Skip to main content
Claude Code is most useful when it works against real files in a metadata repository. The goal is not to generate a disconnected YAML snippet. The goal is to update the same files that kdx sync will validate and deploy.

Start From A Synced Repository

If the environment already contains resources, pull them first:
Then commit the baseline:
Starting from a committed baseline gives Claude Code and reviewers a clean diff.

Give Claude Code The Right Scope

Open Claude Code from the repository root:
Start with a scoped instruction:
This gives Claude Code the business goal, the desired Kodexa mental model, and the deployment boundary.

Ask For A Plan Before Large Edits

For non-trivial changes, ask Claude Code to describe the file plan first:
Review the plan for:
  • resource scope: organization-level versus project-scoped
  • filenames and slugs
  • references to existing task templates, data forms, modules, bridges, and knowledge resources
  • whether a trigger or project binding is needed
  • whether the manifest needs to include new files

Useful Prompt Patterns

Create A Data Definition

Create A Task And Form

Create An Activity Plan

Add Knowledge-Driven Behavior

Review Existing Metadata

Keep References Portable

Prefer sync-friendly references over environment-specific UUIDs when the KDX sync resolver supports them. Examples:
Portable references make the same repository usable across dev, staging, and production targets.

Review The Diff

After Claude Code edits files:
Ask Claude Code to explain the diff in Kodexa terms:

Avoid These Mistakes

Before You Sync

Run these checks before pushing configuration:
If the dry run shows unexpected deletes, unrelated updates, or a target environment you did not intend, stop and inspect the manifest and sync configuration before pushing.