Workflow tip: use Astra for specs, Luna Max thinking for execution to save quota
dinowxyz · x · 2026-09-17
Sharing a two-chat workflow for tight AI coding quotas: have Astra design the spec and implementation plan (as a .md), explicitly framing the executor as a junior dev who tends to go off-rails so the plan stays precise; then in a separate chat, run Luna at Max thinking to walk through and execute the plan.
Related event: Multi-Agent Workflows Slash AI Coding Quota Costs(3 posts)→
More from coding & agent
- BotBell MCP lets AI assistants push notifications to iPhone and Mac — modelcontextprotocol · 2026-09-17
- Hüttentouren MCP adds live hut-to-hut hiking availability in the Alps — modelcontextprotocol · 2026-09-17
- Typesafe early access: AI co-op partner built in 1 hour, 10 min of play cost $0.02 — nptacek · 2026-09-17
- Read-only POS agent retro: near-zero Gemini cache hits, HITL writes on hold — RedaHaloubi · 2026-09-17
- Dev argues long-horizon RL task-building is a fresh career edge for students — himanshustwts · 2026-09-17
- Claude Code + Unreal MCP built a Souls-like boss fight in 72 hours — Delicious-Shower8401 · 2026-09-17