DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run Command Code models in the dsh web app with DSH Commandcode Provider

Install the plugin, add your key, and pick Command Code models in the web model picker.

Credentials. The API key and the CLI login file give access to your Command Code account, so keep them out of shared profiles and logs.

Who it is forA dsh web user with a Command Code account who wants those models in the normal chat picker.

The problemCommand Code models are not in dsh by default, and the key setup is easy to get wrong.

The outcomeCommand Code models appear under commandcode in the picker, and messages sent with them get answers.

What you need first

  • A Command Code account with an API key or subscription
  • A dsh profile on 0.2.0-rc.2 or 0.2.1-rc.2
  • Node.js 22+ if you use the official command-code CLI to sign in

Steps

  1. (Optional) Run npm i -g command-code@latest, then run cmd login to get a key through the official CLI.
  2. Run dsh plugin --profile web add @mars-sea/dsh-commandcode-provider@latest.
  3. Restart the web app.
  4. Open Settings, then Command Code, and paste your key or click Sign in to Command Code.
  5. Open Settings, then Models to confirm the Command Code card, then pick a model your plan includes.

Prompt for your agent

Install the Mars-Sea/dsh-commandcode-provider plugin into the <profile> dsh profile and confirm the commandcode provider appears in the model picker. Expected output: a list of commandcode models in the picker. Verify that a test message sent with one included model returns a reply.

Caveat. You need your own Command Code account, and the in-browser sign-in only works when the Host and your browser are on the same machine.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page