agentops-telemetry

agentops-telemetry is a skill for Claude Code, Codex from MLOps-Courses/agentops-open-course. It costs 68 tokens per session (646 once invoked), scanned A, original, MIT.

An observability setup for an AI agent using OpenTelemetry, a standard way to record connected application work. It records traces, metrics, and logs for model calls, tool calls, timing, tokens, and errors while leaving prompts and responses out by default.

In plain words
What is it for?
Use it to connect an agent to systems such as Tempo, Prometheus, Grafana, or Loki, correlate one request’s work, and export privacy-conscious telemetry through an OpenTelemetry Collector.
Why use it?
It makes production agent behaviour easier to investigate when the final answer alone does not show which model or tool caused a delay or failure, while reducing the risk of storing user content.

Skill for Claude CodeCodex

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 skills/mlops-courses/agentops-open-course/agentops-telemetry
Any agent
npx skills add MLOps-Courses/agentops-open-course --skill agentops-telemetry
Clone the repo
git clone --depth 1 https://github.com/MLOps-Courses/agentops-open-course

Made for: Claude Code, Codex.

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 agentops-telemetry

README.md
[![agentmods](https://agentmods.dev/badge/skills/mlops-courses/agentops-open-course/agentops-telemetry.svg)](https://agentmods.dev/skills/mlops-courses/agentops-open-course/agentops-telemetry)
Your own site
<a href="https://agentmods.dev/skills/mlops-courses/agentops-open-course/agentops-telemetry"><img src="https://agentmods.dev/badge/skills/mlops-courses/agentops-open-course/agentops-telemetry.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 646 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 $0.00068 $0.00646
Opus 5 $0.00034 $0.00323
Sonnet 5 $0.00014 $0.00129
Haiku 4.5 $0.00007 $0.00065

Measured 3d ago against content hash 6a8c15de9610, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentops-telemetry 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 3d 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.

skills/agentops-telemetry/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentOps Telemetry

Trace an agent the way you trace a distributed system: one correlated record of model, tool, and application work per request — not a log line with the final answer. Make privacy the default, not an afterthought.

When to use

  • An agent misbehaves in production and you can only see the final output.
  • You need to correlate a model call, its tool calls, tokens, and latency for one turn.
  • You are exporting agent telemetry to Tempo, Prometheus, Grafana, or Loki.
  • You must instrument without leaking user prompts or model responses into span storage.

Steps

  1. Emit spans over OpenTelemetry, using the GenAI semantic conventions. Name attributes with the standard gen_ai.* keys (gen_ai.operation.name, gen_ai.request.model, gen_ai.tool.name) and error.type so any OTel backend understands them.
  2. Keep content capture off by default. Traces should carry timing, model, tool, token, and status metadata — not the prompt or response body. Make capturing content an explicit, auditable opt-in with a stated privacy and retention cost.
  3. Export through the OTel Collector, then fan out. Send OTLP to a collector that routes traces to your trace store, derives request-count/latency metrics from spans (a spanmetrics connector), and ships logs to a log store — one pipeline, many backends.
  4. Redact and bound the log bridge. If you bridge application logs to OTLP, redact secrets/PII and cap size before export, and deduplicate noisy lines.
  5. Derive RED metrics from spans. Rate, Errors, Duration over a bounded label set (operation, model, error type) — never label by prompt, user, session, or trace id, which explodes cardinality.

Reference implementation

From the AgentOps Open Course, installable with npx skills add MLOps-Courses/agentops-open-course:

  • agents/go/telemetry/ — OTLP setup and a redacting, bounded log bridge with content capture off by default.
  • evals/evidence.go — separate sanitized run/case/score traces and metrics for evaluation.
  • infra/observability/ — OTel Collector, Prometheus, Grafana, Loki, and a shipped dashboard.
  • Course chapters 7.1. Tracing and 7.2. Monitoring.

Read the full file on GitHub · 37 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. 3d ago First seen · 37 lines · 68 tokens per session scan A 6a8c15de9610

Subscribe to this mod's changes

agentops-telemetry is a skill published in the GitHub repository MLOps-Courses/agentops-open-course (2 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 646 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

find-your-level

Interactive quiz that maps your AI/ML knowledge to a starting point in the 523-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".

rohitg00/ai-engineering-from-scratch · 71 tokens

learn-mcp

Focused interactive tutor for the Model Context Protocol (MCP) path in AI Engineering from Scratch. Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates. Teaches one lesson per invocation and records…

rohitg00/ai-engineering-from-scratch · 77 tokens

start-learning

One-time onboarding for the AI Engineering from Scratch curriculum (523 lessons, 20 phases). Interviews the learner, runs the placement quiz, and writes LEARNING.md, a persistent study plan the learn skill drives. Trigger phrases: "start learning", "set up the course", "begin the curriculum", "onboard me", "create my…

rohitg00/ai-engineering-from-scratch · 74 tokens

learn-agent-skills

Focused interactive tutor for the Agent Skills Engineering path in AI Engineering from Scratch. Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills. Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md.

rohitg00/ai-engineering-from-scratch · 67 tokens

skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

rohitg00/ai-engineering-from-scratch · 36 tokens

migration-review

Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.

rohitg00/ai-engineering-from-scratch · 35 tokens