What is tempo-llm-cli CLAUDE.md?

A command-line application for exploring distributed traces in Grafana Tempo with natural-language questions. Distributed traces record how one request moves through multiple services.

Use it to start an interactive tracing session, query Tempo through an MCP server, inspect distributed-system behavior, and ask questions about latency, errors, or traffic.

It lets you investigate service behavior without writing every TraceQL query by hand. You can use it to find slow traces, recurring errors, and request-rate patterns in Tempo data.

How joe-elliott/tempo-llm-cli configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to joe-elliott/tempo-llm-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/joe-elliott/tempo-llm-cli/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/joe-elliott/tempo-llm-cli

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/joe-elliott/tempo-llm-cli/claude-md/github.svg)](https://agentmods.dev/instructions/joe-elliott/tempo-llm-cli/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/joe-elliott/tempo-llm-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/joe-elliott/tempo-llm-cli/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/joe-elliott/tempo-llm-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/joe-elliott/tempo-llm-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 604 This file is loaded in full into every session.

When invoked 604 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00604	$0.00604
Opus 5.5	$0.00242	$0.00242
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 2mo ago against content hash 2d50e33ad92f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tempo-llm-cli CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tempo LLM CLI

A specialized command-line interface that uses Claude to help explore and analyze distributed tracing data from Grafana Tempo.

Overview

This Go application provides an AI-powered interface for exploring tracing data using Tempo's API. Claude is equipped with specialized tools to query traces, analyze metrics, and understand distributed system behavior through TraceQL queries.

Building

# Build the application
go build -o tempo-llm-cli

# Or run directly
go run .

Usage

# Start an AI-powered tracing exploration session
./tempo-llm-cli

Once running, you can ask Claude natural language questions about your tracing data, such as:

"Show me the slowest traces for the payment service"
"What are the most common error patterns?"
"How many requests per minute are we seeing?"

Environment Variables

Set your Anthropic API key:

export ANTHROPIC_API_KEY=your_api_key_here

Optionally configure the MCP server URL (defaults to http://localhost:3200/api/mcp):

export MCP_SERVER_URL=http://localhost:3200/api/mcp

Features

AI-powered natural language queries for tracing data
Interactive exploration of distributed system behavior
Full conversation context preservation for complex analysis
Graceful exit with 'quit' or 'exit' commands
Error handling for API failures

Available Tools

Claude has access to specialized tools for tracing analysis:

TraceQL Search: Find specific traces using TraceQL queries
TraceQL Metrics: Generate metrics and aggregations from trace data
Attribute Discovery: Explore available attributes and their values
Trace Retrieval: Get detailed information about specific traces
Documentation Access: Built-in TraceQL and Tempo documentation

Architecture

The application uses Claude's Messages API with conversation history maintained locally. Each message is sent with the complete conversation context to ensure coherent multi-turn conversations.

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 84 lines · 604 tokens per session scan A 2d50e33ad92f

Subscribe to this mod's changes

tempo-llm-cli CLAUDE.md is an instructions file published in the GitHub repository joe-elliott/tempo-llm-cli (5 stars, last pushed 1y ago), licensed Apache-2.0. It adds 604 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics

tempo-llm-cli CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tempo-llm-cli CLAUDE.mdjoe-elliott/tempo-llm-cli	Instructions file	5	1y ago	Apache-2.0	A	604	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tempo-llm-cli: Instructions file for Claude Code