Drive it yourself: hand the agent a URL
Your script or CI harness runs the CLI; the agent only ever sees a branch URL. The agent needs no Ardent token and can’t touch anything but its branch.AGENT_DATABASE_URL automatically — pass the URL in the agent’s prompt, or export it as DATABASE_URL if your app reads that.
Let the agent drive: set it up once
The agent runs the Ardent CLI itself — creating, using, and deleting its own branches:One-off AI directions: copy/paste
One-off AI directions: copy/paste
For a single task, paste this into Claude Code or Cursor:
Permanent AI skill: SKILL.md
Permanent AI skill: SKILL.md
If your agents touch the database every day, install this as a skill instead of pasting per task. Install into your project (or into The skill keeps itself current: each time it runs, it fetches the latest version of itself from these docs and follows that copy. If the fetch fails (offline, blocked network), it falls back to the directions already installed.Skills load when the task looks relevant — so a request that never mentions the database might skip it. To guarantee it’s used, add this to your project’s This is what it installs:The skill deliberately contains no command arguments. It tells the agent to fetch the current reference from these docs before acting, so when the CLI or API changes, the docs update and every installed copy of the skill stays correct without being touched.
~/.claude/skills/ to use it everywhere) and Claude Code loads it automatically whenever a task involves Ardent:CLAUDE.md, which Claude Code reads every session: