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 agents/amdresearch/ai4science-studio/fom_extractorgit clone --depth 1 https://github.com/AMDResearch/ai4science-studioWhat 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 | $0.00000 | $0.01491 |
| Opus 5 | $0.00000 | $0.00745 |
| Sonnet 5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
fom_extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fom_extractor subagent — ORBIT-2
Computes per-iteration FOMs for the ORBIT-2 loop and optionally TraceLens↔Omnistat correlation (reuse HydraGNN §4 algorithm when traces exist).
Inputs
<perf_run>/manifest.json— must includejob_id,runtime_seconds,global_batch_size,parallelism,data_type.<perf_run>/orbit2-train-<jobid>.out<perf_run>/omnistat-db/+ live VM URL (or start VM with-fs.disableMmap)<perf_run>/traces/*.pt.trace.json(rank-0 kineto)
Outputs
<perf_run>/foms.json— schema below<perf_run>/kernel_correlation.csv— optional; same column idea as HydraGNNfom_extractor.md
foms.json schema (ORBIT-2)
{
"job_id": "12345",
"primary_fom": "throughput_samples_per_s",
"throughput_samples_per_s": 1.23e4,
"steady_batch_time_s": 0.41,
"global_batch_size": 2048,
"mfma_bf16_tflops_per_card_avg": null,
"hbm_read_GBps_per_card_avg": null,
"xgmi_GBps_avg": null,
"loss_sanity_pass": true,
"final_loss": 0.05
}
Step 1 — Log FOMs (required)
Run the repo extractor (writes foms.json base fields):
python3 "$REPO_ROOT/earth_science/models/ORBIT-2/examples/run_fom_extractor.py" --job-dir "$PERF_RUN"
If manifest.json lacks global_batch_size, pass --global-batch-size explicitly.
Effective-batch integrity (read before trusting a throughput delta): foms.json includes
hbm_reserved_GB, hbm_reserved_pct_288, max_batches_per_epoch, throughput_method,
partial_step_fraction, and steady_realized_batch_dims. Throughput now prefers the
real per-step batch dim (throughput_method=real_per_step_batch, read from the EDM y.shape
line) instead of the nominal global_batch_size, so partial trailing batches no longer inflate it.
Still reject any cross-run comparison where partial_step_fraction, steady_realized_batch_dims,
hbm_reserved_pct_288, or max_batches_per_epoch deviates materially from the baseline — even a
correct number can hide a different work mix.
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.
- 3d ago First seen · 99 lines · 0 tokens per session scan A e6f33a4935c2
fom_extractor is an agent 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 1,491 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 agents, from other repositories
sft
Supervised fine-tuning pipeline reference. For config templates and dataset format examples, see getting-started.qmd and dataset-formats/.
by-liability-engineer
Actively propose mutations to fix identified sequence liabilities. Score mutations for structural impact, consider framework vs CDR context, generate ranked mutation panels with predicted impact, and output mutation tables with position, original, proposed, motif removed, and risk level.
by-design
Generate protein/antibody designs using available compute providers (Tamarind, local GPU). Creates tool inputs, submits jobs, and monitors progress.
by-screening
Score, filter, and rank designs. Run liability screening, developability checks, and composite scoring (ipSAE, ipTM, pLDDT). Present ranked candidates.
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
by-knowledge
Query and update the learning system. Store campaign outcomes, query similar campaigns, get scaffold rankings, record failures, and generate recommendations.