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 bex-co/bex --skill bex-scalinggit clone --depth 1 https://github.com/bex-co/bexWrote 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/bex-co/bex/bex-scaling)<a href="https://agentmods.dev/skills/bex-co/bex/bex-scaling"><img src="https://agentmods.dev/badge/skills/bex-co/bex/bex-scaling/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/bex-co/bex/bex-scaling"><img src="https://agentmods.dev/badge/skills/bex-co/bex/bex-scaling.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 | $0.00068 | $0.01536 |
| Opus 5.5 | $0.00027 | $0.00614 |
| Sonnet 5.5 | $0.00014 | $0.00307 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
bex-scaling 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 yesterday.
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.
1. Retrieve the linked Markdown document directly with an available URL-fetching tool or HTTP client, such as `curl`. Do not substitute web-search summaries for the document. How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bex Scaling
This skill covers how to scale Web Services, Private Services, and Background Workers on bex: manual instance counts, autoscaling with a Pro workspace or higher, compute plan choices, and platform limits. Deeper guidance lives under references/.
When a service has or might need an attached disk, read references/persistent-disks.md before choosing a scaling architecture.
When to Use
- Setting or changing instance count (Dashboard, CLI, API, or Blueprint)
- Configuring autoscaling (min/max, CPU and memory targets)
- Choosing vertical (plan) vs horizontal (more instances) scaling
- Understanding constraints (disks, static sites, cron/workflows, 100-instance cap)
- Cost implications of running more or larger instances
- Blueprint fields:
numInstances,scaling,plan
Manual Scaling
- Set instance count from 1 to 100 via the Dashboard, CLI, or API.
- All instances share the same compute plan; you cannot mix plans on one service.
- Changes apply immediately: bex provisions new instances and deprovisions excess capacity as needed.
Autoscaling
Before recommending an autoscaling policy, establish the service type, workspace plan, whether the service is stateless or has a disk, the desired minimum and maximum instance counts, and whether CPU or memory is the limiting resource.
- Available only with a Pro workspace or higher.
- Configure minimum and maximum instances and targets for CPU and/or memory utilization (1–90% each).
- At least one metric must be enabled (CPU or memory). If both CPU and memory autoscaling toggles are off, autoscaling is disabled.
- If both manual instance settings and autoscaling are configured, autoscaling wins—manual count does not override the scaling policy in effect.
Autoscaling Formula
bex computes a candidate instance count from utilization vs target:
new_instances = ceil(current_instances * (current_utilization / target_utilization))
What ships with it
3 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.
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.
- yesterday First seen · 137 lines · 68 tokens per session scan A edf32970adb8
bex-scaling is a skill published in the GitHub repository bex-co/bex (577 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 1,536 once invoked, about $0.0003 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 2026-10-29.
Other skills, from other repositories
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
install
Kubeshark installation and deployment skill. Use this skill whenever the user wants to install Kubeshark, deploy Kubeshark to a Kubernetes cluster, set up Kubeshark, configure Kubeshark helm values, generate a Kubeshark config file, customize Kubeshark deployment, troubleshoot Kubeshark installation, upgrade…
argocd-expert
Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations. Use when the user mentions GitOps, Kubernetes, continuous deployment, declarative, or automation, or when the task involves ArgoCD Architecture, Application CRD, AppProject, or ApplicationSet.
sync-system-bus
Deploy the system-bus-worker to the joelclaw Kubernetes cluster from local machine. Use when syncing changes in packages/system-bus to k8s, especially because the GitHub Actions deploy job targets a non-existent self-hosted runner and cannot complete deploys automatically.
argocd-deploy
GitOps continuous deployment for Kubernetes with ArgoCD.
argocd
Argo CD GitOps continuous delivery reference for Kubernetes. Covers installation, application management, Helm/Kustomize sources, App-of-Apps pattern, ApplicationSet generators, sync waves, progressive delivery, RBAC, SSO, and secrets.