kg-scoutlisted

# History Scout — Mining Past Sessions for Knowledge ## Overview Scout extracts knowledge from Claude Code conversation history using a **tension-driven, tiered approach**: lightweight scanning first, deep investigation only when signals indicate value. The goal is **not** to extract everything — it's to find patterns worth preserving while being economical with tokens. **No special tools needed.** You read history files directly with Read/Bash. Progress persists via `kg_progress`. ## Prerequisites Before scouting, ensure: ``` kg_read(cwd="<project root>") # Load graph + get session_id kg_progress(session_id, task_id="scout") # Check where you left off ``` ## Data Sources ### Tier 1: `~/.claude/history.jsonl` (Always scan first) - Lightweight: timestamp, project path, first ~60 chars of each prompt - Format: `{"display": "...", "project": "/path", "timestamp": ..., "sessionId": "..."}` - Cost: Very low — just metadata - Value: Shows patterns, repetitions, topics across all projects ### Tier 2: `~/.claude/projects/{encoded-path}/{session}.jsonl` (Selective) - Full conversation transcripts with assistant responses, tool calls - Cost: High — can be megabytes per session - Value: Full context, decisions, rationale - Path encoding: `/home/user/project` becomes `-home-user-project` ## Tension-Driven Investigation Don't read full sessions blindly. Use history.jsonl to identify **tension signals**: | Signal | What it looks like in history.jsonl | Action | |------