slime-rl-training

slime-rl-training is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 52 tokens per session (3,094 once invoked), scanned A, original, Apache-2.0.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Skill for Claude CodeCodex

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 skills/synthetic-sciences/openscience/slime
Any agent
npx skills add synthetic-sciences/openscience --skill slime
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

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/synthetic-sciences/openscience/slime.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/slime)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/slime"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/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 3,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00052 $0.03094
Opus 5 $0.00026 $0.01547
Sonnet 5 $0.00010 $0.00619
Haiku 4.5 $0.00005 $0.00309

Measured today against content hash 7b95512b262a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 today.

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.

backend/cli/skills/coding/slime/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 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

Hardware Requirements

  • Minimum: 2x A100 80GB (160 GB total VRAM) for 7B models
  • Recommended: 4x H100 80GB (320 GB total VRAM) for 70B+ models
  • Multi-node: InfiniBand required for cross-node communication
  • Storage: NVMe with 5+ TB for checkpoints

Cost Warning: slime workloads require significant GPU resources. Budget $10-25/hr for a single training node. Multi-node runs scale linearly.

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        │
└─────────────────────────┘ └─────────────────────────────┘

Read the full file on GitHub · 477 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. today First seen · 477 lines · 52 tokens per session scan A 7b95512b262a

Subscribe to this mod's changes

slime-rl-training is a skill published in the GitHub repository synthetic-sciences/openscience (3,432 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 3,094 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

OpenLAIR/dr-claw · 52 tokens

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Orchestra-Research/AI-Research-SKILLs · 52 tokens

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

ihatesea69/HieuNghi-AI-Skills · 52 tokens

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

davila7/claude-code-templates · 52 tokens

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

liortesta/ClawdAgent · 52 tokens

grpo-rl-training

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

OpenLAIR/dr-claw · 26 tokens