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 agentmods add commands/amdresearch/ai4science-studio/run-perf-orbit2git clone --depth 1 https://github.com/AMDResearch/ai4science-studioWrote 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/amdresearch/ai4science-studio/run-perf-orbit2)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-perf-orbit2"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-perf-orbit2.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02205 |
| Opus 5 | $0.00000 | $0.01103 |
| Sonnet 5 | $0.00000 | $0.00441 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade A, and why
run-perf-orbit2 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 5d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run ORBIT-2 perf-analysis or perf-optimizer-loop on an AMD cluster
Guide the user through performance engineering workflows for ORBIT-2 (Bayes-CAST EDM / same-dir timing configs): one-shot perf-analysis (TraceLens + Omnistat diagnosis) or iterative perf-optimizer-loop (accept/revert on throughput). This is not inference/visualization — use /run-orbit2 for that.
Recipe docs: earth_science/models/ORBIT-2/recipes/perf-analysis/README.md, earth_science/models/ORBIT-2/recipes/perf-optimizer-loop/README.md.
Orchestration reference (Cursor / any agent): read .cursor/skills/ai4science-perf-analysis/SKILL.md for the launcher → analyst → verifier → synthesizer loop.
Step 0 — Cluster config check (required)
Read .cluster-config.yaml (repo root) or ~/.config/ai4science-studio/cluster.yaml.
Required for perf recipes:
paths.scratch(or equivalent) → use asAI4S_SHARED_DIR(same convention as other studio scripts).perf_tools.dir→ use asPERF_TOOLS_DIR(layout:perf-inspect/,omnistat-src/,victoriametrics/). If missing or empty, stop and tell the user to re-run/init-clusterand answer Q9 (Performance tooling).
Pre-fill SLURM partition/account from slurm.partition / slurm.account when present.
Runtime note: Perf workflows here assume Apptainer + SLURM (same as sbatch_train_perf_amd.sh). There is no Docker perf path in the recipes.
Step 1 — Questionnaire (ask ALL questions before doing anything)
Ask the following. Do not assume defaults. Wait for answers before proceeding.
Q0. Mode
- perf-analysis — Submit one training perf job; after it finishes, drive subagents per
ai4science-perf-analysisSKILL (agents/launcher.md, analysts, verifiers,synthesizer.md) to producecombined_report.md. - perf-optimizer-loop — Iterative loop: one lever per iteration, accept/revert on
throughput_samples_per_swithloss_sanity_passas a control (see perf-optimizer-loop README).
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.
- 5d ago First seen · 165 lines · 0 tokens per session scan A 9f2d90981764
run-perf-orbit2 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 2,205 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.
Other commands, from other repositories
by:campaign-auto
Full autonomous campaign — research, design, screen, rank with minimal interruption.
by:load
Load a protein target and analyze it for design.
by:approve-lab
Approve lab submission to Adaptyv Bio (triple-gated).
watch
Watch live pipeline progress for a design run.
ml-project
Start a professional AI/ML research-engineer workflow for a task (any domain - CV, medical imaging, NLP/LLM, tabular, time-series). Researches papers first, picks the best method, trains/evaluates rigorously and honestly.
checklist
Generate a custom checklist for the current feature based on user requirements.