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 skills add JAICHANGPARK/workshop-harness --skill workshop-troubleshootergit clone --depth 1 https://github.com/JAICHANGPARK/workshop-harnessWrote 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.
[](https://agentmods.dev/skills/jaichangpark/workshop-harness/workshop-troubleshooter)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 10d ago First seen · 48 lines · 66 tokens per session scan A c6e57f772816
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.
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…
socratic-debugging
Question-only debugging: guide users to find root causes themselves.
create-issue
File a GitHub issue in classroomio/classroomio. Use when the user asks to create, file, or open a bug ticket or issue.
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…
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…
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…