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.
npx skills add MLOps-Courses/agentops-open-course --skill agentops-telemetrygit clone --depth 1 https://github.com/MLOps-Courses/agentops-open-courseWrote 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.
[](https://agentmods.dev/skills/mlops-courses/agentops-open-course/agentops-telemetry)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00625 |
| Opus 5.5 | $0.00033 | $0.00250 |
| Sonnet 5.5 | $0.00017 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00063 |
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 29d 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.
How it starts
The opening of the file, as written. The whole thing — 36 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 MLflow (traces), Prometheus (metrics), or Loki (logs).
- You must instrument without leaking user prompts or model responses into span storage.
Steps
- 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) anderror.typeso any OTel backend understands them. - 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.
- 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.
- 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.
- 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 (agent modules live under agents/python/src/agent/):
telemetry.py— OTLP setup and a redacting, bounded, dedup log bridge; content capture off by default.infra/observability/— OTel Collector, Prometheus, Grafana, Loki, and a shipped dashboard.- Course chapters
7.1. Tracingand7.2. Monitoring.
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.
- 29d ago Changed · -1 lines · +15 tokens per session 463f0d764e4e
- 1mo ago First seen · 37 lines · 68 tokens per session scan A 6a8c15de9610
agentops-telemetry is a skill published in the GitHub repository MLOps-Courses/agentops-open-course (2 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 625 once invoked, about $0.0003 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.
Other skills, from other repositories
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.
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.
orchard-release
Check deployment evidence and recovery conditions.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…
orchard-review
Review a release proposal.