Credentials. OAuth tokens are stored in ~/.dsh/plugins/subscriptions/auth.json, so anyone with access to that file can use the logged-in account.
Who it is forA developer who pays for ChatGPT Plus or Pro and wants to use DSH as a coding or research assistant without buying API credits.
The problemRunning DSH normally needs a separate provider API key and billing, which duplicates a subscription the user already has.
The outcomeCodex models appear in the session model picker, and chat requests run through the ChatGPT subscription.
What you need first
- DeepSeek Harness (DSH) installed, with a web UI you can open
- An active ChatGPT Plus or Pro, Claude Pro or Max, or X Premium subscription, or a GitHub Copilot or Google Antigravity account, for the provider you want
- Permission to install the plugin into DSH, following the Install section of the README
Steps
- Install the plugin into DSH by following the Install section of the README.
- Open the DSH web UI and go to Settings, then Subscriptions.
- Click login on the ChatGPT (Codex) card and finish the OAuth login in the browser.
- Open a new session and choose a Codex model from the session model picker.
- Send a short test prompt and confirm the reply comes back from the selected model.
Prompt for your agent
Using the dsh-plugin-subscriptions repo, log in to the ChatGPT (Codex) subscription in DSH Settings, Subscriptions, then start a session with the Codex model <model-name>. Expected output: a normal chat reply from that model. Verify that the Codex card shows as logged in and the model appears in the session picker.
Caveat. The plugin uses your subscription login rather than an API key, so usage is limited by your ChatGPT plan, and the README does not promise any particular rate.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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