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/nvidia/deepops/deploy-airgappednpx skills add NVIDIA/deepops --skill deploy-airgappedgit clone --depth 1 https://github.com/NVIDIA/deepopsWhat 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 | $0.00065 | $0.11851 |
| Opus 5 | $0.00032 | $0.05926 |
| Sonnet 5 | $0.00013 | $0.02370 |
| Haiku 4.5 | $0.00006 | $0.01185 |
Grade D, and why
deploy-airgapped scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo mkdir -p /var/repos Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "${task_kubespray_import}"' EXIT Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg \ How it starts
The opening of the file, as written. The whole thing — 1,000 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy DeepOps in an air-gapped environment
Preconditions and boundaries
- Use an Internet-connected staging machine and a separate provisioning machine that can reach every target and every internal mirror. Do not connect an isolated network to the Internet for this procedure.
- Fix one DeepOps commit, target OS release, CPU architecture, cluster type, inventory, and enabled feature set before mirroring. Repository and image requirements change when any of these inputs change.
- Provide complete distribution package mirrors plus internal HTTP package/file service and container registry endpoints. Use trusted TLS where possible; if the registry is intentionally insecure, configure it explicitly.
- Bootstrap the isolated provisioning machine with the OS packages and Python
environment required by
scripts/setup.shbefore closing the boundary, or provide approved internal OS and Python package indexes. Copying the source tree alone does not install Ansible. - Reserve enough storage for repository metadata, packages, container images, charts, the initialized DeepOps checkout, and two copies during transfer.
- Confirm that every target is fully manageable and has no active users or workloads. Driver installation can reboot hosts.
- Run DeepOps commands from the repository root. Keep secrets out of archives
and store site configuration in
config/, neverconfig.example/.
DeepOps does not provide supported mirror-building automation. Do not run
scripts/airgap/build_offline_cache.sh: it calls the removed
playbooks/airgap/build-offline-cache.yml and cannot complete in this tree.
Build and verify the mirrors explicitly as described below.
1. Freeze the deployment inputs
-
Record the DeepOps commit and initialize every submodule on the connected staging machine:
git rev-parse HEAD git submodule update --init --recursive ./scripts/setup.sh -
Copy
config.example/toconfig/. Define the real hosts inconfig/inventorybefore collecting artifacts so the selected cluster path and optional components are known:
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.
- 2d ago First seen · 1,000 lines · 65 tokens per session scan D a3fc4e3cf78c
deploy-airgapped is a skill published in the GitHub repository NVIDIA/deepops (1,471 stars, last pushed today), licensed BSD-3-Clause. It adds 65 tokens to every session and 11,851 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, 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
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…
cloud-k8s
Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.
kubernetes-specialist
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
doca-container-deployment
Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod manifests directory, YAML pod-spec drop, kubelet status / ENTRYPOINT logs / per-service liveness, smoke-before-bulk, and the layered…