weekly-reality-capture

name	weekly-reality-capture
description	Auto-generate a reality-first weekly log from daily memory logs, git history, and agent state. Uses Claude to synthesize what actually happened — not a strategic filter, not a curated narrative. Supports backfill by week number. Use when a user says "weekly recap", "what happened this week", "weekly capture", or "reality check".
metadata	{"emoji":"📸","category":"memory","platform":"any (requires Anthropic API key)"}

Weekly Reality Capture

Synthesize a reality-first weekly log from multiple data sources. The key insight: most weekly reviews optimize for narrative. This one optimizes for truth.

Data Sources

Source	What it captures
Daily memory logs	What the agent did/discussed each day
Git log	What code actually changed
Agent session state	Open threads, pending follow-ups
Open threads JSON	Carried-over work items

Usage

# Current week
python3 scripts/capture.py

# Specific week
python3 scripts/capture.py --week 2026-W14

# Dry run (print synthesis prompt, don't call Claude)
python3 scripts/capture.py --dry-run

Configuration (env vars)

Variable	Default	Purpose