metrics
The metrics command retrieves and analyzes agent performance data from a stored metrics file, displaying session counts, activity frequency, files modified per session, and recent session history in a formatted table. Use this command to review workflow efficiency, identify patterns in agent behavior, track changes across sessions, and diagnose whether metrics collection is functioning properly in the Claude workflow environment.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/HEAD/commands/metrics.md -o ~/.claude/commands/metrics.mdmetrics.md
## Context - Metrics file: !`cat .claude/agent-metrics.jsonl 2>/dev/null || echo "NO_METRICS_FILE"` ## Task Analyze the agent performance metrics and present a summary. **If the metrics file does not exist or the context above shows "NO_METRICS_FILE":** Print exactly: "No metrics recorded yet. Metrics are automatically collected after each session." **If metrics data exists**, parse each JSON line and present: 1. **Overview** - Total sessions logged - Sessions in the last 7 days (compare timestamps to now) - Average files changed per session 2. **Recent Sessions** (last 10) Format as a markdown table: | # | Timestamp (UTC) | Files Changed | Commit | Status | | --- | --------------- | ------------- | ------ | ------ | - Show the most recent 10 sessions, newest first - For "Commit", show the short commit message or "—" if none - For "Status", show the duration_hint value 3. **Patterns** - Note any trends (e.g., sessions with many file changes, frequency of commits) - If there are sessions with 0 files changed, note how many were "no-op" sessions Keep the output concise and well-formatted.
Expert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, when asked to review changes, PR review, code quality check, lint, or standards audit. Focuses on quality, security, performance, and maintainability.
Expert debugging specialist for errors, test failures, crashes, segmentation faults, memory leaks, timeouts, race conditions, deadlocks, and unexpected behavior. Use PROACTIVELY when encountering any error, exception, or failing test. Performs systematic root cause analysis.
Technical documentation specialist. Use for creating README files, API documentation, architecture docs, inline comments, user guides, changelogs, migration guides, release notes, FAQs, and troubleshooting docs. MUST BE USED when documentation is needed or when code changes require doc updates.
Master coordinator for complex multi-step tasks. Use PROACTIVELY when a task involves 2+ modules, requires delegation to specialists, needs architectural planning, or involves GitHub PR workflows. MUST BE USED for open-ended requests like "improve", "enhance", "build", "scale", "refactor", "add feature", "system design", "architecture", "complex task", or when implementing features from GitHub issues.
Code refactoring specialist for improving code quality, reducing technical debt, eliminating code smells, reducing complexity, and applying design patterns. Use PROACTIVELY when code needs restructuring, simplification, tech debt reduction, or when applying DRY/SOLID principles.
Security specialist for vulnerability detection, secure coding review, and security hardening. Use PROACTIVELY when handling authentication, authorization, encryption, secrets, credentials, OAuth, JWT, CORS, headers, user input, API keys, or sensitive data. Checks for OWASP Top 10 and common vulnerabilities.
Testing strategy specialist for designing test suites, writing tests, and ensuring comprehensive coverage. Use PROACTIVELY when adding new features, fixing bugs, improving test coverage, creating test plans, mocking strategies, handling flaky tests, or writing integration/E2E tests.
Add tests for recently changed files or specified code