intent-engineering

name

intent-engineering

description

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.

Intent Engineering

The Problem

Without an intent layer, agents optimize for what's measurable (fast response, no errors) rather than what matters (your actual priorities). The Klarna failure: AI saved $60M and destroyed customer loyalty because it optimized resolution time, not relationships.

What This Skill Installs

1. INTENT.md — YAML priority manifest at workspace root
2. lib/agent-context-loader.js — prepends intent summary to every subagent spawn
3. Routing integration — intent propagation flag in all routing decisions

Installation

Step 1 — Create INTENT.md

Copy references/intent-template.md to your workspace root as INTENT.md and edit:

cp $(dirname $0)/references/intent-template.md $OPENCLAW_WORKSPACE/INTENT.md

Or create it manually — see references/intent-template.md for the annotated schema.

Step 2 — Install agent-context-loader

Copy the reference implementation to lib/:

 $( )/references/agent-context-loader-template.js /lib/agent-context-loader.js