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 divinevideo/divine-mobile --skill multi-cluster-api-data-mismatchgit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/multi-cluster-api-data-mismatch)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/multi-cluster-api-data-mismatch"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/multi-cluster-api-data-mismatch/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/divinevideo/divine-mobile/multi-cluster-api-data-mismatch"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/multi-cluster-api-data-mismatch.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 | $0.00131 | $0.01234 |
| Opus 5.5 | $0.00052 | $0.00494 |
| Sonnet 5.5 | $0.00026 | $0.00247 |
| Haiku 4.5 | $0.00013 | $0.00123 |
Grade A, and why
multi-cluster-api-data-mismatch 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Cluster API Data Mismatch
Problem
When investigating why an API returns data that doesn't match direct database queries, the root cause may be that your kubectl context points to a different cluster (e.g., POC) than the one actually serving the public API (e.g., production). Both clusters have the same schemas and similar data volumes, making the mismatch non-obvious.
Context / Trigger Conditions
- API returns records that direct database queries (
kubectl exec ... clickhouse-client) can't find - Data counts are similar (e.g., both have ~20k records) but specific records differ
- You're debugging a data pipeline that "should work" but labels/counts never update
- Multiple kubectl contexts exist (production, staging, POC, test)
- The API response header shows
server: nginxbut no ingress exists in the current cluster's namespace
Solution
Step 1: Verify which cluster serves the domain
# Check DNS for the public API domain
dig relay.divine.video +short
# → 34.58.27.79
# Check your current cluster's gateway/ingress IP
kubectl get gateway -A # or kubectl get ingress -A
# → 35.184.10.63 (different IP = different cluster!)
Step 2: Check all available contexts
kubectl config get-contexts
# Look for production vs staging vs POC contexts
Step 3: Switch to the correct cluster
kubectl config use-context <production-context-name>
Step 4: Verify the database connection
# Check what database the API actually connects to
kubectl get secret -n <namespace> <db-credentials> -o jsonpath='{.data.DATABASE_URL}' | base64 -d
# Production might use managed services (ClickHouse Cloud, Cloud SQL)
# POC might use in-cluster pods
Step 5: Also check for ExternalSecrets when updating secrets
If secrets are managed by ExternalSecrets operator:
# Check if ExternalSecrets manages the secret
kubectl get externalsecret -n <namespace>
# If yes, update the SOURCE (e.g., GCP Secret Manager), not the k8s secret
gcloud secrets versions add <secret-name> --project=<project> --data-file=-
# Force sync after updating
kubectl annotate externalsecret <name> -n <namespace> force-sync=$(date +%s) --overwrite
# Verify the k8s secret updated
kubectl get secret <name> -n <namespace> -o jsonpath='{.data.<key>}' | base64 -d
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.
- 1mo ago First seen · 124 lines · 131 tokens per session scan A f510051fb382
multi-cluster-api-data-mismatch is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 131 tokens to every session and 1,234 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
application-integration-troubleshooting
Diagnoses failed, stuck, or silent Google Cloud Application Integration runs and Integration Connectors tasks using the REST API, Cloud Logging, and Cloud Monitoring. Use when an integration fails, returns HTTP 200 without doing the expected work, hangs in a suspended or retry state, or hits IAM, run-as service…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-mxla-hang
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/).…
gke-ai-troubleshooting-tpu-performance-degradation
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (gcloud alpha mldiagnostics monitored-events / hypercomputecluster.googleapis.com/v1alpha) and 1-minute Cloud Monitoring system metrics (kubernetes.io/node/accelerator/).…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…