An interactive guide to Georgia Tech's PACE high-performance computing clusters, Phoenix and ICE. It routes questions to guidance for Slurm, a job-scheduling system, cluster-specific settings, storage, and connections.

Use it for submitting jobs, requesting GPUs, transferring files, troubleshooting failures, connecting by SSH or a web portal, and checking cluster specifications.

It helps users reach the right instructions without knowing which cluster or technical topic applies.

pace-guide — Command for Claude Code by HCAI-Lab-GT

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.

Clone the repo

git clone --depth 1 https://github.com/HCAI-Lab-GT/gt-hive

Made for: Claude Code.

Or install gt-hive-pace, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-guide/github.svg)](https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-guide)

Your own site

<a href="https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-guide"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-guide"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,175 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.01175
Opus 5	$0.00012	$0.00588
Sonnet 5	$0.00005	$0.00235
Haiku 4.5	$0.00002	$0.00118

Measured 9d ago against content hash 296d27c05382, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pace-guide 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 9d 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.

claude/commands/pace-guide.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PACE HPC Interactive Router

You are helping a user with Georgia Tech's PACE HPC clusters. Present the routing options below using AskUserQuestion, then load the appropriate layered skills based on their selection.

This command routes between three skills:

slurm-core -- generic Slurm job control, scripting, and debugging.
pace-phoenix -- Phoenix-specific charge accounts, QOS, GPU types, storage paths.
pace-ice -- ICE-specific instructional defaults, GPU types, storage paths.

Step 1: Ask What They Need

Use AskUserQuestion with these options:

Option	Label	Description
1	Submit a job	Get Slurm job script templates and submission guidance
2	Request GPUs	GPU syntax, types, and cluster-specific availability
3	Storage / file transfer	Storage tiers, quotas, Globus, SCP, OnDemand
4	Troubleshoot a job	Diagnose pending, failed, or OOM jobs
5	Connect to a cluster	SSH, VPN, OnDemand portal links
6	Explore cluster specs	Node types, partitions, QOS limits

Step 2: Cluster Routing

For options 1, 2, 3, and 6, ask which cluster the user is working with (Phoenix or ICE) using AskUserQuestion -- unless context already makes it clear.

Phoenix indicators: charge account (gts-*), inferno/embers QOS, research context, PI mention, project storage paths.

ICE indicators: course-related work, AI Makerspace, instructional context, <gt-login-host-redacted>.

If the user is working with a generic Slurm cluster (not PACE) or has not identified a specific cluster, fall back to loading slurm-core only.

Step 3: Load Skills

Pick the layered skills based on cluster:

Phoenix -> load slurm-core + pace-phoenix.
ICE -> load slurm-core + pace-ice.
Generic Slurm / unknown cluster -> load slurm-core only.

Within each loaded skill, consult its SKILL.md and references/ directory for the specific topic the user asked about.

Submit a job

From slurm-core: read references/core-workflows.md for the base sbatch template, common directives, and submission patterns.
From pace-phoenix (if Phoenix): read references/workflows.md and references/cost-model.md for charge-account, QOS, and GPU-type adaptations. Read references/phoenix-local-notes.md for storage paths.
From pace-ice (if ICE): read references/workflows.md for instructional defaults (no -A, no -q) and references/ice-local-notes.md for storage paths.

Read the full file on GitHub · 106 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.

9d ago First seen · 106 lines · 23 tokens per session scan A 296d27c05382

Subscribe to this mod's changes

pace-guide is a command published in the GitHub repository HCAI-Lab-GT/gt-hive (4 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,175 once invoked, about $0.0001 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.

Cloud DevOps and cloud

cost-optimize

You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…

wshobson/agents · 0 tokens

deploy

Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.

butterbase-ai/butterbase-skills · 20 tokens

integrate

Set up third-party service integrations.

nxtg-ai/forge-plugin · 6 tokens

env

Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.

vercel/vercel-plugin · 35 tokens

scan

Scan AWS account for cost optimization.

prajapatimehul/claude-aws-cost-saver · 6 tokens

finops-feedback

Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.

glassity/agent-skills · 57 tokens