jnmetacode/local-agent-toolkit/tracelet-instrument

Claude Code and agent skill by jnmetacode/local-agent-toolkit

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Instrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.

Install

npx vskill@latest install jnmetacode/local-agent-toolkit/tracelet-instrument

SKILL.md

The same SKILL.md was published earlier as jnmetacode/local-agent-toolkit/tracelet-instrument.

tracelet-instrument

Goal: make an agent's execution visible — every LLM call, tool call, prompt, token count and latency — without sending anything to a cloud service. tracelet is a local OTLP collector + UI; any OpenTelemetry exporter pointed at http://127.0.0.1:4318 shows up live.

Procedure

  1. Start the collector (keep it running in a terminal):

``bash npx @jnmetacode/tracelet # ingests OTLP on :4318, UI on :4321 ``

  1. Point the app's exporter at it. For most OpenTelemetry SDKs the zero-code

route is environment variables:

``bash export OTEL_EXPORTER_OTLP_ENDPOINT=http://127.0.0.1:4318 export OTEL_SERVICE_NAME=my-agent ``

  1. Framework-specific wiring (pick the one that matches the codebase):

Vercel AI SDK — pass telemetry on each call and register a Node tracer:

``js const result = await generateText({ model, prompt, experimental_telemetry: { isEnabled: true }, }); ``

OpenTelemetry JS (manual spans):

``js import { NodeSDK } from '@opentelemetry/sdk-node'; import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http'; new NodeSDK({ traceExporter: new OTLPTraceExporter({ url: 'http://127.0.0.1:4318/v1/traces' }) }).start(); ``

Python: pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http, then the same OTEL_EXPORTER_OTLP_ENDPOINT env var works.

  1. Name spans so the waterfall reads like the agent's plan: one root span per

run (agent.run), one child per tool call (tool.<name>) and per model call. Attach gen_ai.request.model, input.value, output.value attributes — tracelet recognizes the GenAI/OpenInference conventions and renders prompts, tokens and tool I/O.

  1. Verify: trigger one agent run, open http://127.0.0.1:4321, and confirm

the trace shows the expected span tree with prompts/tokens. If nothing arrives, the exporter is usually pointed at the wrong port (4318) or batching hasn't flushed — force a flush/shutdown on process exit.

Both OTLP/HTTP protobuf (SDK default) and JSON are accepted — no exporter config gymnastics needed.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
14
Repository forks
2
7-day trend score
14

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jnmetacode/local-agent-toolkit/tracelet-instrument/badge)](https://verified-skill.com/skills/jnmetacode/local-agent-toolkit/tracelet-instrument)

Something wrong with this skill or its page? Tell us.