agentmods.dev

orchestrator

orchestrator is an agent for coding agents from AMDResearch/ai4science-studio. It costs 0 tokens per session (1,060 once invoked), scanned A, original, MIT.

An automated loop for improving the speed of ORBIT-2 workloads on MI355X-class hardware. It coordinates several analysis agents, tests configuration changes, and records whether to keep or undo them.

In plain words
What is it for?
Use it to run ORBIT-2 performance-optimization loops, select tuning changes, analyze throughput, and save iteration reports and run status.
Why use it?
It removes the need to manually manage repeated performance tests, compare results, handle failed machines, and track each change.

Agent

not rated 4 1mo ago A scan 0 tokens original MIT
View the source file AMDResearch/ai4science-studio
Install

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.

agentmods
npx agentmods add agents/amdresearch/ai4science-studio/orchestrator
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/orchestrator.svg)](https://agentmods.dev/agents/amdresearch/ai4science-studio/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/amdresearch/ai4science-studio/orchestrator"><img src="https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/orchestrator.svg" alt="Measured on agentmods" 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 1,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01060
Opus 5 $0.00000 $0.00530
Sonnet 5 $0.00000 $0.00212
Haiku 4.5 $0.00000 $0.00106

Measured 3d ago against content hash 351c88e9981a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator 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.

earth_science/models/ORBIT-2/recipes/perf-optimizer-loop/agents/orchestrator.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orchestrator subagent — ORBIT-2 iterative sysopt loop

Drives the ORBIT-2 (Bayes-CAST EDM) optimizer loop on MI355X-class hardware. Dispatches launcher + lever_picker + fom_extractor + perf-analysis analysts/verifiers/synth + story_writer. Owns accept/revert on throughput_samples_per_s, STATUS.txt, STOP, and broken-node exit 42 handling.

HydraGNN reference: mirror control flow in material_science/models/HydraGNN/recipes/perf-optimizer-loop/agents/orchestrator.md; this file only lists ORBIT-2 deltas.

Inputs

  • Loop args: <loop-uuid>, <n_iters_budget>.
  • REPO_ROOT (cwd or env).
  • .cluster-config.yaml (partition, perf_tools.dir).
  • ../lever_catalog.yaml.

Outputs

Under $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/loop-<uuid>/:

  • STATUS.txt, foms.csv, do_not_retry.json, known_bad_nodes.txt, iter-N-<lever>.json → symlink to ../<jobid>/manifest.json, iter-N-env.sh, iter-N-hook.py (when rank_script_patch).

Per job: existing perf-analysis layout under ../<jobid>/ plus foms.json from examples/run_fom_extractor.py (extend with PromQL/kernel_correlation per fom_extractor.md when tooling is available).

ORBIT-2-specific hard constraints

  1. Single concurrent SLURM job — same as HydraGNN.
  2. One lever per iteration — same.
  3. sbatch entrypoint: earth_science/models/ORBIT-2/examples/sbatch_train_perf_amd.sh (from REPO_ROOT).
  4. Rank hooks: set export ORBIT2_RANK_PRE_TRAIN_HOOK=/abs/path/iter-N-hook.py before sbatch so the wrapper expands it into the generated rank script (sbatch_train_perf_amd.sh reads this at submit time). For Bayes EDM the default hook is empty; profiler hook is optional. Hooks are executed via orbit2_rank_hook_runner.py before train_edm.py.
  5. Env file: source loop-<uuid>/iter-N-env.sh then sbatch with --export=ALL plus any ORBIT2_* / NCCL_* overrides from the lever. Match HydraGNN pattern in run_optimizer_loop.sh driver.
  6. Primary FOM (accept/revert): throughput_samples_per_s from <jobid>/foms.json (higher is better). Control: loss_sanity_pass must stay true; if final_loss blows up vs baseline, reject (same 1.5× rule as HydraGNN optional for ORBIT timing runs).
  7. Baseline iter-0: lever_id=baseline with saturated ORBIT2_BATCH_SIZE from BASELINE_LOCKIN.md + bf16 + SDPA.
  8. Exit 42 (mount probe): identical retry with --exclude — do not add lever to do_not_retry.json (see ai4science-perf-analysis SKILL).

Read the full file on GitHub · 54 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. 3d ago First seen · 54 lines · 0 tokens per session scan A 351c88e9981a

Subscribe to this mod's changes

orchestrator 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 1,060 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.

Analytics and metricsBuilding agentsai-for-scienceamddrug-discoveryearth-sciencefine-tuninghealthcare
Related

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/.

axolotl-ai-cloud/axolotl · 0 tokens

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.

001TMF/blatant-why · 55 tokens

by-campaign

Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.

001TMF/blatant-why · 33 tokens

by-plan-checker

Review campaign plans for completeness and correctness before user approval. Checks fold validation, cost estimates, modality selection, parameters, and scaffold justification.

001TMF/blatant-why · 32 tokens

by-knowledge

Query and update the learning system. Store campaign outcomes, query similar campaigns, get scaffold rankings, record failures, and generate recommendations.

001TMF/blatant-why · 30 tokens

grounded-review-writer

Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.

gaotiexinqu/OneResearchClaw · 22 tokens