StarSling
CLI

Overview

The agent-first CLI for StarSling

View Markdown

sling is the primary interface to the StarSling platform for agents and humans. The questions you ask most often are each a single command: why a job failed, where the time went, and what sits at the top of your spend.

Install

Installation Prompt

Paste this prompt into your coding agent:

AI prompt
Install the Sling CLI on this machine.

1. Check whether `sling` is already installed. If it is, show me `sling --version` and do not reinstall it.
2. Confirm this machine is supported: Apple Silicon macOS or x64 glibc Linux. If it is not, stop and explain that the CLI cannot be installed here.
3. Before making changes, show me the official installer command and ask for approval. Once I approve, run:
   curl -fsSL https://runners.starsling.dev/cli/install.sh | sh
4. Follow any PATH instructions printed by the installer, then verify both `command -v sling` and `sling --version` succeed.
5. Determine whether your environment and my terminal share the same machine and user account. If they do, give me a login command that works in my terminal—use the absolute path returned by `command -v sling`, or include the installer's PATH update—then ask me to run it and complete the GitHub browser approval. Wait for me to confirm. If you run on a separate host or in a container whose credentials my terminal cannot share, run `sling login` in your environment, relay its device code and approval URL to me, and wait for me to approve it. Do not attempt to approve the login for me.
6. Run `sling whoami` and `sling doctor`. Report the identity, organization, and every doctor result, including advisory checks.

Do not claim the installation is complete unless the binary works and the authentication checks finish successfully. If a step fails, explain the exact failure and the next action instead of skipping it.

Install manually

On Apple Silicon macOS and x64 glibc Linux:

curl -fsSL https://runners.starsling.dev/cli/install.sh | sh

Using Sling with a coding agent? Install the skill with the command below. Read the sling skill guide for prerequisites, examples, and details about how it works.

From the target project's root directory, run:

npx skills add starslingdev/skills --skill sling

Then sign in and confirm the install:

sling login
sling --version

sling login runs the GitHub device-code flow and saves your session per user, not per shell — so an agent running on the same machine inherits it with no further setup.

For PATH setup, upgrades, digest verification, and sling doctor, see Installation.

What you can do with it

sling time
Job Name: Lint, typecheck, test & spell · Wall-Clock: 58s · Queue-Wait: 2s

  PHASES                           TIME %-SHARE  TIMELINE
  provision                        4.0s   7.14%  ██░░░░░░░░░░░░░░░░░░░░░░
  checkout+patch                   2.0s   3.57%  ░░█░░░░░░░░░░░░░░░░░░░░░
  steps                           46.0s  82.14%  ░░░███████████████████░░
    Set up Bun                     1.0s          ░░░█░░░░░░░░░░░░░░░░░░░░
    Set up mise tools              2.0s          ░░░█░░░░░░░░░░░░░░░░░░░░
    Install dependencies           1.0s          ░░░░█░░░░░░░░░░░░░░░░░░░
    Lint (Biome)                   2.0s          ░░░░█░░░░░░░░░░░░░░░░░░░
    Lint shell (shellcheck)       14.0s          ░░░░░██████░░░░░░░░░░░░░
    Lint Dockerfiles (hadolint)    0.0s          ░░░░░░░░░░░█░░░░░░░░░░░░
  ▸ Typecheck                     18.0s          ░░░░░░░░░░░████████░░░░░
    Test                           7.0s          ░░░░░░░░░░░░░░░░░░░███░░
    Catalog drift                  1.0s          ░░░░░░░░░░░░░░░░░░░░░░█░
    Spell (typos)                  0.0s          ░░░░░░░░░░░░░░░░░░░░░░█░
  teardown                         4.0s   7.14%  ░░░░░░░░░░░░░░░░░░░░░░██
  • sling why classifies why a job failed, with evidence and a fix to run.
  • sling logs filters server-side, returning only the logs that matter.
  • sling time decomposes where the time went, phase by phase.
  • sling top ranks what sits at the top of your spend.
  • sling usage attributes runner minutes and cost, grouped how you ask.
  • sling speedup launches the pinned ci-speedup audit locally in Claude Code or Codex.
  • sling bill is a read-only budget check for the open period.
  • sling disks lists the StarSling Disks your repositories keep and browses the disk presets.

Why it exists

AI agents working inside CI jobs on StarSling Runners, and the humans supervising them, have no first-class way to answer the questions CI work actually consists of: why did this job fail, where does the wall-clock go, what is burning our runner minutes, show me the logs that matter.

Those answers otherwise live behind the GitHub UI (hostile to agents), raw APIs (no diagnosis, no aggregation), and dashboards (exports, not interfaces). Agents end up screen-scraping logs into their context windows, guessing at failure causes, and unable to branch on outcomes without parsing prose. Humans get no leverage from the telemetry StarSling already collects.

Learn more

On this page