BlastLoop: structure-first altitudes + T1/T2/T3 gates for coding agents
At a glance
Open method: Blast/Mid/Inner write at system/subsystem/local altitude, then fixed T1 structural → T2 bug/ops → T3 adversarial gates with handoff packets—agents get AGENTS.md + prompt files, not a vague “please be careful.” This workflow is listed under learnable-paradigm, coding-agents, quality-gates, workflows, ops.
AWS Labs open-source (5k+★): one harness-neutral core turns Claude Code/Codex/Cursor/Copilot/Kiro/opencode into structured, verifiable delivery workflows via `aidlc config --harness` + doctor—install script, not a new agent.
RAX (Robot Agent eXploration) lets a frozen LLM coding agent drive real robots via APIs, explore online, and compile successful perception–planning–control loops into reusable programs—no teleop demos or policy training; +37.4% avg vs baselines in sim; open skill libraries per embodiment.
Empirical study: 34% of popular active repos ship agent instruction files (AGENTS.md dominant); half exceed ~100 lines; ~3/5 rules could be script-checked but <1/20 name the check—actionable lint: short map, name enforcers, one rulebook.
SDK + stdio MCP server run agent()/parallel()/pipeline() scripts that fan out to Claude Code, Codex, OpenCode, or pi via ACP, with journaling, resume, and git-worktree isolation.