⬢github · 31 ★ · pushed 3 d ago · MIT
rlshaw-ml/BlastLoop
Structure-first operating process for AI coding agents: Blast / Mid / Inner build altitudes with clear ownership, then T1 structural, T2 bug/ops, T3 adversarial quality gates.
BlastLoop is a process framework for working with AI coding agents. It defines three coding 'altitudes' — Blast (system structure), Mid (subsystems), Inner (local changes) — and requires changes to pass three ordered review gates: T1 structural, T2 bug/ops, and T3 adversarial. It ships as prompt files (AGENTS.md plus per-altitude and per-gate prompts) you clone into your repo.
Why now: It was just launched on Hacker News as a Show HN (v1.0.0), riding current interest in structured methods for governing AI coding agents.
Who it is for: Engineering teams using AI coding agents who want an explicit ownership and review process around generated code.
ai-agentsai-governanceai-transformationblastloopcoding-agentsllmmitprocess-improvementpromptingquality-assurance
Stars over our 42 snapshots: 31 to 31, since 10 h ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/rlshaw-ml/BlastLoop