databrickslabs / databrickslabs/coding-agents-databricks-apps
Bundled plugin marketplace — coda-essentials
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 40
- Forks
- 11
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
Summary
Introduces a plugin system for CODA and ships coda-essentials as the first bundled plugin. Migrating from datasciencemonkey PR #140.
Plugin loader changes (setup_claude.py):
- Stage plugins into
~/.claude/plugins/cache/and write the state files Claude Code's plugin loader expects. - Inject fork-wide directives (uv version floor, library floors, UC catalog name) into
~/.claude/CLAUDE.md. - Editor detection (micro, nano, vim) for Bash deny-rule population so the user's preferred editor isn't blocked.
coda-essentials provides:
- Agents:
build-feature,implementer,prd-writer,test-generator. - Commands:
/cache-stats(token cache hit rate),/til(capture learning). - Hooks:
session-context-loader,session-crystallize-nudge,push-brain-to-workspace(syncs~/.claude/to Databricks Workspace on commit),check-memory-staleness,mlflow-trace-stop.
claude_brain_sync.py — post-commit hook that syncs Claude brain files to Databricks Workspace for cross-session persistence.
Branch
feat/coda-essentials-plugin — about to be pushed.
Diff scope
+1220 / -31, 16 files. No tests yet — plugin marketplace flow needs an integration test before merge.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with setup_claude.py and claude_brain_sync.py, then review the plugin agents, commands, and hooks listed in the issue. The proposed branch and 16-file diff are already described, but no integration test exists; done means the marketplace flow is covered by an integration test and the bundled plugin sync behavior works as specified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cloud, devtools
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100