/ 3 min read

From Chatbot to Development Partner


This is Part 6 of a series on plan-based development with Claude Code. Today we explore how Claude Code becomes an integrated development partner.


From Chatbot to Development Partner


Claude Code isn’t a chatbot you occasionally ask questions. It’s an integrated development partner that understands your codebase, follows your patterns, and executes multi-step tasks.


The difference is profound:

  • Chat: “How do I add a new route in Express?”
  • Claude Code: “Add a new protected route for user preferences following our existing patterns in @bts/api

Custom Commands: Codified Workflows


We created custom commands that encode our team’s workflows:


.claude/
├── commands/
│ ├── research.md # /research - Research & planning
│ ├── understand.md # /understand - Code comprehension
│ ├── find.md # /find - Code discovery
│ ├── test.md # /test - Testing workflow
│ ├── review.md # /review - PR-style code review
│ └── write.md # /write - Code generation

The /research Command


When planning a new feature:


/research add real-time notifications to the dashboard

This triggers a structured research process:

  1. Searches for existing notification patterns
  2. Reviews the current architecture
  3. Identifies affected packages
  4. Produces a structured implementation plan

The /review Command


Before committing:


/review staged

This performs a comprehensive code review:

  • Checks for bugs and security issues
  • Validates TypeScript patterns
  • Ensures consistency with repo conventions
  • Suggests improvements

Skills: Context-Aware Assistance


Unlike commands that you invoke explicitly, skills activate automatically based on context:


.claude/skills/type-safety/SKILL.md
## When to Activate
- Questions about TypeScript errors
- Code with type assertions or `any`
- Discussions of validation or schemas
## Guidance
- Prefer Zod schemas over manual type guards
- Use branded types for IDs
- Validate at system boundaries

When Claude sees code with as any, it automatically applies the type-safety skill’s guidance.


The Plan Mode Workflow


For complex features, we use Claude Code’s plan mode:


  1. Enter plan mode: Triggered for multi-step implementations
  2. Explore codebase: Claude reads relevant files, understands patterns
  3. Write plan: Creates detailed implementation steps
  4. Review: Human reviews and approves the plan
  5. Execute: Claude implements following the approved plan

This mirrors our manual plan-based development but with AI assistance at every step.


Real Examples from Our Workflow


Example 1: Fixing a Build Issue


> bun run dev shows "Cannot find module '@bts/effect/services'"
Claude analyzes:
- Checks turbo.json for task dependencies
- Identifies race condition: dev starts before build completes
- Proposes fix: Add "^build" to dev task dependencies
- Implements the fix
- Verifies with test run

Example 2: Adding a New Package


> Create a new @bts/highlighter-router package following existing patterns
Claude:
- Uses `turbo gen package` generator
- Creates turbo.json with correct tags
- Sets up tsconfig.json extending base
- Adds to workspace catalog
- Creates initial exports
- Updates @bts/router to include new router

The Amplification Effect


Claude Code doesn’t replace developer judgment—it amplifies it.


  • Without Claude: Manually search 60 packages, copy patterns, adapt to context
  • With Claude: Describe intent, review proposed solution, approve and refine

The cognitive load shifts from “how do I do this?” to “is this the right approach?”


Next up in Part 7: Putting it all together - the virtuous cycle and lessons learned from six months of this workflow.