Add agent files to DABs templates#5996
Open
lennartkats-db wants to merge 9 commits into
Open
Conversation
Generated DAB projects now include an AGENTS.md with project layout, the common bundle CLI workflow (validate/deploy/run/summary), and conventions, plus a CLAUDE.md that imports it via @AGENTS.md so Claude Code and tools using the AGENTS.md convention share one source of truth. Added to the default, default-sql, default-scala, and dbt-sql template bodies, which covers all built-in templates (default-python, default-minimal, lakeflow-pipelines, and pydabs share the default body). Co-authored-by: Isaac
…templates Update the remaining template files that referred to the product by its former name: the databricks.yml header comments (default, default-sql, default-scala bodies), the dbt_project.yml comment, and the default-minimal welcome message. Co-authored-by: Isaac
Replace the verbose per-template AGENTS.md with the short version originally used in experimental/aitools (removed in c8d825c): point agents at the databricks skill, explain how to install agent skills (databricks aitools install), and leave a placeholder for project-specific instructions. Inlining all instructions is a non-goal. Co-authored-by: Isaac
Reword the section to "Use the Databricks Agent Skills": read the core databricks skill, reach for the product skills it links to (databricks-jobs, databricks-pipelines, databricks-apps), and install them with databricks aitools install. Regenerate template goldens. Co-authored-by: Isaac
# Conflicts:
# acceptance/bundle/templates/default-minimal/output.txt
# acceptance/bundle/templates/default-minimal/output/my_default_minimal/databricks.yml
# acceptance/bundle/templates/default-python/classic/output/my_default_python/databricks.yml
# acceptance/bundle/templates/default-python/serverless/output/my_default_python/databricks.yml
# acceptance/bundle/templates/default-scala/output/my_default_scala/databricks.yml
# acceptance/bundle/templates/default-sql/output/my_default_sql/databricks.yml
# acceptance/bundle/templates/lakeflow-pipelines/python/output/my_lakeflow_pipelines/databricks.yml
# acceptance/bundle/templates/lakeflow-pipelines/sql/output/my_lakeflow_pipelines/databricks.yml
# acceptance/bundle/templates/pydabs/init-classic/output/my_pydabs/databricks.yml
# acceptance/bundle/templates/telemetry/default-python/out.databricks.yml
# acceptance/bundle/templates/telemetry/default-sql/out.databricks.yml
# libs/template/templates/default-minimal/databricks_template_schema.json
# libs/template/templates/default-scala/template/{{.project_name}}/databricks.yml.tmpl
# libs/template/templates/default-sql/template/{{.project_name}}/databricks.yml.tmpl
# libs/template/templates/default/template/{{.project_name}}/databricks.yml.tmpl
Point coding agents at Databricks AI Tools: read the databricks-core skill, and install via `databricks aitools install` if it's missing. CLAUDE.md is a one-line @AGENTS.md include. Decided at the DABs core meeting. Co-authored-by: Isaac
Contributor
Approval status: pending
|
Co-authored-by: Isaac
lennartkats-db
commented
Jul 21, 2026
| @@ -0,0 +1,33 @@ | |||
| {{- /* | |||
Contributor
Author
There was a problem hiding this comment.
This file is repeated a few times now, as a followup I want to look into a clean way to avoid the duplication. That will require a change in the templating code.
Contributor
There was a problem hiding this comment.
The default-*/ templates already pick up everything from default/ so you only need to duplicate dbt-sql
Contributor
Author
There was a problem hiding this comment.
Unfortunately, default-sql and default-scala are also special right now.
Collaborator
Integration test reportCommit: b0d8254
8 interesting tests: 4 SKIP, 3 KNOWN, 1 RECOVERED
Top 4 slowest tests (at least 2 minutes):
|
The lakeflow-pipelines template reuses default via template_dir, so
projects initialized by the pipelines/{init,e2e} acceptance tests now
emit AGENTS.md and CLAUDE.md; add them to those tests' goldens.
Co-authored-by: Isaac
1 task
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changes
Add an
AGENTS.mdto the bundle templates (default,default-scala,default-sql,dbt-sql, plus the templates that reusedefault). It points coding agents at Databricks AI Tools: read thedatabricks-coreskill first, and install viadatabricks aitools installif it's missing. A one-lineCLAUDE.mdincludes it via@AGENTS.md.Why
We'd like to help AI agents in new projects via Databricks AI Tools.
Tests
Regenerated the template acceptance goldens;
task test-update-templatespasses.