A Codex Skill for lightweight acceptance review and bounded fix loops.
-
Updated
Jul 1, 2026
A Codex Skill for lightweight acceptance review and bounded fix loops.
Pi-native workflow baton runner with per-step model switching and isolated step context.
West Loop AI Orchestrator turns long-horizon agent work into a governed iteration loop with durable state, executor-verifier checks, spec-driven plans, controlled experiments, and evidence-based reporting. Use West Loop AI Orchestrator to schedule AI teams, recover progress, compare outcomes, and run reliable coding workflows.
Claude builds in-session (no claude -p); Codex reviews headless. Every claimed result is re-run and diffed (claimed==actual) so hallucinated numbers die at the gate. A self-healing 6-stage build/review loop that runs until a real problem stops it.
Reusable Codex and Claude agent skills for VRM avatar polish: Blender/MMD inspection, SpringBone hair and skirt physics, clipping QA, backups, and evidence-driven review loops.
Spec-gated, dual-review-loop implementation workflow for Claude Code
Fallibilist Plan → Implement → Review → Fix → Loop skill for robust agent workflows
Privacy-first local MCP hub for coordinating Claude, OpenAI, Gemini, Ollama, and optional cloud council seats.
To associate your repository with the review-loop topic, visit your repo's landing page and select "manage topics."