sglang: Skill for Claude Code

.agents/skills/large-class-style/SKILL.md

large-class-style is a skill for Claude Code, Codex from sgl-project/sglang. It costs 51 tokens per session (1,800 once invoked), scanned A, original, Apache-2.0.

A code-style guide for SGLang's Scheduler, TokenizerManager, and ModelRunner classes, which coordinate request scheduling, token handling, and model execution.

In plain words
What is it for?
Use it when changing or reviewing those three classes, especially to decide what belongs in the orchestrator and what belongs in a separate collaborator.
Why use it?
It keeps these large coordination files focused on wiring and sequencing instead of accumulating business logic, making ownership and testing clearer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sgl-project/sglang's own configuration. It tells Claude Code and Codex how to work on sglang itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sglang configures →

About the project

SGLang is a framework for running inference for large language models and multimodal models, meaning it processes inputs to produce model outputs such as text or other media. It is used to serve and accelerate open AI models and related workloads.

sgl-project/sglang · 38,324 stars · on GitHub · sglang.io

Reuse

Borrowing it

Nothing to install: this file belongs to sgl-project/sglang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sgl-project/sglang/main/.agents/skills/large-class-style/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sgl-project/sglang

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 large-class-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/sgl-project/sglang/large-class-style/github.svg)](https://agentmods.dev/skills/sgl-project/sglang/large-class-style)
Your own site
<a href="https://agentmods.dev/skills/sgl-project/sglang/large-class-style"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/large-class-style/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.

agentmods 80×15 button for large-class-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/sgl-project/sglang/large-class-style"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/large-class-style.svg" alt="Reviewed on agentmods" width="80" 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 1,800 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. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original 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 5.1 $0.00051 $0.01800
Opus 5.5 $0.00020 $0.00720
Sonnet 5.5 $0.00010 $0.00360
Haiku 4.5 $0.00005 $0.00180

Measured 2mo ago against content hash e4c7ffb53e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

large-class-style 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 2mo 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.

.agents/skills/large-class-style/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Style for Scheduler / TokenizerManager / ModelRunner

Conventions for SGLang's three large classes:

  • Scheduler — python/sglang/srt/managers/scheduler.py
  • TokenizerManager — python/sglang/srt/managers/tokenizer_manager.py
  • ModelRunner — python/sglang/srt/model_executor/model_runner.py

1. Frozen Code

  • Some core files are frozen: orchestration-only — a thin composition root that constructs collaborators, wires them, delegates to them, and coordinates the calls. They must stay that way.
  • Domain logic does not belong in a frozen file; it lives in a collaborator class in its own module.

1.1 Why

  • The file is a thin orchestrator over collaborator classes; freezing keeps it that way and stops it growing back into a god class.
  • Keeping domain logic in collaborators (their own files) is what makes per-file code ownership, single responsibility, and unit testing possible.
  • The orchestrator is the composition root: it may know about every collaborator, because wiring and sequencing them is its job. Coordination stays here — domain logic does not.

1.2 Frozen files

  • python/sglang/srt/model_executor/model_runner.py

1.3 Allowed: orchestration

Every statement refers to a collaborator and is one of:

  1. Construct — a short init_<thing> helper whose body is essentially a single construction (follows §2); use maybe_init_<thing> with a one-line gate when conditional.
  2. Wire — a short call that runs the helper from the orchestrator (e.g. in __init__).
  3. Delegate — calls to a collaborator's methods at the necessary call sites (self.foo.run(...)).
  4. Coordinate — the minimal control flow that selects or orders the above: an if choosing whether / which collaborator to wire or call, the order of calls, threading one call's result into the next.
  • Heuristic: a statement is allowed only if it constructs, wires, delegates, or selects/orders those — never if it computes or transforms a value beyond passing arguments and results through.

Read the full file on GitHub · 140 lines

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. 2mo ago First seen · 140 lines · 51 tokens per session scan A e4c7ffb53e47

Subscribe to this mod's changes

large-class-style is a skill published in the GitHub repository sgl-project/sglang (38,324 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,800 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens

perf-optimize

Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the…

NVIDIA/TensorRT-LLM · 224 tokens

perf-analyze

Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill), nsys + ncu per-kernel…

NVIDIA/TensorRT-LLM · 159 tokens

fireworks-ai-inference

Fast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.

synthetic-sciences/openscience · 62 tokens

vllm

Use when self-hosting an OpenAI-compatible LLM endpoint with vLLM 0.32 — vllm serve, offline LLM.generate / llm.chat, PagedAttention with continuous batching and prefix caching, --tensor-parallel-size / --pipeline-parallel-size, AWQ/GPTQ/FP8 quantization, or wiring LangChain/LlamaIndex clients at…

znlgis/opengis-skills · 121 tokens

llm-kv-cache-paged-attention

Use this skill when the user says 'KV cache', 'PagedAttention', 'vLLM memory', 'gpumemoryutilization', 'prefix caching', 'max concurrent sequences', 'KV cache size', 'context length OOM'. Explains KV cache memory math and how paged allocation, prefix caching, KV quantization, and attention variants (MQA/GQA/MLA)…

j4flmao/agent-skills · 150 tokens