slime-rl-training

slime-rl-training is a skill for Claude Code, Codex from braxtonROSE4/zorro-agent. It costs 52 tokens per session (2,976 once invoked), scanned A, a copy of slime, MIT.

Guidance for training language models with reinforcement learning, a method where model behaviour is improved using scored or rewarded examples. Slime connects Megatron-LM for training with SGLang for generating responses during training.

In plain words
What is it for?
It is for post-training GLM, Qwen3, DeepSeek, or Llama models, creating training data during runs, and using Megatron-LM with SGLang.
Why use it?
It gives teams a defined workflow for coordinating model training, response generation, and stored training data across these systems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for post-training GLM, Qwen3, DeepSeek, or Llama models, creating training data during runs, and using Megatron-LM with SGLang.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/braxtonrose4/zorro-agent/slime
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 braxtonROSE4/zorro-agent --skill slime
Clone the repo
git clone --depth 1 https://github.com/braxtonROSE4/zorro-agent

Made for: Claude Code, Codex.

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 slime-rl-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/braxtonrose4/zorro-agent/slime.svg)](https://agentmods.dev/skills/braxtonrose4/zorro-agent/slime)
Your own site
<a href="https://agentmods.dev/skills/braxtonrose4/zorro-agent/slime"><img src="https://agentmods.dev/badge/skills/braxtonrose4/zorro-agent/slime.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,976 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 92% 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 $0.00052 $0.02976
Opus 5 $0.00026 $0.01488
Sonnet 5 $0.00010 $0.00595
Haiku 4.5 $0.00005 $0.00298

Measured 8d ago against content hash b4d2cd12c759, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

slime-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 8d 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

92% identical to slime — 7 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.

optional-skills/mlops/slime/SKILL.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

slime: LLM Post-Training Framework for RL Scaling

slime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects Megatron-LM for training with SGLang for high-throughput rollout generation.

When to Use slime

Choose slime when you need:

  • Megatron-LM native training with SGLang inference
  • Custom data generation workflows with flexible data buffers
  • Training GLM, Qwen3, DeepSeek V3, or Llama 3 models
  • Research-grade framework with production backing (Z.ai)

Consider alternatives when:

  • You need enterprise-grade stability features → use miles
  • You want flexible backend swapping → use verl
  • You need PyTorch-native abstractions → use torchforge

Key Features

  • Training: Megatron-LM with full parallelism support (TP, PP, DP, SP)
  • Rollout: SGLang-based high-throughput generation with router
  • Data Buffer: Flexible prompt management and sample storage
  • Models: GLM-4.x, Qwen3, DeepSeek V3/R1, Llama 3

Architecture Overview

┌─────────────────────────────────────────────────────────┐
│                    Data Buffer                          │
│ - Prompt initialization and management                  │
│ - Custom data generation and filtering                  │
│ - Rollout sample storage                                │
└─────────────┬───────────────────────────┬───────────────┘
              │                           │
┌─────────────▼───────────┐ ┌─────────────▼───────────────┐
│ Training (Megatron-LM)  │ │ Rollout (SGLang + Router)   │
│ - Actor model training  │ │ - Response generation       │
│ - Critic (optional)     │ │ - Reward/verifier output    │
│ - Weight sync to rollout│ │ - Multi-turn support        │
└─────────────────────────┘ └─────────────────────────────┘

Installation

# Recommended: Docker
docker pull slimerl/slime:latest
docker run --rm --gpus all --ipc=host --shm-size=16g \
  -it slimerl/slime:latest /bin/bash

# Inside container
cd /root/slime && pip install -e . --no-deps

Read the full file on GitHub · 468 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. 8d ago First seen · 468 lines · 52 tokens per session scan A b4d2cd12c759

Subscribe to this mod's changes

slime-rl-training is a skill published in the GitHub repository braxtonROSE4/zorro-agent (8 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 2,976 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to slime, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

LQF_Machine_Learning_Expert_Guide

LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…

foryourhealth111-pixel/Vibe-Skills · 152 tokens

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

foryourhealth111-pixel/Vibe-Skills · 62 tokens

scientific-data-preprocessing

⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization…

foryourhealth111-pixel/Vibe-Skills · 137 tokens

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens