Usage Scout — Data & AI agent for Claude Code
Read-only scout for session, token, and cost code in this FastAPI tracker.
How to install Usage Scout
Installs to ~/.claude/agents/njengah-claude-code-tracker-usage-scout.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Njengah/claude-code-tracker/HEAD/.claude/agents/usage-scout.md -o ~/.claude/agents/njengah-claude-code-tracker-usage-scout.md Restart Claude Code, or start a new session, for it to be picked up.
What Usage Scout does
name: usage-scout description: Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage is recorded, how cost_usd is calculated, or which routes touch sessions and analytics. Use proactively for "where does X live" questions about tokens, sessions, or cost. Do not use for auth review or for writing code. tools: Read, Grep, Glob model: haiku
You are a read-only scout for Claude Code Session Tracker.
Your job is to find the files and f
Alternatives in Data & AI
- Claude Mem — A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresse 38.9k ★
- Harness Scout — Picks the right AI agent harness for a described task or project 801 ★
- API Cost Scanner — Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching stra 160 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
LLM Performance Analyst
Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patter
Agentic AI Specialist
Focused worker for the Python symptom-analysis service in agentic_ai/, including FastAPI routes, LangGraph orc
Python LLM Expert
Senior LLM/bot engineer. Use proactively for LangGraph assistants, prompt orchestration, FastAPI routes, Redis
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Tp Context Engineer
PROACTIVELY use this when the user says "setup this project for AI-assisted coding", "agent is producing wrong
AI Cost Optimizer
Audits an LLM application or AI agent for token cost and rate-limit risk, using its usage logs and code, and r
Related Skills
Cost Autopsy
Session token-burn autopsy (TCO v1). Reads the TIS telemetry log and reports per-session token spend (input /
Usage Tracker
See what your agent sessions actually cost. OpenClaw, Claude Code, and Codex usage analytics: API spend vs OAu
Claude Code Token Lens
A beautiful, local-first usage tracker and analytics dashboard for AI coding agents (Claude Code, etc.). (一款美观