sglang: Skill for Claude Code

.claude/skills/sglang-prod-incident-triage/SKILL.md

sglang-prod-incident-triage is a skill for Claude Code from sgl-project/sglang. It costs 83 tokens per session (2,090 once invoked), scanned A, original, Apache-2.0.

A replay-first guide for investigating SGLang serving failures, such as unhealthy checks, slowdowns, growing queues, timeouts, hangs, crashes, and changed outputs.

In plain words
What is it for?
Use it to collect evidence, save a failing request or crash dump, replay the problem on a clean target, and report the problem class, findings, likely cause, exclusions, next step, and production risk.
Why use it?
It turns a live or recent production problem into a repeatable case before deeper investigation, making it clearer what was checked and what remains likely.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sgl-project/sglang's own configuration. It tells Claude Code 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 · 35,828 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/.claude/skills/sglang-prod-incident-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sgl-project/sglang

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 sglang-prod-incident-triage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sgl-project/sglang/sglang-prod-incident-triage"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/sglang-prod-incident-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,090 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. 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 $0.00083 $0.02090
Opus 5 $0.00042 $0.01045
Sonnet 5 $0.00017 $0.00418
Haiku 4.5 $0.00008 $0.00209

Measured 12d ago against content hash 7f0cfc4c6829, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sglang-prod-incident-triage 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/incident_artifact_tool.py, scripts/replay_trusted_request_dump.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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://127.0.0.1:30000/set_trace_level?level=1"
.claude/skills/sglang-prod-incident-triage/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SGLang Serving Debug

Overview

Use this skill to turn a live serving problem into a debug path you can replay.

Use one loop:

  • collect a baseline bundle
  • save the failing request or crash dump
  • replay on a clean target
  • only then switch tools

Do not start with profiling.

This skill should work with more focused skills instead of re-implementing them:

  • debug-cuda-crash when replay plus coredump points to a CUDA crash path
  • debug-distributed-hang when the problem is clearly a TP/PP/DP/EP hang
  • llm-torch-profiler-analysis when the issue is already narrowed to a compute-side path

Three examples are included:

  • TTFT spike with low queue time
  • replay-first CUDA crash flow
  • request-shaped distributed hang flow

Output Contract

Return:

  • problem class
  • what was checked
  • strongest signal so far
  • current best guess
  • what was ruled out
  • next step
  • production risk

When To Use It

  • /health or /health_generate is unhealthy
  • latency or throughput regressed under serving load
  • queue size grows while health still looks green
  • one request class times out or hangs
  • the server crashes only after some requests
  • outputs changed after a deploy, topology change, or weight switch
  • one older commit is known-good and a newer commit is known-bad

Workflow

1. Collect a baseline bundle

If a live server is reachable, collect a read-only bundle before anything more intrusive:

python3 scripts/incident_artifact_tool.py collect-bundle \
  --base-url http://127.0.0.1:30000 \
  --outdir /tmp/incident_bundle

python3 scripts/incident_artifact_tool.py summarize-bundle \
  /tmp/incident_bundle

If the server is protected:

python3 scripts/incident_artifact_tool.py collect-bundle \
  --base-url http://127.0.0.1:30000 \
  --token "$SGLANG_BEARER_TOKEN" \
  --outdir /tmp/incident_bundle

The bundle script collects:

  • /health
  • /health_generate
  • /model_info
  • /server_info
  • /v1/loads?include=all
  • /v1/loads?include=core,queues,disagg,spec
  • /metrics
  • /hicache/storage-backend on a best-effort basis

Read the full file on GitHub · 292 lines

Files

What ships with it

6 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. 12d ago First seen · 292 lines · 83 tokens per session scan A 7f0cfc4c6829

Subscribe to this mod's changes

sglang-prod-incident-triage is a skill published in the GitHub repository sgl-project/sglang (35,828 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 2,090 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.