원클릭으로
team-audit
Analyze Claude Code audit logs — session summaries, metrics, timelines, anomaly detection, and claim verification
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Analyze Claude Code audit logs — session summaries, metrics, timelines, anomaly detection, and claim verification
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Build and deploy features — branch, implement, commit, review, test, deploy, PR/merge
shadcn/ui component patterns including Radix UI primitives, CVA variants, form components with React Hook Form, and Tailwind CSS styling. Use when creating UI components, building forms, implementing design systems, or working with shadcn/ui.
Add critical test coverage — tests ONLY for functionality that could cause production disasters
List all available tools with their signatures and purposes
Technical debt and refactoring — analyze, refactor, and validate code improvements
Create a new custom agent using the meta-agent with guided requirements gathering
| name | team-audit |
| description | Analyze Claude Code audit logs — session summaries, metrics, timelines, anomaly detection, and claim verification |
| argument-hint | [action] [session:id] [limit:number] [claims:claim1,claim2] |
| allowed-tools | Bash(node *) |
Analyze Claude Code audit logs to provide insights into tool usage, file operations, commands executed, and verify claims about what was accomplished during a session.
Extract action and options from arguments, then run the log analyzer:
ARGS="$ARGUMENTS"
ACTION="summary"
SESSION=""
LIMIT="50"
CLAIMS=""
# Parse action from first token only
FIRST_TOKEN=$(printf '%s\n' "$ARGS" | awk '{print $1}')
case "$FIRST_TOKEN" in
report|metrics|timeline|verify|anomalies) ACTION="$FIRST_TOKEN" ;;
esac
# Extract session ID (session:abc123)
SESSION=$(echo "$ARGS" | grep -o 'session:[^[:space:]]*' | cut -d':' -f2 || echo "")
# Extract limit (limit:25)
LIMIT=$(echo "$ARGS" | grep -o 'limit:[0-9]*' | cut -d':' -f2 || echo "50")
# Extract claims (claims:"claim1,claim2")
CLAIMS=$(echo "$ARGS" | grep -o 'claims:"[^"]*"' | sed 's/claims://; s/"//g' || echo "")
Build and run the log analyzer command:
HOOKS_DIR="${CLAUDE_HOOKS:-$HOME/.claude/hooks}"
set -- node "$HOOKS_DIR/log_analyzer.cjs"
case "$ACTION" in
"report") set -- "$@" --report ;;
"metrics") set -- "$@" --metrics ;;
"timeline") set -- "$@" --timeline --limit "$LIMIT" ;;
"verify")
if [ -n "$CLAIMS" ]; then
set -- "$@" --verify
IFS=',' read -ra CLAIM_ARRAY <<< "$CLAIMS"
for claim in "${CLAIM_ARRAY[@]}"; do
set -- "$@" "$(echo "$claim" | xargs)"
done
else
echo "Error: Claims required for verify action. Use: /team-audit verify claims:\"claim1,claim2\""
exit 1
fi
;;
"anomalies") set -- "$@" --anomalies ;;
esac
if [ -n "$SESSION" ]; then
set -- "$@" --session "$SESSION"
fi
"$@"
| Action | Description |
|---|---|
| summary (default) | Quick overview of session metrics |
| report | Comprehensive audit report with all details |
| metrics | Detailed metrics about tools, files, and performance |
| timeline | Chronological view of all events (use limit:N to control output) |
| verify | Verify specific claims about what was accomplished |
| anomalies | Detect unusual patterns or potential issues |
/team-audit - Show summary for current session/team-audit report - Generate full audit report/team-audit timeline limit:25 - Show last 25 timeline events/team-audit verify claims:"tests were run,files were created" - Verify claims/team-audit metrics session:abc123 - Show metrics for specific session/team-audit anomalies - Detect anomalies in current session