Software Dev AI Claude Toolkit

<img width="1024" height="1024" alt="image" src="https://github.com/user-attachments/assets/362fbec4-a3f8-463e-aa98-11e50b895815" /> <div align="center">

Quick Install • What's Inside • Rules • Commands • Agents • Skills • Contributing

</div>

A production-ready Claude Code configuration for backend-heavy full-stack developers. Pre-configured rules, slash commands, agents, skills, hooks, and MCP servers — covering Java 17 + Spring Boot 3, Python 3.12 + FastAPI, JavaScript (Express.js + React), PostgreSQL, MongoDB, Redis, Kafka, Flink, Docker, Kubernetes, and AI/ML workflows.

Drop it in, run the installer, and Claude Code immediately understands your stack, enforces your standards, and works the way you work.

Who This Is For

• Backend developers working with Java/Spring Boot, Python/FastAPI, or Node.js/Express
• Full-stack developers who also touch React frontends
• Engineers working with PostgreSQL, MongoDB, Redis, Kafka, or Flink
• Anyone building AI/ML pipelines (RAG, agents, MCP servers, vector databases)
• Developers who want Claude Code to follow real engineering standards, not generic defaults

What's Inside

| Component | Count | What It Does | |-----------|-------|--------------| | Rules | 9 | Coding standards Claude follows on every response | | Slash Commands | 8 | One-command workflows (/plan, /tdd, /code-review, etc.) | | Agents | 5 | Specialized AI personas for planning, review, security, architecture, TDD | | Skills | 14 | Deep domain knowledge packs (Spring Boot, Python, React, PostgreSQL, Kafka, etc.) | | Hooks | 4 | Automated guardrails that run before/after tool use | | MCP Servers | 4 | External tool integrations (docs lookup, memory, reasoning, GitHub) | | Examples | 3 | Ready-to-use CLAUDE.md templates for your projects |

Total: 47 components working together to make Claude Code act like a senior engineer on your team.

Before vs After

Before (vanilla Claude Code)

You: "Add a user registration endpoint"

Claude: *generates a basic endpoint with no validation, no error handling,
        uses field injection, no tests, hardcoded values, no consideration
        for your existing project patterns*

After (with this toolkit)

You: "Add a user registration endpoint"

Claude: *reads your project's CLAUDE.md, follows your naming conventions,
        uses constructor injection, adds @Valid with proper DTOs, writes
        Flyway migration, includes unit + integration tests with Testcontainers,
        uses your custom exception hierarchy, follows your git commit format,
        and warns you about the missing rate limiter*

The difference is not magic — it's context. This toolkit gives Claude Code the same context you'd give a new developer joining your team.

---

Quick Install

Mac / Linux

git clone https://github.com/Ashfaqbs/software-dev-ai-claude-toolkit.git
cd software-dev-ai-claude-toolkit
chmod +x install.sh
./install.sh

Windows (PowerShell)

git clone https://github.com/Ashfaqbs/software-dev-ai-claude-toolkit.git
cd software-dev-ai-claude-toolkit
.\install.ps1

The installer:

• Copies all components to ~/.claude/
• Backs up existing files before overwriting
• Merges hooks into your existing settings.json
• Skips CLAUDE.md if you already have one (won't overwrite your personal config)

Manual Install

If you prefer to cherry-pick, copy individual folders to ~/.claude/:

~/.claude/
  rules/        <- copy rules/*.md
  commands/     <- copy commands/*.md
  agents/       <- copy agents/*.md
  skills/       <- copy skills/*/
  settings.json <- merge hooks from hooks/settings.json
  .mcp.json     <- copy mcp/mcp-servers.json
  CLAUDE.md     <- copy examples/CLAUDE.md (customize it)

---

Rules (9 files)

Rules are always-on instructions that Claude Code follows in every response. They live in ~/.claude/rules/ and are automatically loaded.

| File | Covers | |------|--------| | coding-style.md | Immutability, naming conventions, file organization, function design, error handling | | java-springboot.md | Java 17 features, Spring Boot 3 standards, project structure, REST conventions, Redis, Kafka | | python-backend-ai.md | FastAPI, Pydantic, SQLAlchemy 2.0, RAG pipelines, MCP/ADK agents, ML best practices | | javascript.md | Express.js API patterns, React conventions, hooks, project structure | | databases.md | PostgreSQL (migrations, indexes, UUIDs), MongoDB (embedding vs referencing), Redis (data structures, TTL, key naming) | | infra.md | Docker (multi-stage builds), Kubernetes (probes, HPA, PDB), Kafka (topics, consumers, idempotency), Flink (state, checkpoints) | | git-workflow.md | Conventional commits, branch strategy, PR process, what not to commit | | testing.md | TDD workflow, 80% coverage target, JUnit/pytest/Jest patterns, test naming | | security.md | Auth, secrets management, API security, data protection, container security |

