sglang

sglang is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 72 tokens per session (3,226 once invoked), scanned A, a copy of sglang, Apache-2.0.

A framework for serving language and vision-language models with fast response generation and reusable prompt context. It can restrict outputs to formats such as JSON or regular-expression patterns.

In plain words
What is it for?
Use it to build tool-using agents, cache shared conversation or tool prompts, generate structured output, and serve models.
Why use it?
It helps when applications repeatedly send the same instructions or need model responses to follow a strict structure.

Skill for Claude CodeCodex

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

Good fit Use it to build tool-using agents, cache shared conversation or tool prompts, generate structured output, and serve models.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthetic-sciences/openscience/sglang
About the project

synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.

synthetic-sciences/openscience · 3,501 stars · on GitHub · openscience.sh

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 synthetic-sciences/openscience --skill sglang
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 sglang

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/sglang.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/sglang)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/sglang"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/sglang.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% 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 $0.00072 $0.03226
Opus 5 $0.00036 $0.01613
Sonnet 5 $0.00014 $0.00645
Haiku 4.5 $0.00007 $0.00323

Measured 4d ago against content hash cee337564afa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sglang 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 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.

Makes network callslowCapability

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

curl http://localhost:30000/v1/chat/completions \
Origin

This is a copy

91% identical to sglang — 8 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.

backend/cli/skills/ml-inference/sglang/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SGLang

High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching.

When to use SGLang

Use SGLang when:

  • Need structured outputs (JSON, regex, grammar)
  • Building agents with repeated prefixes (system prompts, tools)
  • Agentic workflows with function calling
  • Multi-turn conversations with shared context
  • Need faster JSON decoding (3× vs standard)

Use vLLM instead when:

  • Simple text generation without structure
  • Don't need prefix caching
  • Want mature, widely-tested production system

Use TensorRT-LLM instead when:

  • Maximum single-request latency (no batching needed)
  • NVIDIA-only deployment
  • Need FP8/INT4 quantization on H100

Quick start

Installation

# pip install (recommended)
pip install "sglang[all]"

# With FlashInfer (faster, CUDA 11.8/12.1)
pip install sglang[all] flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/

# From source
git clone https://github.com/sgl-project/sglang.git
cd sglang
pip install -e "python[all]"

Launch server

# Basic server (Llama 3-8B)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
    --port 30000

# With RadixAttention (automatic prefix caching)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
    --port 30000 \
    --enable-radix-cache  # Default: enabled

# Multi-GPU (tensor parallelism)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-70B-Instruct \
    --tp 4 \
    --port 30000

Basic inference

import sglang as sgl

# Set backend
sgl.set_default_backend(sgl.OpenAI("http://localhost:30000/v1"))

# Simple generation
@sgl.function
def simple_gen(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", max_tokens=100)

# Run
state = simple_gen.run(question="What is the capital of France?")
print(state["answer"])
# Output: "The capital of France is Paris."

Structured JSON output

Read the full file on GitHub · 449 lines

Files

What ships with it

3 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 · 449 lines · 72 tokens per session scan A cee337564afa

Subscribe to this mod's changes

sglang is a skill published in the GitHub repository synthetic-sciences/openscience (3,501 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 3,226 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 91% identical to sglang, differing in 8 lines, and is treated as a copy.

Related

Other skills, from other repositories

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

davila7/claude-code-templates · 72 tokens

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Orchestra-Research/AI-Research-SKILLs · 72 tokens

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

OpenLAIR/dr-claw · 72 tokens

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

liortesta/ClawdAgent · 72 tokens

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

OpenLAIR/dr-claw-plugin-cc · 72 tokens

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

ihatesea69/HieuNghi-AI-Skills · 72 tokens