Claude Code projects hands-on: coordinator updates fixable via prompt, no auto-approve mode yet
soumitrashukla9 · x · 2026-10-03
- Developer kr0der tested Claude Code projects (multi-thread orchestration, currently in beta) and found it promising despite three issues:
- The coordinator is good at dispatching tasks but rarely receives updates from threads, so it seldom reports progress or blockers. Key fix: explicitly instruct the coordinator to give more updates and flag blockers — works much better afterward.
- Threads keep pausing for approval, with no way found to enable auto mode or bypass permissions.
- Threads can't use computer use.
Overall positive after the coordinator fix; author is excited for the feature's evolution.
More from coding & agent
- Dev benchmark by experience: Sonnet 5.5 runs faster than Codex and burns less of the weekly limit — burkov · 2026-10-03
- OpenAI DevDay notes: 4 key levers to cut costs and boost agent performance — omarsar0 · 2026-10-03
- GitHub Copilot CLI v1.0.92-3 adds Ctrl+E picker to switch local and cloud runs — copilot-cli-release-app[bot] · 2026-10-03
- PhD-turned-founder: LLMs flipped which criteria kill programming tool startups — jimmykoppel · 2026-10-03
- Qwen Code v0.24.7 nightly adds local workspace-agent collaboration — qwen-code-ci-bot · 2026-10-03
- Veteran engineer: AI coding now beats humans on quality, not just speed — facontidavide · 2026-10-03