Skip to main content
Use the Query skill before non-trivial work so your agent can align with existing project decisions, patterns, and gotchas. The normal workflow is agent-driven: ask the agent to check ByteRover, then let it use the retrieved memory while it works.
Run Query from inside the project folder. If the project should use a named space, bind it first with Bind.

​
Ask your agent to query

Use natural language. Include the area of the codebase or decision you are about to touch. 
Before changing authentication, query ByteRover for the current desktop auth and daemon sync decisions.
Other examples: 
Check ByteRover for testing conventions before adding these tests.

Query ByteRover for deployment gotchas related to the desktop app.
The agent should run the query from inside the project folder so ByteRover can resolve the correct space.

​
Review the answer

The agent should summarize the relevant memory and show the source when ByteRover returns one. Use the answer as project context, not as a blind command. If the recorded memory conflicts with the current task, ask the agent to explain the conflict before changing direction.

​
Narrow the query

If the answer is too broad, ask a more specific follow-up: 
Narrow that to auth token storage and browser approval only.
If the answer misses a topic you expected, mention the likely area: 
Search ByteRover again, focused on the desktop daemon auth flow.

​
Record what is missing

If nothing useful appears, continue the work. When the decision becomes clear, ask the agent to record it: 
Record the auth token storage decision we just made, including why we rejected pasted tokens.

​
Manual reference

Most users do not need to run the script directly. The connected agent runs it from the installed ByteRover skill directory. The script shape is: 
node scripts/query.mjs "desktop auth daemon sync" --limit 5
The command returns JSON with:
FieldMeaning
hitsRanked matching topics with path, title, score, and snippet.
queryThe resolved query text.
should_citeWhether the result set is strong enough for the agent to cite.
citation_blockA ready-to-share citation block for the matching memories.

​
Read a full topic

When a hit looks useful, read the full topic: 
node scripts/brv.mjs read "architecture/auth.html"
The agent should treat recorded decisions and rules as constraints unless it explains why the current task needs to diverge.