Monitor Claude Code sessions and tool activity with Claude Code Agent Monitor
Install Claude Code hooks that stream session, tool, subagent, and workflow events into a local dashboard for live observability and review.
npx skills add agentskillexchange/skills --skill monitor-claude-code-sessions-and-tool-activity-with-claude-code-agent-monitor
npm run setup, run npm run install-hooks to add Claude Code hook entries to ~/.claude/settings.json, then start with npm run dev for development or npm run build && npm start for production.Use Claude Code Agent Monitor when a team or operator needs visibility into active Claude Code work instead of relying only on terminal scrollback. The operator installs the dashboard, registers Claude Code hooks, starts the local server, and reviews live sessions, tool calls, subagent orchestration, waiting states, cost and model usage, workflows, alerts, and exported snapshots. The boundary is Claude Code observability and session operations, not a general analytics product or generic dashboard framework.
What this skill actually does
Inputs and prerequisites: Claude Code, Node.js 20+, npm, local dashboard server; optional MCP host integration.
Setup notes: Clone the repository, run npm run setup , run npm run install-hooks to add Claude Code hook entries to ~/.claude/settings.json , then start with npm run dev for development or npm run build && npm start for production.
Source and verification boundary: use https://github.com/hoangsonww/Claude-Code-Agent-Monitor as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Claude Code workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.