Adds a machine-readable intent layer to OpenClaw agents. Creates INTENT.md (optimization priorities, tradeoffs, delegation rules), wires it into subagent spawns via agent-context-loader, and ensures every subagent knows what you're optimizing for — not just what to do. Solves the "Klarna failure mode": AI optimizes measurable metrics instead of actual goals. Use when setting up a new OpenClaw workspace, when subagents keep making the wrong tradeoffs, or when you want explicit control over cost/quality/speed priorities.

为 OpenClaw 代理添加机器可读的目标层。生成 INTENT.md 文件（包含优化优先级、权衡规则和委托规则），并通过 agent-context-loader 将其注入子代理的启动流程，确保每个子代理都清楚你追求的目标，而不仅仅是任务指令。解决“Klarna 失效模式”：AI 优化可测量指标而非真实目标。适用于新建 OpenClaw 工作空间、子代理持续做出错误权衡，或需要明确控制成本/质量/速度优先级的场景。