Getting Started

Hosted Quickstart

Validate the CLI against the hosted production backend, set a workspace, and get to your first runnable command in a few minutes.

This path is for people changing the CLI or trying the product without booting the whole stack locally.

Note

The hosted quickstart assumes your workspace already has challenge packs and deployments. If it does not, stop after link and then author a pack with challenge-pack init; you have still verified auth, connectivity, and workspace selection.

1. Install the CLI

bash
npm i -g agentclash

2. Point the CLI at production and log in

bash
1export AGENTCLASH_API_URL="https://api.agentclash.dev"
2agentclash auth login --device

Use --device when you are in a remote shell or do not want the CLI to open a browser automatically.

bash
agentclash link

The CLI resolves the API base URL in this order:

text
--api-url > AGENTCLASH_API_URL > saved user config > built-in default

The built-in default depends on how the CLI was built: released binaries (what npm i -g agentclash installs) default to https://api.agentclash.dev, while source builds (go run . / make build) default to http://localhost:8080. Because this quickstart uses the released npm binary, you only need the AGENTCLASH_API_URL export above if you want to override that default.

agentclash link saves the selected workspace in user config so later commands do not need raw IDs by default.

4. Choose your next path

bash
1agentclash doctor
2agentclash eval start --help

If the workspace is already seeded with challenge packs and agent deployments, create and follow a run:

bash
agentclash eval start --follow

If the workspace is empty, scaffold a starter pack first:

bash
1agentclash challenge-pack init support-eval.yaml
2agentclash challenge-pack validate support-eval.yaml
3agentclash challenge-pack publish support-eval.yaml
4agentclash eval start --follow
5agentclash baseline set
6agentclash eval scorecard

Verification

You should now have:

  • a valid CLI login
  • a default workspace linked locally
  • a working connection to the hosted API
  • either a created run or enough context to see what the workspace is missing
  • a clear next step: publish a challenge pack, start an eval, or save a baseline

See also