ai4science-studio: Command for Claude Code

.claude/commands/run-perf-hydragnn.md

run-perf-hydragnn is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (1,779 once invoked), scanned A, original, MIT.

A guided workflow for measuring and improving HydraGNN, a scientific graph-based model, on an AMD cluster. It either diagnoses performance once or repeatedly tests changes using training time.

In plain words
What is it for?
Use it to run a two-node performance analysis or an accept-or-revert optimization loop. It is for training speed work, not ensemble prediction.
Why use it?
It helps find slow parts of HydraGNN training and checks whether a change reduces the time needed for each training period.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is AMDResearch/ai4science-studio's own configuration. It tells Claude Code how to work on ai4science-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai4science-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AMDResearch/ai4science-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AMDResearch/ai4science-studio/main/.claude/commands/run-perf-hydragnn.md
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Claude Code.

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 run-perf-hydragnn

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-perf-hydragnn/github.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/run-perf-hydragnn)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-perf-hydragnn"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-perf-hydragnn/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 run-perf-hydragnn

Your own site · 80×15
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-perf-hydragnn"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-perf-hydragnn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,779 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 $0.00000 $0.01779
Opus 5 $0.00000 $0.00890
Sonnet 5 $0.00000 $0.00356
Haiku 4.5 $0.00000 $0.00178

Measured 10d ago against content hash a870cede2573, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

run-perf-hydragnn 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.

.claude/commands/run-perf-hydragnn.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run HydraGNN perf-analysis or perf-optimizer-loop on an AMD cluster

Guide the user through performance engineering for HydraGNN Predictive GFM: one-shot perf-analysis (2-node training + TraceLens + Omnistat diagnosis) or iterative perf-optimizer-loop (accept/revert on epoch_time_s). This is not ensemble inference — use /run-hydragnn for that.

Recipe docs: material_science/models/HydraGNN/recipes/perf-analysis/README.md, material_science/models/HydraGNN/recipes/perf-optimizer-loop/README.md.

Attribution / levers: dispatch-attribution.md, lever_catalog.yaml.

Orchestration reference: .cursor/skills/ai4science-perf-analysis/SKILL.md (launcher → parallel analysts → parallel verifiers → synthesizer).

Step 0 — Cluster config check (required)

Read .cluster-config.yaml (repo root) or ~/.config/ai4science-studio/cluster.yaml.

Required for perf recipes:

  • Set AI4S_SHARED_DIR from cluster config (paths.scratch or documented scratch root).
  • Set PERF_TOOLS_DIR from perf_tools.dir. If missing, stop and send the user to /init-cluster Q9 (Performance tooling).

Pre-fill SLURM partition/account from config.

Runtime: Apptainer + SLURM only (sbatch_train_perf_amd.sh).


Step 1 — Questionnaire (ask ALL before acting)

Q0. Mode

  • perf-analysis — One 2-node perf job + post-hoc multi-subagent analysis (default topology for this recipe).
  • perf-optimizer-loop — Iterative tuning; primary FOM epoch_time_s (lower is better); see recipes/perf-optimizer-loop/README.md for stop rules and do_not_retry.json.

Q1. HydraGNN checkout (HG_REPO_DIR)

Default in sbatch: $AI4S_SHARED_DIR/models/HydraGNN/code/HydraGNN (cloned at pinned SHA if missing).

Read the full file on GitHub · 147 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 · 147 lines · 0 tokens per session scan A a870cede2573

Subscribe to this mod's changes

run-perf-hydragnn is a command published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,779 tokens. 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.