launcher

launcher is an agent for coding agents from AMDResearch/ai4science-studio. It costs 0 tokens per session (2,762 once invoked), scanned A, original, MIT.

A job launcher for two-node ORBIT-2 training on AMD Instinct MI355X GPUs. It also records PyTorch profiling data and Omnistat telemetry, which is machine-performance monitoring information.

In plain words
What is it for?
Submitting training through SLURM, collecting logs and traces, running performance tools, and saving the run metadata for performance extraction.
Why use it?
It packages the training run and its measurements into a manifest and organized output directory for later analysis.

Agent

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/launcher
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 launcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/launcher.svg)](https://agentmods.dev/agents/amdresearch/ai4science-studio/launcher)
Your own site
<a href="https://agentmods.dev/agents/amdresearch/ai4science-studio/launcher"><img src="https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/launcher.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 2,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.02762
Opus 5 $0.00000 $0.01381
Sonnet 5 $0.00000 $0.00552
Haiku 4.5 $0.00000 $0.00276

Measured 3d ago against content hash 32bf86c4796b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

launcher scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

VM_VERSION=$(curl -fsSL https://api.github.com/repos/VictoriaMetrics/VictoriaMetrics/releases/latest | grep '"tag_name":' | sed -E 's/.*"([^"]+)".*/\1/')
earth_science/models/ORBIT-2/recipes/perf-analysis/agents/launcher.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

launcher subagent

Submits a 2-node ORBIT-2 training (AMD Instinct MI355X) with PyTorch profiling and Omnistat user-mode telemetry, waits for completion, and writes manifest.json for downstream subagents.

Inputs

  • The ai4science-studio repo checkout ($REPO_ROOT).
  • Cluster config at .cluster-config.yaml (partition/account, shared dirs).
  • Optional env-var overrides: ORBIT2_BATCH_SIZE, HYDRAGNN_MAX_NUM_BATCH, ORBIT2_NUM_EPOCH, ORBIT2_PRECISION, PROFILE_TARGET_EPOCH.

Outputs

  • ${PERF_TOOLS_DIR}/perf-inspect/ — Python venv with omnistat (PR #271 + main merged) and TraceLens.
  • ${PERF_TOOLS_DIR}/victoriametrics/victoria-metrics-prod — VictoriaMetrics binary.
  • $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/omnistat.config — Omnistat user-mode config.
  • $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/manifest.json — manifest schema below.
  • $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/orbit2-train-<jobid>.out — symlinked from output dir.
  • $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/logs/ — symlinked rank-0 trace.
  • $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/omnistat-db/ — VictoriaMetrics datadir.

Manifest schema

{
  "jobid": "<int as str>",
  "submitted_at": "ISO 8601 UTC",
  "completed_at": "ISO 8601 UTC",
  "exit_state": "COMPLETED|FAILED|TIMEOUT|...",
  "nodes": 2,
  "gpus_per_node": 8,
  "ranks": 16,
  "nodelist": "<node-a>,<node-b>",
  "partition": "<partition>",
  "account": "<account>",
  "runtime_seconds": <float>,
  "config_used": "<path to interm_8m_with_profile.json>",
  "profile_target_epoch": <int>,
  "trace_paths": ["<path to .pt.trace.json>"],
  "omnistat_db_path": "<dir>",
  "training_log_path": "<path>",
  "perf_run_dir": "<dir>",
  "hg_precision": "fp64",
  "hg_batch_size": 200,
  "hg_num_epoch": 2,
  "orbit2_max_num_batch": 30,
  "tools_versions": {
    "omnistat_commit": "<sha>",
    "tracelens_commit": "<sha>",
    "victoriametrics_version": "<v>"
  }
}

Steps

1. Lazy install tools (idempotent)

Read the full file on GitHub · 216 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 · 216 lines · 0 tokens per session scan A 32bf86c4796b

Subscribe to this mod's changes

launcher 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 2,762 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

by-epitope

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why · 58 tokens

by-research-synthesizer

Synthesizes outputs from 4 parallel research agents into a unified target report. Reads targetstructures.json, targetsequence.json, priorart.json, and epitopeanalysis.json. Produces targetreport.json and researchreport.md.

001TMF/blatant-why · 55 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-prior-art-researcher

Parallel prior art research via SAbDab, PubMed, bioRxiv, and literature. Finds existing binders, antibodies, nanobodies against the target. Maps the competitive landscape.

001TMF/blatant-why · 47 tokens

by-design

Generate protein/antibody designs using available compute providers (Tamarind, local GPU). Creates tool inputs, submits jobs, and monitors progress.

001TMF/blatant-why · 32 tokens

by-diversity

Analyze sequence and structural diversity across a design set. Sequence clustering, structural clustering, Pareto front analysis, scaffold balance, phylogenetic dendrograms, and diverse panel selection.

001TMF/blatant-why · 41 tokens