From brad-personal
Create detailed implementation plans with thorough research and iteration. Use when starting significant features spanning multiple files, planning refactors affecting architecture, working on multi-phase projects with milestones, establishing success criteria before coding, breaking down complex work, or documenting approach for non-trivial technical decisions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/brad-personal:create-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Read all mentioned files completely (no partial reads)
Codebase Research:
codebase-locator - Find WHERE files/components livecodebase-analyzer - Understand HOW existing code workscodebase-pattern-finder - Find similar implementations to learn fromAgent Tips:
Wait for ALL sub-agents, then:
Present outline for approval:
## Overview
[1-2 sentence summary]
## Implementation Phases:
1. [Phase Name] - [What this accomplishes]
2. [Phase Name] - [What this accomplishes]
3. [Phase Name] - [What this accomplishes]
Get explicit user buy-in before investing in detailed planning.
Save to: thoughts/shared/plans/YYYY-MM-DD-brief-description.md (if thoughts/ exists)
Or present inline if no thoughts directory.
Structure:
Per phase:
End with:
humanlayer thoughts sync (if applicable)Automated: Tests, type check, lint, build
Manual: Feature works, performance acceptable, edge cases handled
Database Changes: Schema → Store/Repository methods → Business logic → API endpoints → Client code
New Features: Research patterns → Data model → Backend implementation → API → UI/Frontend
Refactoring: Document current state → Incremental changes → Maintain backwards compatibility → Migration strategy
API Changes: Document current behavior → Deprecation plan → New implementation → Migration guide → Old code removal
npx claudepluginhub carterbs/agent-config --plugin brad-personalDesigns multi-file implementation plans grounded in codebase research. Invoked for any feature, refactor, or change needing structured design before coding.
Generates detailed implementation plans for features, refactors, migrations, bug fixes, and architectural changes using multi-agent collaboration. Outputs structured Markdown files with steps, scope, and risks.
Transforms research findings into actionable implementation plans with granular steps, verification criteria, and stakes-based enforcement. Useful for structuring complex coding tasks before execution.