Monitor local coding-agent sessions and token usage with Loongsuite Pilot
Collect local telemetry from Claude Code, Codex, Cursor, OpenClaw, OpenCode, and related coding agents, then inspect token usage, tool calls, sessions, and traces from one local dashboard or OpenTelemetry pipeline.
npx skills add agentskillexchange/skills --skill monitor-local-coding-agent-sessions-and-token-usage-with-loongsuite-pilot
curl -fsSL https://loongcollector-community-edition.oss-cn-shanghai.aliyuncs.com/loongsuite-pilot/installer.sh -o loongsuite-pilot-installer.sh && bash loongsuite-pilot-installer.sh install, then verify with loongsuite-pilot status. On Windows, use the documented PowerShell installer. After installation, use loongsuite-pilot start, loongsuite-pilot status, loongsuite-pilot token-usage, and the local dashboard at http://127.0.0.1:8765/.Use Loongsuite Pilot when an operator needs a local, repeatable telemetry pass across multiple AI coding agents instead of checking each agent’s native logs by hand. The agent/operator workflow is to install Pilot, let it discover supported local agents, enable the relevant hooks or plugins, review `loongsuite-pilot status` and `loongsuite-pilot token-usage`, and inspect the local dashboard or exported JSONL/HTTP/OTLP trace data for session, model, token, tool-call, cost, privacy, and audit signals. The scope boundary is coding-agent telemetry collection and operational inspection, not generic observability infrastructure or normal use of an Alibaba Cloud product.
What this skill actually does
Inputs and prerequisites: Node.js 18+, npm, curl or wget, supported local coding agents such as Claude Code, Codex, Cursor, OpenClaw, OpenCode, or related hook/plugin-compatible agents; PowerShell 5.1+ on Windows.
Setup notes: Follow the upstream Quick Start. On Linux or macOS, download and run the public installer with curl -fsSL https://loongcollector-community-edition.oss-cn-shanghai.aliyuncs.com/loongsuite-pilot/installer.sh -o loongsuite-pilot-installer.sh && bash loongsuite-pilot-installer.sh install , then verify with loongsuite-pilot status . On Windows, use the documented PowerShell installer. After installation, use loongsuite-pilot start , loongsuite-pilot status , loongsuite-pilot token-usage , and the local dashboard at http://127.0.0.1:8765/ .
Source and verification boundary: use https://github.com/alibaba/loongsuite-pilot#readme 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 Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.