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 gke-labs/kube-agents --skill kube-agents-observabilitygit clone --depth 1 https://github.com/gke-labs/kube-agentsWrote 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/gke-labs/kube-agents/kube-agents-observability)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/kube-agents-observability"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/kube-agents-observability/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/gke-labs/kube-agents/kube-agents-observability"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/kube-agents-observability.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 | $0.00031 | $0.03302 |
| Opus 5.5 | $0.00012 | $0.01321 |
| Sonnet 5.5 | $0.00006 | $0.00660 |
| Haiku 4.5 | $0.00003 | $0.00330 |
Grade A, and why
kube-agents-observability scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sh -c 'curl -i -s -o /dev/null -w "%{http_code}\n" -X POST "$OTEL_EXPORTER_OTLP_ENDPOINT/v1/traces"' How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Audit, verify, and troubleshoot the logging, metrics, and distributed tracing observability of the Platform Agent.
[!TIP] The provided Python scripts in the
scripts/subdirectory are parameterized reference implementations. When troubleshooting, you can run them directly, customize their parameters, or write custom just-in-time scripts/commands to query more specific metrics, endpoints, or time ranges as required by the task context.
[!IMPORTANT] The helpers reach Google APIs through the credential broker and never hold a token: the Cloud Trace and Cloud Monitoring reads go through
credential_proxy_client.ApiSession(seescripts/google_api.py), and the Cloud Logging read runsgcloud logging readthrough the broker's shim. Write a just-in-time script the same way. Do not fetch an access token and do not write anAuthorizationheader yourself: the shim refuses agcloudtoken fetch, the metadata server answers the sandbox with an identity IAM grants nothing, and whatever either returns lands in the transcript.
Workflow
Logging
1. Audit Agent Main Logs
- Verify that the main agent container is writing logs to
/opt/data/logs/*.log. - View the internal agent log files directly:
kubectl exec <pod-name> -c <agent-container-name> -n kubeagents-system -- tail -n 100 /opt/data/logs/agent.log - The tool-call audit trail is not in
agent.log: it is one JSON object per line in/opt/data/logs/audit.jsonlfor the front door and/opt/data/profiles/<profile>/logs/audit.jsonlfor a named profile; in Logs Explorer,jsonPayload.audit_event:*, withjsonPayload.file_pathnaming the profile's file.kubectl exec <pod-name> -c <agent-container-name> -n kubeagents-system -- tail -n 20 /opt/data/logs/audit.jsonl
2. Inspect Sidecar Log Aggregator (Fluent-bit)
- Verify the
fluent-bitsidecar container tails the log directory and streams to standard output:kubectl logs <pod-name> -c fluent-bit -n kubeagents-system --tail=100 - Retrieve and verify the configuration of the Fluent-bit sidecar:
kubectl get configmap <agent-name>-fluent-bit-config -n kubeagents-system -o yaml - Ensure the shared
/opt/datavolume is mounted to both the agent and Fluent-bit containers:kubectl get pod <pod-name> -n kubeagents-system -o jsonpath='{.spec.containers[*].volumeMounts}'
What ships with it
7 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.
- scripts/analyze_trace_latency.py 6.9 KB runs code
- scripts/check_token_usage.py 4.2 KB runs code
- scripts/fetch_traces.py 1.2 KB runs code
- scripts/get_chat_users.py 8.9 KB runs code
- scripts/get_metric_descriptors.py 1.9 KB runs code
- scripts/google_api.py 14 KB runs code
- scripts/test_observability_helpers.py 59 KB runs code
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.
- 5d ago Changed dbed6b009227
- 11d ago Changed · +3 lines 2edd5b96f868
- 12d ago Changed · +1 lines d95cddd28231
- 18d ago Changed · +5 lines 4a2b583a0344
- 21d ago Changed · +4 lines 3de820f69391
- 1mo ago Changed · +7 lines 8adc1d7cfd5b
- 1mo ago Changed 0cede5ad755b
- 1mo ago First seen · 191 lines · 31 tokens per session scan A f3c65fd22c17
kube-agents-observability is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 3,302 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.