with one click
researching-codebases
// Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
// Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
| name | researching-codebases |
| description | Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings |
Coordinate parallel sub-agents to answer complex codebase questions.
code-locator directlyweb-searcher directlyBefore decomposing a new research question, consider checking for related past research:
list-research.py script to see recent research docssearch-research.py script with relevant keywordsread-research.py script to load itSee research-tools.md for script usage.
If the user references specific files, read them FULLY before spawning agents. This gives you context for decomposition.
Break the query into parallel research tasks. Consider:
agent-selection.md for agent capabilitiesLaunch multiple agents concurrently for independent tasks. Use the task tool with appropriate subagent_type.
Wait for ALL agents to complete before synthesizing.
Combine findings into a coherent answer:
file:line referencesFor substantial research, ask:
Want me to save this to a research doc? (project:
.research/or global:~/.research/)
Skip this for quick answers.
When saving:
gather-metadata.py script to get date, repo, branch, commit, cwd.output-format.md{filename_date}_topic-slug.mdSee agent-selection.md for when to use each agent.
Spawning agents before reading context: Read any files the user mentions first.
Not waiting for all agents: Synthesize only after ALL agents complete.
Over-documenting simple answers: Not every question needs a saved research doc.
Sequential when parallel works: If tasks are independent, spawn them together.