sglang: Skill for Claude Code

.claude/skills/clean-startup-log/SKILL.md

clean-startup-log is a skill for Claude Code from sgl-project/sglang. It costs 45 tokens per session (5,058 once invoked), scanned A, original, Apache-2.0.

A workflow for removing unwanted messages from SGLang server startup logs. It compares captured output with an expected clean log and looks for warnings, deprecation messages, third-party prints, and duplicates.

In plain words
What is it for?
Investigating and cleaning noisy startup output when launching SGLang servers, including single-GPU, multi-GPU, mixture-of-experts, and hybrid models.
Why use it?
It makes real startup problems easier to spot by separating useful server information from noise. It also checks different paths, such as multi-GPU and hybrid models.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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 · 35,615 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/clean-startup-log/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 clean-startup-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/sgl-project/sglang/clean-startup-log.svg)](https://agentmods.dev/skills/sgl-project/sglang/clean-startup-log)
Your own site
<a href="https://agentmods.dev/skills/sgl-project/sglang/clean-startup-log"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/clean-startup-log.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,058 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 282
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 $0.00045 $0.05058
Opus 5 $0.00023 $0.02529
Sonnet 5 $0.00009 $0.01012
Haiku 4.5 $0.00005 $0.00506

Measured 8d ago against content hash bead524743d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

clean-startup-log 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.

.claude/skills/clean-startup-log/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Up SGLang Server Startup Logs

Goal: ensure the server startup log is clean and minimal, with no spurious warnings, deprecation messages, or unformatted prints from third-party libraries.

Workflow

1. Launch a server and capture the log

uv run sglang serve --model-path Qwen/Qwen3-8B 2>&1 | tee /tmp/startup_log.txt

Wait until the server prints The server is fired up and ready to roll!, then Ctrl-C.

For TP>1 testing:

uv run sglang serve --model-path Qwen/Qwen3-8B --tp 2 2>&1 | tee /tmp/startup_log.txt

For MoE / hybrid-SWA models (e.g. gpt-oss), test separately — they exercise different code paths:

uv run sglang serve --model-path openai/gpt-oss-20b 2>&1 | tee /tmp/startup_log.txt

2. Compare against the clean reference log

Read /tmp/startup_log.txt and compare it against the reference log at the bottom of this file. Identify lines that:

  • Do NOT have the [timestamp] or [timestamp TPx] logger prefix
  • Contain WARNING, deprecated, is deprecated, or similar noise
  • Are printed by third-party libraries (transformers, torchao, NCCL, Gloo, tqdm, etc.)
  • Are duplicate/redundant with information already logged by SGLang
  • Appear multiple times due to ModelConfig being constructed in multiple processes

3. Classify each noisy line

For each noisy line, determine:

Category Action
SGLang code using wrong API Fix the SGLang code (e.g., replace deprecated API with new one)
SGLang code logging at wrong level Change log level (e.g., warning -> debug for non-actionable messages)
Duplicated across processes Downgrade to debug — info logged in one process becomes noise in 3-4
Third-party lib prints at import time Suppress the logger or redirect stdout during that import
C-level print from .so library Redirect fd 1 during the specific C call, or accept it if too invasive
Real warning the user should see Keep it

4. Present findings before fixing

Read the full file on GitHub · 283 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. 8d ago First seen · 283 lines · 45 tokens per session scan A bead524743d1

Subscribe to this mod's changes

clean-startup-log is a skill published in the GitHub repository sgl-project/sglang (35,615 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 5,058 once invoked, about $0.0002 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 2026-08-30.