AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
Vibecoding harness:结构化规划 → 检查清单执行 → 多视角自我审查。兼容 Cursor、Claude Code、Codex 等。
AI 翻譯
Vibecoding harness: structured planning → checklist execution → multi-lens self-review. Works with Cursor, Claude Code, Codex, and more.
開發工具TypeScript · JavaScriptGitHub @mt2007自行安裝營運者未確認
試用過了嗎? 點一下就好,不需要登入。
正在載入完整 README。 以下為已儲存的摘錄。
autopilot-harness — a vibecoding harness that turns open-ended agent chat into structured planning → checklist execution → multi-lens self-review. (中文说明) Vibe coding is fast until scope drifts, acceptance stays implicit, and “looks done” skips hard review angles. Autopilot keeps the agent on a durable track: 1. Grill the plan before writing product code 2. Execute against a checklist (artifacts.plans_dir/ /, new-init default docs/autopilot/plans) 3. Self-review under rotating lenses before an item is marked done檢視完整 README ↗
目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
autopilot-harness — a vibecoding harness that turns open-ended agent chat into structured planning → checklist execution → multi-lens self-review. (中文说明) Vibe coding is fast until scope drifts, acceptance stays implicit, and “looks done” skips hard review angles. Autopilot keeps the agent on a durable track: 1. Grill the plan before writing product code 2. Execute against a checklist (artifacts.plans_dir/ /, new-init default docs/autopilot/plans) 3. Self-review under rotating lenses before an item is marked done檢視完整 README ↗