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 agentmods add skills/bex-co/bex/deploy-appnpx skills add bex-co/bex --skill deploy-appgit clone --depth 1 https://github.com/bex-co/bexWhat 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 | $0.00056 | $0.00566 |
| Opus 5 | $0.00028 | $0.00283 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
deploy-app 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 3d 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.
allowed-tools: Bash(kubectl:*), Bash(bash scripts/app-apply.sh:*), Bash(curl:*), Bash(jq:*) What it actually says
Deploy an App and verify it end-to-end. Use KUBECONFIG=infra/local/bex.kubeconfig if no other cluster is targeted.
Requires BEX_API_URL and BEX_API_TOKEN in the environment (scripts/app-apply.sh reads them and fails with set BEX_API_URL if unset — both are client-supplied, not in .env.example; BEX_API_PUBLIC_URL in .env.example is the unrelated backend DeployHook origin). BEX_API_TOKEN is the Hydra-issued Bearer token (API key minted via /v1/api-keys), not the removed static shared secret. Optional BEX_OWNER_ID, BEX_REPO, BEX_BRANCH narrow the deploy.
- If
$ARGUMENTSis a path to arender.yaml(or legacybex.ymlalias — canonical isrender.yaml, seescripts/app-apply.sh), apply it withDRY_RUN=1 bash scripts/app-apply.sh $ARGUMENTSfirst and show the generated App CR, thenbash scripts/app-apply.sh $ARGUMENTSto deploy. If$ARGUMENTSis a directory, pass the directory — the script discoversrender.yamlthenbex.ymlinside it. Otherwise apply the sample:kubectl apply -f examples/whoami-app.yaml. - Watch until ready: poll
kubectl get apps.app.bex.co <name> -o jsonpath='{.status.phase} {.status.revision} {.status.url}'until phase isReady(timeout ~3 minutes; on timeout, showkubectl describe apps.app.bex.co <name>and the operator logskubectl -n bex-system logs deploy/bex-controller-manager --tail=50). - If
status.urlis set and resolvable,curl -fsSit (use--resolve/-konly if the local mock has no real DNS/TLS) and show the response status. - Report: App name, phase, revision, url, and where the pods landed (
kubectl get pods -l app.bex.co/app=<name> -o wide).
What ships with it
1 file 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.
- 3d ago First seen · 18 lines · 56 tokens per session scan A 76fe692aec21
deploy-app is a skill published in the GitHub repository bex-co/bex (420 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 566 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
k8s-deploy
Deploy and manage applications on Kubernetes clusters with kubectl and Helm.
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…
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
nvca-self-managed-install
Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.
image-pull-debug
Diagnose container image pull failures (ErrImagePull / ImagePullBackOff). Checks pod status, containerd logs, and events to identify root cause.
pod-pending-debug
Diagnose pod scheduling failures (Pending, Unschedulable). Checks events, node resources, taints, affinity, and PVC bindings to identify why a pod cannot be scheduled.