Session Report

When you need to understand what actually happened in a Claude Code session, this pulls everything from the Agent Monitor API and formats it into a readable report. You get per-model token breakdowns including cache read/write stats, exact costs via matched pricing rules, the full agent hierarchy with subagent types, tool invocation counts, compaction events, and a timeline of errors and turn durations. It's built for the localhost:4820 monitor setup, so you can review a specific session ID, grab the latest one, or summarize a date range. The cache hit rate calculation and baseline token tracking are especially useful for spotting context management issues before your bill gets weird.

GitHub stars: 455
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill session-report --agent claude-code

Installs into .claude/skills of the current project.

Files

Session Report

Generate a detailed session report from the Claude Code Agent Monitor.

Input

The user provides: $ARGUMENTS

This may be a session ID, "latest", or a date range like "last 24 hours".

Data Sources

All data comes from the Agent Monitor API at http://localhost:4820:

Endpoint	What it returns
`GET /api/sessions/{id}`	Session with nested `.agents[]` and `.events[]`
`GET /api/sessions?limit=50`	Session list with `agent_count`, `last_activity`, and inline `cost` per session (bulk pricing applied server-side)
`GET /api/pricing/cost/{sessionId}`	`{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }`
`GET /api/events?session_id={id}`	Event stream: each has `event_type`, `tool_name`, `summary`, `data` (JSON), `created_at`