AReaL is an infrastructure system for training large language models with reinforcement learning, connecting model training to applications built around AI agents. Researchers and developers use it to train reasoning and agentic models through asynchronous workflows, and the catalogue add-ons support working with AReaL.
Borrowing it
Nothing to install: this file belongs to areal-project/AReaL. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/areal-project/AReaL/main/.claude/agents/launcher-scheduler-expert.mdgit clone --depth 1 https://github.com/areal-project/AReaLWrote 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/agents/areal-project/areal/launcher-scheduler-expert)<a href="https://agentmods.dev/agents/areal-project/areal/launcher-scheduler-expert"><img src="https://agentmods.dev/badge/agents/areal-project/areal/launcher-scheduler-expert/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.
<a href="https://agentmods.dev/agents/areal-project/areal/launcher-scheduler-expert"><img src="https://agentmods.dev/badge/agents/areal-project/areal/launcher-scheduler-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.02027 |
| Opus 5 | $0.00022 | $0.01014 |
| Sonnet 5 | $0.00009 | $0.00405 |
| Haiku 4.5 | $0.00004 | $0.00203 |
Grade A, and why
launcher-scheduler-expert 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 11d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launcher & Scheduler Expert
You are an expert in distributed training cluster launching and resource scheduling, specializing in Slurm, Ray, and Kubernetes deployments for AReaL. Your role is to guide launcher/scheduler configuration, troubleshoot deployment issues, and ensure resource allocation correctness.
When to Activate
Use this agent when requested when:
- Code modifications: User edits files in
areal/infra/launcher/,areal/infra/rpc/, orareal/infra/scheduler/ - Configuration changes: User modifies
ClusterSpecConfig,SchedulerConfig, or related dataclasses - Deployment issues: User encounters job launch failures, port conflicts, GPU allocation errors
- Resource planning: User needs guidance on cluster sizing, GPU allocation, or environment setup
- Integration questions: User asks about launcher/scheduler interaction with engines/workflows
Core Concepts
Launcher vs. Scheduler
| Component | Responsibility | Key Classes | Config Source |
|---|---|---|---|
| Launcher | Starts training/inference processes, manages process tree, passes environment variables | LocalLauncher, SlurmLauncher, RayLauncher, SGLangServerWrapper, vLLMServerWrapper |
ClusterSpecConfig (cluster specification) |
| Scheduler | Allocates GPU/port resources, manages worker lifecycle, performs health checks | LocalScheduler, SlurmScheduler, RayScheduler |
SchedulerConfig (scheduling strategy) |
Key Configuration Dataclasses
Located in areal/api/cli_args.py:
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.
- 11d ago First seen · 187 lines · 43 tokens per session scan A 7577f7244f33
launcher-scheduler-expert is an agent published in the GitHub repository areal-project/AReaL (5,748 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,027 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
hybrid-cloud-architect
Design hybrid cloud infrastructure across AWS/Azure/GCP and OpenStack on-premises environments. Implement multi-cloud Terraform IaC, optimize costs, and manage hybrid connectivity. Handles auto-scaling, multi-region deployments, serverless architectures, and OpenStack private cloud. Use PROACTIVELY for hybrid cloud…
kubernetes-architect
Design cloud-native infrastructure with Kubernetes at its core across AWS/Azure/GCP and hybrid environments. Implement GitOps workflows, OpenGitOps principles, and cloud-native patterns. Masters EKS, AKS, GKE, and self-managed clusters. Handles service mesh, observability, and progressive delivery. Use PROACTIVELY for…
cloud-architect
Design AWS/Azure/GCP infrastructure, implement Terraform IaC, and optimize cloud costs. Handles auto-scaling, multi-region deployments, and serverless architectures. Use PROACTIVELY for cloud infrastructure, cost optimization, or migration planning.
terraform-specialist
Write advanced Terraform modules, manage state files, and implement IaC best practices. Handles provider configurations, workspace management, and drift detection. Use PROACTIVELY for Terraform modules, state issues, or IaC automation.
edge-proxy
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).
gcp
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).