Sprint Summary

If you're running Claude Code sessions throughout a sprint and want to see what you actually accomplished, this pulls everything from your local Agent Monitor API and formats it into a proper retrospective document. You get sessions grouped by project directory, cost breakdowns per model, token efficiency stats like cache hit rates, and velocity metrics you can compare sprint over sprint. The retrospective section is genuinely useful because it surfaces your most expensive sessions and highest error rates alongside what worked well. It's basically turning your localhost:4820 monitoring data into something you could actually show a team lead without having to manually spreadsheet it all together.

GitHub stars: 455
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill sprint-summary --agent claude-code

Installs into .claude/skills of the current project.

Files

Sprint Summary

Generate a sprint summary from Claude Code Agent Monitor data.

Input

The user provides: $ARGUMENTS

This may be:

A sprint duration: "last 2 weeks", "last 10 days"
A date range: "2025-03-31 to 2025-04-13"
"current sprint" (default: last 14 days)

Procedure

Fetch sprint data from http://localhost:4820:
- GET /api/sessions?limit=500 — all sessions in range (default sort: most recently updated first)
- GET /api/analytics — aggregated metrics
- GET /api/pricing/cost — total costs
- For high-value sessions: GET /api/events?session_id={id} — event details
Compile sprint summary:

🎯 Sprint Overview
- Sprint period: [start] to [end]
- Total sessions: N (completed: N, errored: N, abandoned: N)
- Total development hours with Claude Code: N
- Total cost: $X.XX
- Overall completion rate: N%
📦 Deliverables

Group sessions by working directory (project):
- Project A (/path/to/project)
  - N sessions, N hours, key activities
- Project B (/path/to/other)
  - N sessions, N hours, key activities