sglang: Skill for Claude Code

.claude/skills/babysit-pr-to-pass-ci/SKILL.md

babysit-pr-to-pass-ci is a skill for Claude Code, Codex from sgl-project/sglang. It costs 110 tokens per session (2,555 once invoked), scanned A, original, Apache-2.0.

A persistent workflow for monitoring selected GitHub Actions checks on an SGLang pull request and continuing until the latest revision passes. GitHub Actions is GitHub’s system for automatically running tests and other checks.

In plain words
What is it for?
Watching and retrying pull-request checks such as linting, tests, extra tests, or AMD workflows, and fixing change-related failures until the selected checks pass.
Why use it?
It keeps track of retries, new commits, and whether failures come from the change or from flaky infrastructure. It limits monitoring to the workflows the user selects.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: $skill-name invocation.

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 · 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/babysit-pr-to-pass-ci/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 babysit-pr-to-pass-ci

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sgl-project/sglang/babysit-pr-to-pass-ci"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/babysit-pr-to-pass-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,555 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 warn 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 $0.00110 $0.02555
Opus 5 $0.00055 $0.01277
Sonnet 5 $0.00022 $0.00511
Haiku 4.5 $0.00011 $0.00255

Measured 12d ago against content hash d7399e80252c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

babysit-pr-to-pass-ci 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 12d 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/babysit-pr-to-pass-ci/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Babysit a PR Until Selected CI Passes

Drive only the selected workflows to green on the PR's latest head commit. Keep working across turns by starting a durable goal; do not stop merely because a run was dispatched, a retry began, or a fix was pushed.

Invocation and arguments

Accept:

$babysit-pr-to-pass-ci [PR_NUMBER|PR_URL] [WORKFLOW ...]
$babysit-pr-to-pass-ci [PR_NUMBER|PR_URL] --only WORKFLOW [WORKFLOW ...]
  • If the PR is omitted, resolve the PR associated with the current branch.
  • If workflows are omitted, select lint.yml and pr-test.yml.
  • Without --only, add named workflows to the two defaults.
  • With --only, monitor exactly the named workflows.
  • Accept a workflow basename such as pr-test-extra.yml, a repository path such as .github/workflows/pr-test-extra.yml, or an unambiguous workflow display name.
  • Treat extra as pr-test-extra.yml.
  • Accept natural-language equivalents, such as “PR 12345 plus extra and AMD.” Resolve “AMD” to an exact workflow file from the user's wording or repository context; do not guess when multiple AMD workflows fit.

Examples:

$babysit-pr-to-pass-ci
$babysit-pr-to-pass-ci 12345
$babysit-pr-to-pass-ci https://github.com/sgl-project/sglang/pull/12345 pr-test-extra.yml
$babysit-pr-to-pass-ci 12345 --only pr-test-amd-rocm720.yml

Start or continue the durable goal

Treat explicit invocation of this skill as authorization to create a goal and perform the scoped CI actions below.

  1. Resolve the PR and exact workflow set first.
  2. Inspect the current goal.
  3. If no unfinished goal exists, create one immediately using the product's goal mechanism. Include the resolved PR URL, selected workflow files, and this stopping condition: every selected workflow has a successful run for the PR's latest head SHA.
  4. Include these constraints in the goal objective:
    • Ignore every unselected workflow.
    • Diagnose each selected-workflow failure as PR-related, unrelated/infrastructure, or still uncertain.
    • Implement, validate, commit, and push a PR-related fix only when it is clean, non-tricky, and at most 100 changed lines.
    • Stop for user review before editing when the proposed fix is tricky, dirty, or over 100 changed lines.
    • Retry unrelated failures at most 10 times per workflow and head SHA, using failed-jobs-only reruns.
    • Never rerun a full workflow merely to recover failed tests.
  5. If the active goal already represents this same PR and workflow set, continue it instead of creating another goal.
  6. If a different unfinished goal is active, do not replace it silently. Report the conflict and ask the user to pause or clear it.

Read the full file on GitHub · 174 lines

Files

What ships with it

1 file 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 · 174 lines · 110 tokens per session scan A d7399e80252c

Subscribe to this mod's changes

babysit-pr-to-pass-ci is a skill published in the GitHub repository sgl-project/sglang (35,828 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 2,555 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens

swarm-migrate

Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…

yonatangross/orchestkit · 103 tokens

zb-release-pipeline

Generate a GitHub Actions pipeline that builds a zb (Zero Dependencies Builder) project and publishes a GitHub Release with the produced JAR. Use whenever the user wants CI/CD, a build pipeline, a release workflow, or GitHub Actions for a zb-based Java project — phrases like "set up GitHub Actions for this zb…

AdamBien/airails · 148 tokens

release-engineering

Design, automate, and operate end-to-end software releases: release process models and pipelines (trunk-based development, CD stages, release trains), progressive delivery and feature flags, versioning and artifact management (SemVer, conventional commits, changelogs, SBOM/provenance), readiness and quality gates…

magnus919/agent-skills · 158 tokens

verified-delivery

Implement and deliver an authorized change end to end — verify, open the PR, merge, and confirm post-merge state — using live-state gates, durable interruption handoffs, and live-state-first resumption. Use when a user grants end-to-end delivery authority for a specific change and the work may cross tool-call limits…

magnus919/agent-skills · 123 tokens

deployment-safety

Production deployment rules, rollback-first recovery, dependency batching, CI cost awareness, framework upgrade verification, fallback observability, and GitHub repo settings standardization.

juan294/cc-rpi · 35 tokens