From agent-dashboard
Deep-dive into a codebase question, failure, or architectural concern without making changes
npx claudepluginhub bjornjee/agent-dashboard --plugin agent-dashboardThis skill uses the workspace's default tool permissions.
Investigate a codebase question or concern. **This is a read-only skill — do not modify any files.**
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Investigate a codebase question or concern. This is a read-only skill — do not modify any files.
Question or concern: $ARGUMENTS
Follow these phases in order. Apply all project rules and conventions that are in your context.
git checkout maingit pull origin mainGate: The investigation scope is clear and bounded.
Use read-only tools only. Do not edit, write, or create any files.
git log --all -S "<term>" to find when relevant code was introduced or changed. Use git blame for context on specific lines.Explore broadly first, then narrow to the relevant areas. Take notes as you go.
Present a structured report to the user:
/fix to address the null check at src/auth.py:42", "run /refactor to extract the retry logic into a shared utility").Gate: The user has received a clear, actionable report. No files were modified.