tracing-expert

tracing-expert is an agent for Claude Code from vibeeval/vibecosystem. It costs 29 tokens per session (1,880 once invoked), scanned A, original, MIT.

A specialist for following requests across multiple services using distributed tracing tools such as OpenTelemetry, Jaeger, and Tempo. It connects traces with logs and metrics to show where time is spent.

In plain words
What is it for?
Use it to set up tracing, pass trace information between services, choose sampling rules, and investigate service performance or request failures.
Why use it?
It helps locate slow or failing parts of a system when one request passes through several services. It also makes related activity easier to connect during debugging.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/tracing-expert
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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.

agentmods badge for tracing-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/tracing-expert.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/tracing-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/tracing-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/tracing-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.01880
Opus 5 $0.00015 $0.00940
Sonnet 5 $0.00006 $0.00376
Haiku 4.5 $0.00003 $0.00188

Measured 2d ago against content hash a4f4093b4527, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tracing-expert 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 2d 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.

agents/tracing-expert.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TRACING-EXPERT -- Distributed Tracing & Observability Specialist

Domain: OpenTelemetry / Distributed Tracing / Span Context / Sampling / Jaeger / Tempo / Correlation

Core Concepts

Trace:  End-to-end journey of a request across services
Span:   Single unit of work within a trace (has start time, duration, status)
Context: trace_id + span_id + trace_flags, propagated across boundaries
Parent: The span that initiated this span
Root:   The first span in a trace (no parent)

Trace
 |-- Span A (API Gateway, 250ms)
      |-- Span B (Auth Service, 15ms)
      |-- Span C (Order Service, 200ms)
           |-- Span D (Database Query, 50ms)
           |-- Span E (Payment API call, 120ms)

OpenTelemetry Setup (Node.js)

// tracing.ts -- Load BEFORE any other imports
import { NodeSDK } from '@opentelemetry/sdk-node'
import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http'
import { getNodeAutoInstrumentations } from '@opentelemetry/auto-instrumentations-node'
import { Resource } from '@opentelemetry/resources'
import { ATTR_SERVICE_NAME, ATTR_SERVICE_VERSION } from '@opentelemetry/semantic-conventions'

const sdk = new NodeSDK({
  resource: new Resource({
    [ATTR_SERVICE_NAME]: 'order-service',
    [ATTR_SERVICE_VERSION]: '1.2.0',
    'deployment.environment': process.env.NODE_ENV,
  }),
  traceExporter: new OTLPTraceExporter({
    url: process.env.OTEL_EXPORTER_OTLP_ENDPOINT || 'http://localhost:4318/v1/traces',
  }),
  instrumentations: [getNodeAutoInstrumentations({
    '@opentelemetry/instrumentation-http': {
      ignoreIncomingPaths: ['/health', '/ready', '/metrics'],
    },
    '@opentelemetry/instrumentation-express': { enabled: true },
    '@opentelemetry/instrumentation-pg': { enabled: true },
    '@opentelemetry/instrumentation-redis': { enabled: true },
  })],
})

sdk.start()
process.on('SIGTERM', () => sdk.shutdown())

Manual Instrumentation

import { trace, SpanKind, SpanStatusCode } from '@opentelemetry/api'

const tracer = trace.getTracer('order-service', '1.0.0')

async function processOrder(order) {
  return tracer.startActiveSpan('processOrder', {
    kind: SpanKind.INTERNAL,
    attributes: {
      'order.id': order.id,
      'order.item_count': order.items.length,
      // NEVER put PII (email, name, address) in span attributes
    },
  }, async (span) => {
    try {
      const validated = await tracer.startActiveSpan('validateOrder', async (childSpan) => {
        const result = await validateOrder(order)
        childSpan.setAttribute('validation.passed', result.valid)
        childSpan.end()
        return result
      })

      if (!validated.valid) {
        span.setStatus({ code: SpanStatusCode.ERROR, message: 'Validation failed' })
        span.recordException(new Error(validated.reason))
        return { error: validated.reason }
      }

      const payment = await processPayment(order)
      span.addEvent('payment_processed', { 'payment.id': payment.id })

      span.setStatus({ code: SpanStatusCode.OK })
      return { success: true, payment }
    } catch (error) {
      span.setStatus({ code: SpanStatusCode.ERROR, message: error.message })
      span.recordException(error)
      throw error
    } finally {
      span.end()
    }
  })
}

Read the full file on GitHub · 235 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.

  1. 2d ago First seen · 235 lines · 29 tokens per session scan A a4f4093b4527

Subscribe to this mod's changes

tracing-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 29 tokens to every session and 1,880 once invoked, about $0.0001 per session on Opus 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 2026-09-03.