Daily Standup

Turns your Claude Code session logs into a proper standup report. It hits the Agent Monitor API, pulls your last 24 hours of sessions (or whatever date range you specify), and formats everything into accomplishments, blockers, metrics, and suggestions. You get working directories grouped as projects, tool usage patterns, cost breakdowns, and error highlights. Honestly most useful if you're juggling multiple coding sessions and need to remember what you actually shipped versus what you abandoned at 2am. The metrics table makes it easy to spot when you're burning through context or hitting API errors repeatedly.

GitHub stars: 455
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill daily-standup --agent claude-code

Installs into .claude/skills of the current project.

Files

Daily Standup

Generate a daily standup report from Claude Code Agent Monitor data.

Input

The user provides: $ARGUMENTS

This may be:

"today" or empty (default: last 24 hours)
"yesterday" for the previous day
A specific date: "2025-04-10"

Procedure

Fetch recent session data from http://localhost:4820:
- GET /api/sessions?limit=50 (default sort: most recently updated first)
- Filter sessions that started within the target day
- For each matching session: GET /api/events?session_id={session_id}
Compile standup sections:

✅ What I accomplished
- List each completed session with:
  - Brief description (from session name or first tool's context)
  - Working directory (project context)
  - Key tools used and outcomes
  - Duration and model used
- Group by project/working directory if multiple
⚠️ Issues encountered
- Sessions that ended in error or abandoned status
- Tools that failed (from error events)
- Compaction events (hit context limits)
- Unusually long sessions (>2x average duration)