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 HCAI-Lab-GT/gt-hive --skill pace-phoenixgit clone --depth 1 https://github.com/HCAI-Lab-GT/gt-hiveWrote 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/hcai-lab-gt/gt-hive/pace-phoenix)<a href="https://agentmods.dev/skills/hcai-lab-gt/gt-hive/pace-phoenix"><img src="https://agentmods.dev/badge/skills/hcai-lab-gt/gt-hive/pace-phoenix/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/hcai-lab-gt/gt-hive/pace-phoenix"><img src="https://agentmods.dev/badge/skills/hcai-lab-gt/gt-hive/pace-phoenix.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 | $0.00069 | $0.02879 |
| Opus 5 | $0.00034 | $0.01439 |
| Sonnet 5 | $0.00014 | $0.00576 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
pace-phoenix 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACE Phoenix Overlay
This skill is the Phoenix-specific overlay for Georgia Tech PACE. It adds site
facts that slurm-core deliberately does not know.
What this overlay adds
Load this skill when the user is working on (or asking about) the PACE Phoenix
research cluster at Georgia Tech. The overlay supplies Phoenix-specific
account naming, QOS policies, partition and constraint conventions, GPU types,
storage tiers, login/portal endpoints, and cost guidance — plus the
VERIFY_ON_PACE discipline for user/group-specific values.
The layered model is: load slurm-core for portable Slurm patterns
(sbatch, srun, salloc, sacct, job arrays, dependencies, debugging
checklists), plus this overlay for Phoenix-specific account/QOS/storage/cost
decisions. Do not duplicate slurm-core content here; reference it instead.
Ground truth for every claim in this skill is docs/PACE Documentation/
(an export of the official PACE knowledge base). When in doubt, re-verify
against those docs and cite the specific page used.
Operating defaults
- Default cluster: Phoenix.
- Default QOS:
inferno(paid production path; max wallclock 8 days; base priority). - Free-tier QOS:
embers(free; preemptible after 1 hour wallclock; max 8-hour wallclock; runs as backfill). - Account naming pattern:
gts-<PI_username>[-CODA20|-FY20PhaseN|-paid|-startup](perUsing Slurm on Phoenix.md). Substitute<PI_username>with the user's PI's GT username; suffix variants are optional. - Free-tier allowance: 10k CPU-hours/month on the institute-sponsored
gts-<PI_username>account, billed against base CPU-192GB nodes; credits reset on the 1st of each month (perUsing Slurm on Phoenix.md). - Login endpoint:
<gt-login-host-redacted>(ssh <gt_username>@<gt-login-host-redacted>). - OnDemand portal:
https://ondemand-phoenix.pace.gatech.edu/. - Account/quota discovery: use
pace-quotaon a Phoenix login node to discover charge accounts and storage usage. Do not invent an account. - Cluster size (stale-sensitive — re-verify against PACE docs): ~1393 base
nodes from Phase 1–6 migration completed Feb 2023; plus 54 cpu-gnr (Granite
Rapids) CPU nodes added Oct 2025; plus 3 gpu-rtxpro-blackwell GPU nodes total
per current
Phoenix Cluster Resources.mdinventory table (2 of those were added Oct 2025 perUsing Slurm on Phoenix.md; subsequent additions are undated in current docs — check the inventory table for the current count).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 222 lines · 69 tokens per session scan A 6b5eaa989d45
pace-phoenix is a skill published in the GitHub repository HCAI-Lab-GT/gt-hive (4 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,879 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
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
modal-compute
Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman research workflow needs burst remote GPU compute and the Modal CLI is available.
dnanexus-integration
DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.