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 ollygarden/opentelemetry-agent-skills --skill otel-telemetry-emissionsgit clone --depth 1 https://github.com/ollygarden/opentelemetry-agent-skillsWrote 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/ollygarden/opentelemetry-agent-skills/otel-telemetry-emissions)<a href="https://agentmods.dev/skills/ollygarden/opentelemetry-agent-skills/otel-telemetry-emissions"><img src="https://agentmods.dev/badge/skills/ollygarden/opentelemetry-agent-skills/otel-telemetry-emissions/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/ollygarden/opentelemetry-agent-skills/otel-telemetry-emissions"><img src="https://agentmods.dev/badge/skills/ollygarden/opentelemetry-agent-skills/otel-telemetry-emissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00473 |
| Opus 5 | $0.00037 | $0.00236 |
| Sonnet 5 | $0.00015 | $0.00095 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
otel-telemetry-emissions 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 12d 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.
What it actually says
Telemetry Emissions
A registry of what telemetry OpenTelemetry components actually emit, pinned to upstream versions.
Note: The telemetry emissions in these files were detected by LLM analysis of the upstream source and may contain errors. Verify against the component's source or docs before relying on a row for critical decisions.
Layout
<repo basename>/<path in repo>/v<version>.md
Example: opentelemetry-collector-contrib/receiver/kafkareceiver/v0.158.0.md
One file per scanned version. The files in a component directory are its
telemetry history; index.md lists every file — start there to see what is
covered.
Looking up a component at a version
- Find the component's directory (or its row in
index.md). - Pick the file matching the target version exactly.
- If there is no exact match, use the file with the highest version below the target and say the exact version is unverified.
- If the component or version is not covered at all, say so — do not infer telemetry from semantic conventions.
What a data file contains
Frontmatter (repo, path, version, scope_name, commit_sha,
last_verified), then per-signal tables:
- Traces — span name, kind, attributes, notes
- Metrics — metric name, instrument type, unit, attributes, notes
- Logs — log/event name, attributes, notes
scope_name is the component's instrumentation scope — the anchor for
matching runtime telemetry back to the component. Absent signals are omitted
entirely. Notes marks conditional emission (feature gates, opt-in config,
experimental semconv). Sources lists the upstream files the data came from.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 3.7 KB
- evals/results.md 18 KB
- index.md 36 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.153.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.154.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.155.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.156.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.157.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.158.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/servicegraphconnector/v0.160.0.md 2.6 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.153.0.md 2.5 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.154.0.md 2.7 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.155.0.md 2.5 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.156.0.md 2.3 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.157.0.md 2.3 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.158.0.md 2.5 KB
- opentelemetry-collector-contrib/connector/spanmetricsconnector/v0.160.0.md 2.5 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.154.0.md 4.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.155.0.md 4.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.156.0.md 4.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.157.0.md 4.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.158.0.md 4.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.159.0.md 5.7 KB
- opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/v0.160.0.md 4.9 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.153.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.154.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.155.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.156.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.157.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.158.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/filterprocessor/v0.160.0.md 1.0 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.153.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.154.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.155.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.156.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.157.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.158.0.md 8.3 KB
- opentelemetry-collector-contrib/processor/k8sattributesprocessor/v0.160.0.md 8.8 KB
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.153.0.md 627 B
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.154.0.md 627 B
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.155.0.md 627 B
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.156.0.md 627 B
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.157.0.md 1.2 KB
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.158.0.md 1.2 KB
- opentelemetry-collector-contrib/processor/resourcedetectionprocessor/v0.160.0.md 1.2 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.153.0.md 2.8 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.154.0.md 3.0 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.155.0.md 3.0 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.156.0.md 3.0 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.157.0.md 3.2 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.158.0.md 3.2 KB
- opentelemetry-collector-contrib/processor/tailsamplingprocessor/v0.160.0.md 3.2 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.153.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.154.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.155.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.156.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.157.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.158.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.159.0.md 13 KB
- opentelemetry-collector-contrib/receiver/dockerstatsreceiver/v0.160.0.md 13 KB
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.
- 12d ago First seen · 49 lines · 75 tokens per session scan A 47f92dd790b8
otel-telemetry-emissions is a skill published in the GitHub repository ollygarden/opentelemetry-agent-skills (98 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 473 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
clawmetry-selfcheck
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task. Use when ClawMetry is installed on this machine and you want to check whether you are re-reading files, spinning in loops, or burning budget.
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
clawmetry
Real-time observability for OpenClaw agents — local dashboard + optional encrypted cloud sync. Tracks costs, tokens, sessions, tool calls, memory, crons, and system health. Access from anywhere via ClawMetry Cloud.