verl-rl-training

verl-rl-training is a skill for Claude Code from liortesta/ClawdAgent. It costs 51 tokens per session (2,768 once invoked), scanned A, a copy of verl-rl-training, Apache-2.0.

Guidance for verl, a framework for training large language models with reinforcement learning. It supports several training and text-generation backends, so the systems used for learning and generating samples can be selected separately.

In plain words
What is it for?
Use it for RLHF, PPO, GRPO, DAPO, RLOO, and related post-training methods, including multi-turn tool use and vision-language model training.
Why use it?
It reduces the work needed to assemble reinforcement-learning training at scale and lets you change infrastructure components as requirements change.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for RLHF, PPO, GRPO, DAPO, RLOO, and related post-training methods, including multi-turn tool use and vision-language model training.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liortesta/clawdagent/verl
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.

Any agent
npx skills add liortesta/ClawdAgent --skill verl
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

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 verl-rl-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/liortesta/clawdagent/verl.svg)](https://agentmods.dev/skills/liortesta/clawdagent/verl)
Your own site
<a href="https://agentmods.dev/skills/liortesta/clawdagent/verl"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/verl.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00051 $0.02768
Opus 5 $0.00026 $0.01384
Sonnet 5 $0.00010 $0.00554
Haiku 4.5 $0.00005 $0.00277

Measured 4d ago against content hash 1167e2b2994c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verl-rl-training 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 4d 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.

Origin

This is a copy

100% identical to verl-rl-training — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/06-post-training/verl/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed team. It implements the HybridFlow framework (EuroSys 2025) and powers models like Doubao-1.5-pro achieving O1-level performance on math benchmarks.

When to Use verl

Choose verl when you need:

  • Production-ready RL training at scale (tested up to 671B parameters)
  • Flexibility to swap backends (FSDP ↔ Megatron-LM ↔ vLLM ↔ SGLang)
  • Support for multiple RL algorithms (PPO, GRPO, RLOO, REINFORCE++, DAPO)
  • Multi-turn rollout with tool calling for agentic workflows
  • Vision-language model RL training

Consider alternatives when:

  • You need Megatron-native training → use slime or miles
  • You want PyTorch-native abstractions with Monarch → use torchforge
  • You only need simple SFT/DPO → use TRL or Axolotl

Key Features

  • Training backends: FSDP, FSDP2, Megatron-LM
  • Rollout engines: vLLM, SGLang, HuggingFace Transformers
  • Algorithms: PPO, GRPO, DAPO, RLOO, ReMax, REINFORCE++, SPIN, SPPO
  • Models: Qwen-3, Llama-3.1, DeepSeek, Gemma-2 (0.5B to 671B)
  • Advanced: LoRA RL, sequence parallelism, expert parallelism, multi-turn tools

Installation

# Option 1: pip install
pip install verl[vllm]  # or verl[sglang] for SGLang backend

# Option 2: Docker (recommended for production)
docker pull verlai/verl:vllm011.latest

# Option 3: From source
git clone https://github.com/volcengine/verl.git
cd verl && pip install -e .[vllm,math]

Quick Start: GRPO Training

python3 -m verl.trainer.main_ppo \
    algorithm.adv_estimator=grpo \
    data.train_files=~/data/gsm8k/train.parquet \
    actor_rollout_ref.model.path=Qwen/Qwen2.5-7B \
    actor_rollout_ref.rollout.n=8 \
    actor_rollout_ref.actor.use_kl_loss=True \
    trainer.n_gpus_per_node=8

Core Architecture

verl uses a HybridFlow programming model separating control flow from computation:

Read the full file on GitHub · 392 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 392 lines · 51 tokens per session scan A 1167e2b2994c

Subscribe to this mod's changes

verl-rl-training is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,768 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to verl-rl-training, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

davila7/claude-code-templates · 51 tokens

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

OpenLAIR/dr-claw · 51 tokens

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

ihatesea69/HieuNghi-AI-Skills · 51 tokens

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

davila7/claude-code-templates · 26 tokens

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

davila7/claude-code-templates · 72 tokens