klh

LLM Performance Analyst — Data & AI agent for Claude Code

Data & AI community

Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patterns.

How to install LLM Performance Analyst

Installs to ~/.claude/agents/klh-speedy-claude-llm-performance-analyst.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/klh/speedy-claude/HEAD/agents/llm-performance-analyst.md -o ~/.claude/agents/klh-speedy-claude-llm-performance-analyst.md

Restart Claude Code, or start a new session, for it to be picked up.

What LLM Performance Analyst does

name: llm-performance-analyst description: Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patterns. Diagnoses dumb errors from hasty narrow edits that miss the bigger pattern, and prescribes concrete fixes to CLAUDE.md, hooks, permissions, and skills. Scope is agent behavior and agent config only — auditing online services or SaaS subscriptions is tool-stack-auditor's job. Use after long sessions, cost spikes, repeated error loops, or

Alternatives in Data & AI

  • Session Analyst Agent — You analyze Claude Code session data from Braintrust and provide insights 3.6k ★
  • API Cost Scanner — Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching stra 160 ★
  • Review Code Correctness — A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable 134 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Usage Scout — Data & AI agent for Claude Code

Usage Scout

Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage

Data & AI community
Design Guardian — Data & AI agent for Claude Code

Design Guardian

Accountable design decider and applier. Reviews real UI evidence, rejects token drift and generic AI styling,

Data & AI community
Budget — Data & AI agent for Claude Code

Budget

AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits

Data & AI community
AI Provider Expert — Data & AI agent for Claude Code

AI Provider Expert

Primary reviewer for AI provider integrations, model routing, embeddings, prompt systems, streaming, token eff

Data & AI community
Pipeline Optimizer — Data & AI agent for Claude Code

Pipeline Optimizer

Reviews the LLM/agent pipeline — model selection, LangGraph wiring, MCP client lifecycle, async/streaming beha

Data & AI community
Product Data Analyst — Data & AI agent for Claude Code

Product Data Analyst

Sorcerer — Interpret product usage, conversion, drop-off, errors and feedback; form evidence-backed hypotheses

Data & AI community

Related Skills

Unity Fix — Development skill for Claude Code

Unity Fix

Diagnoses and fixes a Unity bug — reads console errors, checks common causes, applies targeted fix, verifies v

Development community
Drachometer — Data skill for Claude Code

Drachometer

A Claude Code hook that logs every turn and tool call to a local SQLite database, with a browser dashboard for

Data community
Open Skills — Security skill for Claude Code

Open Skills

The improve- family: senior-advisor Claude Code skills that audit a codebase (copy, prompts, error handling, a

Security community