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 workload-rebalancinggit 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/workload-rebalancing)<a href="https://agentmods.dev/skills/gke-labs/kube-agents/workload-rebalancing"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/workload-rebalancing/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/workload-rebalancing"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/workload-rebalancing.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 | $0.00051 | $0.00947 |
| Opus 5 | $0.00026 | $0.00474 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
workload-rebalancing 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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workload Rebalancing Skill (validation-then-declare)
When live cluster utilization — checked via the read-only gke MCP / kubectl top on each cluster — shows a cluster overutilized / under pressure and another with headroom, you may relocate a workload. You act as an orchestrator: cluster agents validate feasibility (read-only); you declare the change as a single GitOps PR; KCC reconciles the actual move. Never issue imperative start/stop.
When to use vs. do-it-yourself
Delegating is optional. Use this fan-out when you want per-cluster local validation and a single aggregated decision. For a trivial single-cluster change, act directly.
The card graph (fan-out validation → decide on your own card)
Resolve each cluster's profile name first (cluster_agent_profile.py name --project … --cluster … --location …), then:
- Card A — can clusterA host it?
kanban_create(assignee="<clusterA-profile>", title="Validate can-host <workload>", body="Can you host <ns/workload> (needs ~<cpu>/<mem>)? Check capacity, affinity/taints, quotas. Do NOT mutate.") - Card B — is clusterB safe to evacuate?
kanban_create(assignee="<clusterB-profile>", title="Validate safe-to-evacuate <workload>", body="Is it safe to evacuate <ns/workload>? Check PDBs, statefulness/local PVs, in-flight work. Do NOT mutate.") - Wait on your own card: poll A and B with
kanban_show(<id>)(sleep 60between rounds) until both are settled, then read theirmetadata.
Cards A and B are created with no parents so they run in parallel immediately (independent read-only checks) while you wait. Do not add your own currently-running card to A or B's parents — parents means "runs after", and that would stop them being claimed at all (SOUL.md §0). Do not complete your card while A or B is unfinished: your card's result is what the requester receives, and the image refuses a kanban_complete over unfinished fan-out cards (#1010). (The actual make-before-break ordering of the move is handled by KCC when it reconciles the PR, not by the agents.)
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.
- 7d ago Changed 69da9804ca62
- 8d ago First seen · 60 lines · 51 tokens per session scan A daa7f05a7e64
workload-rebalancing is a skill published in the GitHub repository gke-labs/kube-agents (54 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 947 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…