From claude-reflect
Displays the learnings queue with confidence scores, patterns, and relative timestamps for each item.
How this command is triggered — by the user, by Claude, or both
Slash command
/claude-reflect:view-queueThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
## Context - Queue file: per-project at `~/.claude/projects/<encoded-cwd>/learnings-queue.json` - Legacy global queue (`~/.claude/learnings-queue.json`) is auto-migrated on first access ## Your Task Display the current learnings queue in a readable format with confidence scores, patterns, and relative timestamps. **Output format:** If queue is empty: ## Implementation **Step 1: Read the project-scoped queue file:** **Step 2: Parse and format each item with:** - **Confidence score**: `[0.XX]` format, from `item.confidence` (default 0.60 if missing) - **Message preview**: First 50 c...
~/.claude/projects/<encoded-cwd>/learnings-queue.json~/.claude/learnings-queue.json) is auto-migrated on first accessDisplay the current learnings queue in a readable format with confidence scores, patterns, and relative timestamps.
Output format:
════════════════════════════════════════════════════════════
LEARNINGS QUEUE: [N] items
════════════════════════════════════════════════════════════
[0.85] "use gpt-5.1 not gpt-5" (use-X-not-Y) - 2 days ago
[0.70] "perfect, that's exactly right" (positive) - 5 days ago
[0.90] "remember: always run tests" (explicit) - just now
════════════════════════════════════════════════════════════
Commands:
/reflect - Process and save learnings
/skip-reflect - Discard all learnings
════════════════════════════════════════════════════════════
If queue is empty:
════════════════════════════════════════════════════════════
LEARNINGS QUEUE: Empty
════════════════════════════════════════════════════════════
No learnings queued. Use "remember: <learning>" to add items,
or corrections will be auto-detected. Run /reflect to process.
════════════════════════════════════════════════════════════
Step 1: Read the project-scoped queue file:
python3 scripts/read_queue.py 2>/dev/null || echo "[]"
Step 2: Parse and format each item with:
[0.XX] format, from item.confidence (default 0.60 if missing)item.messageitem.patterns (show first pattern if multiple)item.timestampRelative time calculation:
Calculate the difference between now and item.timestamp (ISO 8601 format):
Python snippet for relative time:
from datetime import datetime, timezone
def relative_time(iso_timestamp):
"""Convert ISO timestamp to relative time string."""
try:
dt = datetime.fromisoformat(iso_timestamp.replace('Z', '+00:00'))
now = datetime.now(timezone.utc)
diff = now - dt
seconds = diff.total_seconds()
if seconds < 60:
return "just now"
elif seconds < 3600:
minutes = int(seconds / 60)
return f"{minutes} minute{'s' if minutes > 1 else ''} ago"
elif seconds < 86400:
hours = int(seconds / 3600)
return f"{hours} hour{'s' if hours > 1 else ''} ago"
elif seconds < 604800:
days = int(seconds / 86400)
return f"{days} day{'s' if days > 1 else ''} ago"
else:
weeks = int(seconds / 604800)
return f"{weeks} week{'s' if weeks > 1 else ''} ago"
except:
return "unknown"
Formatting rules:
[0.85](pattern-name)(auto) for auto-detected or (explicit) for remember:Example output line:
[0.85] "use gpt-5.1 not gpt-5" (use-X-not-Y) - 2 days ago
npx claudepluginhub dyai2025/claude-reflect3plugins reuse this command
First indexed Mar 16, 2026
/view-queueDisplays the learnings queue with confidence scores, patterns, and relative timestamps for each item.
/phase4-queueChecks the memory-palace knowledge queue for pending items, reports status, prompts for promotion/archive/defer decisions, and executes promotions with file moves and frontmatter updates.
/listLists all stored learnings with optional sorting by recency or usefulness, and filtering by category or project.