hooks in practice: keep last n messages verbatim, summarize the rest for full agent continuity — MoonL88537 · 2026-10-21
- The blank prompt box hides real operational burden: context, workflow and supervision fall on users — _AustinCalvert_ · 2026-10-21
- DeepMind paper: self-evolving agents forget as they learn — fastest learner GEPA also breaks old tasks most — rohanpaul_ai · 2026-10-21
- arXiv: Are Self-Evolving Agents Continual Learners? Plasticity comes at the cost of stability — rohanpaul_ai · 2026-10-21
- PM OS vs Team OS vs Company OS: how to layer your AI setup and which to build first — aakashgupta · 2026-10-21