hyperpod-node-debugger
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs…
Connecting the steps of a workflow
What it does
Operating policy. Run read-only diagnostics yourself. Never run a command that changes cluster, node, or workload state — present each one as a Suggested command (run this yourself) block and wait for the customer.
Read more
Destructive order: investigate → reboot → replace (replace destroys root + secondary volumes; not supported on Slurm controller nodes). Never discard training state, logs, or caches on speculation.
What it can touch
Includes 4 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/check-efa-sg.sh, scripts/check-node-reachability.sh, scripts/check-vpc-config.sh, scripts/triage-cluster.sh.
Installs other software
Following it will install packages (npm, pip, brew or similar). Those come from their own publishers, not from this skill.
How we know
The SKILL.md contains package-install commands.
Decodes hidden text and runs it
Code run this way does whatever the other server sends at that moment — what you can read today is not necessarily what runs.
How we know
scripts/triage-cluster.sh line 164 (and 1 more in that file): “local remote="bash -c \"echo $cmd_b64 | base64 -d | bash\""”. Read 2026-10-04, commit e32b05b.
scripts/triage-cluster.sh, line 164 ↗Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-04, commit e32b05b.
5 smaller things worth knowing
Refers to a credentials file (SSH keys, cloud logins, tokens); Sets itself up to run again automatically later; Contains commands that delete or overwrite; Contacts a server by raw IP address. Usually legitimate — listed so nothing is hidden.
How we know
Refers to a credentials file (SSH keys, cloud logins, tokens) — references/node-diagnostics-detail.md line 113; Sets itself up to run again automatically later — references/node-diagnostics-detail.md line 604; Contains commands that delete or overwrite — references/node-diagnostics-detail.md line 802; Refers to a credentials file (SSH keys, cloud logins, tokens) — scripts/check-node-reachability.sh line 233; Contacts a server by raw IP address — scripts/check-node-reachability.sh line 233. Read 2026-10-04, commit e32b05b.
references/node-diagnostics-detail.md, line 113 ↗references/node-diagnostics-detail.md, line 604 ↗references/node-diagnostics-detail.md, line 802 ↗scripts/check-node-reachability.sh, line 233 ↗scripts/check-node-reachability.sh, line 233 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to awslabs/agent-plugins: 2026-10-02 (2 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 4 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
Worth knowing
- It can only read. Nothing it does changes anything on the other side.
More from awslabs
All from this publisher →- amplify-workflow
Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first).
- api-gateway
Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket).
- aws-architecture-diagram
Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries.
- aws-lambda
Design, build, deploy, test, and debug serverless applications with AWS Lambda.
- aws-lambda-durable-functions
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration…
