sglang: Skill for Claude Code

.claude/skills/sglang-bisect-ci-regression/SKILL.md

sglang-bisect-ci-regression is a skill for Claude Code from sgl-project/sglang. It costs 56 tokens per session (2,548 once invoked), scanned A, original, Apache-2.0.

A guide for finding why an SGLang continuous-integration test keeps failing. CI is the automated system that runs tests on code changes and scheduled builds.

In plain words
What is it for?
Use it to extract a failure signature from workflow logs, narrow down the responsible commit, check hardware specificity, and optionally reproduce the failure on a remote GPU host.
Why use it?
It distinguishes a code regression from a GPU or runner-specific problem and from an environment change by locating the change between a passing and failing commit.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ssh {SSH_TARGET} "docker exec -e CUDA_VISIBLE_DEVICES=0,1 {CONTAINER} python3 /tmp/repro_script.py".

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 · 35,749 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-bisect-ci-regression/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-bisect-ci-regression

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sgl-project/sglang/sglang-bisect-ci-regression"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/sglang-bisect-ci-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,548 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 $0.00056 $0.02548
Opus 5 $0.00028 $0.01274
Sonnet 5 $0.00011 $0.00510
Haiku 4.5 $0.00006 $0.00255

Measured 11d ago against content hash 8807e22391ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sglang-bisect-ci-regression 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 11d 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.

ssh {SSH_TARGET} "docker exec {CONTAINER} bash -c 'cd /tmp && curl -L https://github.com/sgl-project/sglang/archive/refs/heads/main.tar.gz | tar xz && cd sglang-main && pip install -e \"python[all]\"'"
.claude/skills/sglang-bisect-ci-regression/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SGLang Bisect CI Regression

Investigate a consistently failing CI test to find the root cause - whether it's a code regression from a specific PR, a hardware/runner-specific issue, or an environment change. Optionally reproduce the failure on a remote GPU server.

Slash Command

/sglang-bisect-ci-regression <test_name_or_ci_url> [ssh_target] [docker_container]

When to Use This Skill

  • A CI test is failing consistently on main (scheduled runs)
  • You need to find which PR introduced a regression
  • You suspect a runner-specific or GPU-specific issue
  • You want to reproduce a CI failure on a remote server

Arguments

  • First argument (required): Test file name (e.g. test_lora_tp.py) or a GitHub Actions job URL
  • Second argument (optional): SSH target for remote reproduction (e.g. user@host)
  • Third argument (optional): Docker container name on the SSH target (e.g. sglang_dev)

If SSH target and docker container are not provided, the skill will only perform the CI log analysis and bisection, without remote reproduction. Ask the user for these if reproduction is needed and they weren't provided.

Background: Scheduled CI Runs

SGLang uses the pr-test.yml workflow with scheduled runs (cron-triggered) to periodically test the main branch. These runs are the primary data source for detecting regressions:

Always use these scheduled runs (not PR-triggered runs) when bisecting regressions on main. The --event schedule filter in gh run list ensures you only see these periodic main-branch runs.

Workflow

Phase 1: Extract the Failure Signature

Read the full file on GitHub · 225 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. 11d ago First seen · 225 lines · 56 tokens per session scan A 8807e22391ab

Subscribe to this mod's changes

sglang-bisect-ci-regression is a skill published in the GitHub repository sgl-project/sglang (35,749 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 2,548 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

meta-long-running-build-watchdog

Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.

opensquilla/opensquilla · 131 tokens

ci-debug

Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…

yonatangross/orchestkit · 92 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

rpi-fix-ci

Diagnose existing CI failures and repair their root causes locally with regression evidence and complete verification before any authorized publication.

juan294/cc-rpi · 28 tokens

ci-repair

Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.

yimwoo/codex-agenteam · 26 tokens

ci-triage

Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.

eli-labz/Godcoder · 38 tokens