troubleshooting

troubleshooting is a skill for Claude Code from yale-som-hpc/claude-code-marketplace. It costs 81 tokens per session (1,424 once invoked), scanned A, original, Unlicense.

A troubleshooting guide for jobs on the Yale SOM high-performance computing cluster, a shared system for running demanding computational work.

In plain words
What is it for?
Use it when a cluster job fails, is killed, stays pending, or reports errors such as missing packages, incompatible libraries, or GPU problems.
Why use it?
It maps common job errors, pending reasons, time limits, memory failures, and missing software to specific checks and fixes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hpc plugin — 23 skills, 3 commands shipped together

Good fit Use it when a cluster job fails, is killed, stays pending, or reports errors such as missing packages, incompatible libraries, or GPU problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yale-som-hpc/claude-code-marketplace/troubleshooting
Install

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.

Any agent
npx skills add yale-som-hpc/claude-code-marketplace --skill troubleshooting
Clone the repo
git clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplace

Made for: Claude Code.

Or install hpc, the plugin that ships this one along with the rest of its 23 skills, 3 commands.

Wrote 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.

agentmods badge for troubleshooting

README.md
[![agentmods](https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/troubleshooting/github.svg)](https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/troubleshooting)
Your own site
<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/troubleshooting"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/troubleshooting/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.

agentmods 80×15 button for troubleshooting

Your own site · 80×15
<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/troubleshooting"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01424
Opus 5 $0.00041 $0.00712
Sonnet 5 $0.00016 $0.00285
Haiku 4.5 $0.00008 $0.00142

Measured 11d ago against content hash f96e2238c2b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

troubleshooting scanned grade A with 0 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 11d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/hpc/skills/troubleshooting/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Troubleshooting

Rule: read the actual error (and the pending reason), match it below, apply the fix. Don't guess from symptoms — squeue --me -o "%T %r", the job's .out/.log, and seff JOBID almost always name the cause.

Quick triage

Symptom / error Likely cause Fix
Job stuck PENDING for ages, cluster looks idle Targeted partition's nodes are full or reserved for a higher-priority partition (the CPU partitions overlap on shared nodes). squeue --me -o "%T %r" to read the reason; sinfo -o "%R %C" for idle cores; resubmit to a partition with capacity (often gpunormal for CPU work). See managing-jobs.
Job killed near a round time (e.g. exactly 4h) Hit the partition time limit — default_queue caps at 4h. Move long work to cpunormal/gpunormal (no time limit), or split into resumable chunks.
Out Of Memory / job killed, seff shows high memory --mem too low. Check seff JOBID (MaxRSS is on the .batch row); set --mem to ~1.5–2× observed peak. See self-diagnosing-resource-use.
./tool: ... version 'GLIBC_2.xx' not found Prebuilt binary needs a newer glibc than the cluster has. Use a musl/static build, a module, or Apptainer; or compile on the cluster. See installing-software.
R: there is no package called 'X' The base R module ships no add-on packages. Bootstrap a project library first: install.packages("renv") then renv::init()/renv::install(...) on the login node. See running-r.
Python: ModuleNotFoundError inside a job Job ran the wrong interpreter, or env not synced. Launch with srun .venv/bin/python ...; run uv sync --frozen on the login node (never inside the job). See running-python.
Stata: Slurm .out is empty / "where's my output?" stata-mp -b writes its own .log, not stdout. Read the do-file's .log (and the stray main.log Stata drops in the working dir), not the .out. See running-stata.
sbatch fails: bad interpreter, : not found, or $'\r' CRLF line endings (edited on Windows). dos2unix job.sh or sed -i 's/\r$//' job.sh; set your editor to LF for .sh.
nvidia-smi: command not found or it errors You're on a login node (no GPU driver), or no GPU was allocated. Run inside a GPU allocation (--gres=gpu:1); see using-gpus.
git: command not found (or other tool) Tool isn't on the default PATH. module spider <tool> then module load; for user tools install into ~/.local/bin. git in particular needs module load git.
Python forkserver job hangs at startup, 0% CPU forkserver deadlocks under srun .venv/bin/python. Use fork (CPU work) or spawn (CUDA/threads). See parallel-python.
seff reports CPU Utilized: 00:00:00 on a job that worked seff samples coarsely; sub-minute jobs read as 0. Ignore CPU-efficiency on jobs under ~1–2 minutes; trust it only on longer jobs.
Heavy work slow / login node sluggish for everyone Ran compute on the login node. Login nodes are for editing/submitting only — put compute in sbatch/srun. See overview.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 11d ago First seen · 49 lines · 81 tokens per session scan A f96e2238c2b5

Subscribe to this mod's changes

troubleshooting is a skill published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 2mo ago), licensed Unlicense. It adds 81 tokens to every session and 1,424 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens