Publish a script with your agent

Your coding agent can prepare a script you already have for your team. Its inputs become a form and an agent tool, secrets stay out of the code, and the agent proves the draft works before you decide to publish.

1. Connect the agent

Connect it to Reminix’s MCP server, or let it use the CLI, and give it the skill that explains how Reminix works (Use with AI agents).

2. Paste this prompt

Publish scripts/<your-script> to Reminix. Search the team's
scripts first in case one exists. Describe its inputs in the input
schema with clear titles, write a short README, keep every secret out of
the code (ask me to save it as a Reminix secret) and declare only the
hosts it calls. Upload it as a draft, test-run it with realistic inputs,
show me the result, and ask me before publishing.

3. What it does

1. reminix publish --plan shows what Reminix works out from the folder: the script’s name, its command and its inputs. Nothing is uploaded. Your code stays as it is.
2. To describe the inputs with titles and examples, it adds a reminix.json (reminix init writes one to edit), and it writes a README.md.
3. reminix publish --draft uploads a draft. Nobody else can run it yet.
4. It test-runs the draft: reminix run <slug> --version <n> --input '{…}' --log. Reminix marks a test run as one and starts no triggers or webhooks from it. It counts toward the month’s runs, like any run.
5. It shows you the result and asks you to publish that version, in the app or with reminix publish --number <n>. If your workspace requires a second person to publish, you get an approval link.

Test runs

The script’s owner, workspace owners and admins, and the person who uploaded a version can test-run that version:

curl -X POST https://api.reminix.com/v1/scripts/monthly-report/versions/3/runs \
  -H "Authorization: Bearer $REMINIX_TOKEN" -H "X-Workspace: acme" \
  -H "Content-Type: application/json" -d '{ "inputs": { "month": "2026-09" } }'

The script’s approval policy still applies to test runs.