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/openshell/debug-openshell-clusternpx skills add NVIDIA/OpenShell --skill debug-openshell-clustergit clone --depth 1 https://github.com/NVIDIA/OpenShellWhat 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 | $0.00136 | $0.10726 |
| Opus 5 | $0.00068 | $0.05363 |
| Sonnet 5 | $0.00027 | $0.02145 |
| Haiku 4.5 | $0.00014 | $0.01073 |
Grade B, and why
debug-openshell-cluster scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo systemctl enable --now nvidia-cdi-refresh.path How it starts
The opening of the file, as written. The whole thing — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug OpenShell Gateway Deployment
Diagnose a gateway and its selected compute platform. Do not assume OpenShell provisions Kubernetes or runs a k3s container. OpenShell targets a reachable gateway endpoint backed by Docker, Podman, Kubernetes, the experimental VM driver, or an operator-managed out-of-tree compute driver.
Use openshell first to identify the active endpoint. Then use the platform tools that match the gateway's compute driver: docker, podman, kubectl/helm, or VM driver logs.
Overview
The target deployment flow is:
- Operator starts or deploys the gateway with system packages, systemd, Helm, or a development task. The CLI does not start, stop, or destroy gateway services.
- Operator configures the compute driver.
- Operator provides the CLI and supervisor authentication material required by the deployment mode: edge or OIDC user auth, optional CLI mTLS, and gateway-minted sandbox JWTs.
- The CLI registers a reachable gateway endpoint with
openshell gateway add. - The gateway creates sandboxes through the selected compute driver.
The standard gateway binary explicitly installs its compiled Docker, Podman, Kubernetes, and VM registrations at startup. With no configured driver, the gateway probes only installed registrations in priority order (Kubernetes, Podman, then Docker); VM has no probe and remains opt-in. A custom gateway binary may install a different set, so confirm the binary's registered drivers when auto-detection reports that no suitable driver is available.
For local evaluation only, TLS may be disabled and the gateway can be reached through http://127.0.0.1:<port>.
Prerequisites
- The
openshellCLI must be available for endpoint checks. - Know the active gateway name and endpoint, or be able to inspect local gateway metadata.
- Know the compute platform: Docker, Podman, Kubernetes, VM, or an out-of-tree driver.
- For Kubernetes:
kubectlmust target the cluster that hosts OpenShell and Helm version 3 or later must be available. - For Docker or Podman: the runtime socket must be reachable from the gateway host.
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 · 647 lines · 136 tokens per session scan B cb196da26d21
debug-openshell-cluster is a skill published in the GitHub repository NVIDIA/OpenShell (8,421 stars, last pushed 2d ago), licensed Apache-2.0. It adds 136 tokens to every session and 10,726 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…