stats

ContextStellar Stats

Show scoring statistics and RLM learning progress for the current project.

What to do

1. Check that CONTEXTSTELLAR_API_KEY is set. If not, tell the user to run /contextstellar:setup.

2. Fetch the shell stats (lightweight summary):

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/shell-stats" \
  -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

3. If the user wants detailed stats, also fetch the full stats:

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/stats?projectId=${CONTEXTSTELLAR_PROJECT_ID}" \
  -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

4. Present the results:

Quick Summary (from shell-stats):

• Score: {score} ({grade}) {trend arrow}
• Success Rate: {successRate}%
• RLM Confidence: {rlmConfidence}% ({rlmSamples} samples)
• Total Events: {totalEvents}

Detailed View (from full stats, if requested):

• Event counts by type (PreToolUse, PostToolUse, Stop)
• Grade distribution (A+ through F with counts)
• Learned weights vs default weights (show deltas)
• Average latency

5. If RLM confidence is low (< 40%), suggest the user keep using Claude Code to accumulate more samples for better weight learning.

6. If the average score is below B, suggest running /contextstellar:optimize for improvement tips.