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.
git 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/commands/hcai-lab-gt/gt-hive/pace-sbatch)<a href="https://agentmods.dev/commands/hcai-lab-gt/gt-hive/pace-sbatch"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-sbatch/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/commands/hcai-lab-gt/gt-hive/pace-sbatch"><img src="https://agentmods.dev/badge/commands/hcai-lab-gt/gt-hive/pace-sbatch.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 | $0.00025 | $0.00866 |
| Opus 5 | $0.00013 | $0.00433 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
pace-sbatch 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sbatch wizard
Draft a Slurm batch script through structured questions. Use this command when the user wants a runnable sbatch file fast and is happier clicking through options than describing every directive in prose.
Step 1: cluster
Use AskUserQuestion with these options:
| Option | Label | Description |
|---|---|---|
| 1 | Phoenix | Georgia Tech research cluster (gts-* accounts, inferno/embers QOS) |
| 2 | ICE | Georgia Tech instructional cluster (no -A, no manual partition) |
| 3 | Generic Slurm | A non-PACE Slurm site |
Step 2: workload
Use AskUserQuestion:
| Option | Label | Description |
|---|---|---|
| 1 | CPU | CPU-only batch job |
| 2 | Single GPU | One GPU on one node |
| 3 | Multi-GPU | Multiple GPUs (single node or multi-node) |
| 4 | Array | Array of independent tasks |
| 5 | MPI | Distributed MPI workload (uses srun, never mpirun) |
Step 3: basic params
Use a single grouped AskUserQuestion to collect cores, memory (GB), and
walltime (HH:MM:SS). Provide sensible defaults: 4 cores, 16 GB, 02:00:00.
Step 4: GPU type (only if Step 2 was GPU)
Look up the cluster's available GPU types:
- Phoenix: read
pace-phoenix/references/workflows.mdfor the H100 / H200 / L40S / RTX 6000 / Blackwell list and the per-GPU core ratios. - ICE: read
pace-ice/references/workflows.mdfor the ICE GPU list.
Present those GPUs as AskUserQuestion options.
Step 5: load skills and draft the script
Load skills based on cluster:
- Phoenix ->
slurm-core+pace-phoenix. - ICE ->
slurm-core+pace-ice. - Generic Slurm ->
slurm-coreonly.
Read slurm-core/references/core-workflows.md for the base sbatch template
and the cluster overlay's references/workflows.md for site-specific
directives.
Draft a complete .sbatch file with long-form Slurm directives. For values
the agent cannot know, emit the VERIFY_ON_PACE marker pattern from the
overlay paired with the discovery command:
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 · 86 lines · 25 tokens per session scan A c669c272c623
pace-sbatch is a command published in the GitHub repository HCAI-Lab-GT/gt-hive (4 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 866 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.
Other commands, from other repositories
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
graphite-morphology-classify
Classify graphite in a cast-iron micrograph per ASTM A247 / ISO 945-1, quantify nodularity, and read the matrix — the single most diagnostic observation in a cast-iron case.