workshop-troubleshooter

workshop-troubleshooter is a skill for Claude Code, Codex from JAICHANGPARK/workshop-harness. It costs 66 tokens per session (737 once invoked), scanned A, original, MIT.

A troubleshooting guide generator for technical workshops. It creates instructions tailored to operating systems, computer memory sizes, network problems, local AI servers, and CPU or GPU fallback.

In plain words
What is it for?
Use it to prepare FAQs and troubleshooting guides for model downloads, firewall or network issues, Ollama and LM Studio connection errors, and hardware-specific setup.
Why use it?
It helps facilitators diagnose common attendee failures quickly during a live session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare FAQs and troubleshooting guides for model downloads, firewall or network issues, Ollama and LM Studio connection errors, and hardware-specific setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jaichangpark/workshop-harness/workshop-troubleshooter
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 JAICHANGPARK/workshop-harness --skill workshop-troubleshooter
Clone the repo
git clone --depth 1 https://github.com/JAICHANGPARK/workshop-harness

Made for: Claude Code, Codex.

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 workshop-troubleshooter

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/workshop-troubleshooter/github.svg)](https://agentmods.dev/skills/jaichangpark/workshop-harness/workshop-troubleshooter)
Your own site
<a href="https://agentmods.dev/skills/jaichangpark/workshop-harness/workshop-troubleshooter"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/workshop-troubleshooter/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 workshop-troubleshooter

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaichangpark/workshop-harness/workshop-troubleshooter"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/workshop-troubleshooter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 737 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 $0.00066 $0.00737
Opus 5 $0.00033 $0.00368
Sonnet 5 $0.00013 $0.00147
Haiku 4.5 $0.00007 $0.00074

Measured 10d ago against content hash c6e57f772816, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workshop-troubleshooter 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 10d 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.

skills/workshop-troubleshooter/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workshop Troubleshooter Skill

Purpose

Hardware variations, operating system firewall policies, and local LLM server port mismatches cause predictable attendee failures during live workshops. This skill pre-generates complete troubleshooting matrices (docs/20-faq.md and troubleshooting guides) so facilitators and TAs can resolve issues in under 30 seconds.


RAM-Tier Sizing & Model Selection Matrix

Hardware RAM Tier Maximum Parameter Size Recommended Ollama Model Tag Context Window Limit (num_ctx)
8GB RAM 2B parameters max gemma4:e2b or phi-4-mini 2048
16GB RAM 4B parameters comfortable gemma4:e4b 4096
32GB+ RAM 12B - 14B parameters gemma4:e12b or qwen3:14b 8192

Local LLM Server Port & Network Error Resolution

Symptom / Error Message Root Cause Port / Tool Immediate Fix Action
connection refused :11434 Ollama server process not running Port 11434 (Ollama) Run ollama serve & in terminal
connection refused :1234 LM Studio server not started Port 1234 (LM Studio) Go to LM Studio Developer tab -> Click Start Server
404 Not Found on /v1/chat/completions Port mismatch (pointing to Ollama 11434 instead of LM Studio 1234, or vice versa) Port 11434 / 1234 Update client base_url: http://localhost:11434/v1 for Ollama, http://localhost:1234/v1 for LM Studio
Error: model not found Model tag not pulled into local server runtime Ollama / LM Studio Run ollama pull gemma4:e4b or search in LM Studio UI
CUDA out of memory / VRAM exhausted GPU memory exceeded by large context or model size VRAM limit Force CPU mode: CUDA_VISIBLE_DEVICES="" ollama serve
Windows Firewall blocking port Local firewall blocking incoming loopback connections Windows Security Run PowerShell: New-NetFirewallRule -DisplayName "Ollama Port" -Direction Inbound -LocalPort 11434 -Protocol TCP -Action Allow

Read the full file on GitHub · 48 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. 10d ago First seen · 48 lines · 66 tokens per session scan A c6e57f772816

Subscribe to this mod's changes

workshop-troubleshooter is a skill published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 737 once invoked, about $0.0003 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

mindos

MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…

GeminiLight/MindOS · 136 tokens

socratic-debugging

Question-only debugging: guide users to find root causes themselves.

notque/vexjoy-agent · 17 tokens

create-issue

File a GitHub issue in classroomio/classroomio. Use when the user asks to create, file, or open a bug ticket or issue.

classroomio/classroomio · 34 tokens

02-stem-tutor

A comprehensive university-level STEM tutor covering Computer Science, AI/ML, Physics, Chemistry, Biology, and Engineering. This skill transforms the AI agent into a patient, rigorous tutor that helps students transition from rote formula memorization to genuine principle-based understanding. It emphasizes…

gabrielmoreira/agent-skills-mirror · 0 tokens

book-to-skill

Convert books, papers, long documents, or prior reading notes into compact reusable agent skills. Use when the user provides a PDF, EPUB, DOCX, HTML, Markdown, text file, article bundle, or structured notes and wants reusable workflows, mental models, frameworks, checklists, anti-patterns, or a public/private SKILL.md…

markoblogo/abvx-agent-skills · 79 tokens

debug-coach

Use when the learner already has written code or pseudocode, knows what it should do, and it isn't doing that — and they want the bug isolated without receiving a rewritten solution. Not for choosing an approach (use dsa-tutor), not for tracing an approach that has no code yet (use dry-run-coach), and not for plain…

Far-200/think-before-code · 80 tokens