Example: What the Java Rule Does

When you ask Claude to write a Spring Boot service, it automatically:

• Uses Java 17 records for DTOs
• Applies constructor injection (no @Autowired)
• Uses @ConfigurationProperties with records (no @Value)
• Follows the correct package structure (domain/, service/, controller/, dto/)
• Adds @Valid on controller inputs
• Uses @Transactional on service methods
• Writes Flyway migrations instead of ddl-auto

No prompting needed. It just knows.

---

Slash Commands (8 commands)

Slash commands are on-demand workflows you invoke with /command-name in Claude Code.

| Command | What It Does | |---------|--------------| | /plan | Creates a step-by-step implementation plan before writing code. Identifies affected files, risks, and complexity. | | /code-review | Reviews uncommitted changes for security issues, code quality, and testing gaps. | | /tdd | Drives test-driven development: RED (failing test) -> GREEN (minimal code) -> IMPROVE (refactor). | | /build-fix | Incrementally fixes build errors one at a time until the build succeeds. | | /api-design | Designs REST API endpoints with request/response schemas, error formats, and data models. | | /docker-setup | Generates Dockerfile, docker-compose.yml, and .dockerignore by detecting your project stack. | | /system-design | Walks through system design: requirements, architecture, data design, APIs, scaling, reliability. | | /db-schema | Designs database schemas: identifies entities, picks the right DB, defines tables/collections, plans migrations. |

Example: Using /plan

You: /plan Add order cancellation with inventory rollback

Claude:
## Implementation Plan: Order Cancellation

### Phase 1: Domain Changes
- Add `CANCELLED` to OrderStatus enum
- Add CancellationReason value object
- New Flyway migration V6__add_cancellation_fields.sql

### Phase 2: Service Layer
- OrderCancellationService with rollback logic
- InventoryService.rollback(orderId) method
- Kafka event: orders.order.cancelled

### Phase 3: API
- POST /api/v1/orders/{id}/cancel
- CancelOrderRequest record with reason field

### Phase 4: Tests
- Unit: cancellation service, inventory rollback
- Integration: full cancel flow with Testcontainers
- Edge cases: already cancelled, already shipped

### Risks
- Race condition: order shipped while cancellation in progress
- Partial rollback if inventory service fails mid-operation

### Estimated Complexity: Medium
Files affected: 8 | New files: 3 | Migration: Yes

---

Agents (5 agents)

Agents are specialized AI personas with their own system prompts, tools, and reasoning models. They handle deeper analysis than slash commands.

| Agent | Model | What It Does | |-------|-------|--------------| | planner | Sonnet | Analyzes requirements, reads existing patterns, identifies files to change, produces phased implementation plans. Never writes code. | | code-reviewer | Sonnet | Scans recent changes for bugs, logic errors, style violations, and stack-specific anti-patterns. Categorizes by severity. | | security-reviewer | Opus | Checks code for hardcoded secrets, SQL injection, missing auth checks, XSS, CSRF, and stack-specific vulnerabilities. | | architect | Opus | System design and architecture decisions. Analyzes options, explains trade-offs, recommends patterns for services and technology choices. | | tdd-guide | Sonnet | TDD coach that ensures test-first development. Guides through RED/GREEN/IMPROVE cycles. Blocks implementation before tests exist. |

How Agents Differ from Commands

Commands are scripts — they follow a fixed workflow. Agents are thinkers — they analyze your specific situation, adapt their approach, and provide nuanced feedback. Use commands for routine tasks, agents for decisions that need judgment.

---

Skills (14 skill packs)

Skills are deep domain knowledge packs that activate contextually. When Claude detects you're working on a Spring Boot project, the relevant skills auto-load to provide patterns, examples, and best practices.

| Skill | Domain | What It Provides | |-------|--------|-----------------| | springboot-patterns | Java/Spring | REST API design, layered architecture, caching, async processing, logging patterns | | springboot-security | Java/Spring | Auth/authz, validation, CSRF, secrets, security headers, rate limiting | | springboot-tdd | Java/Spring | JUnit 5, Mockito, MockMvc, Testcontainers, JaCoCo coverage patterns | | java-coding-standards | Java | Java 17 idioms, records, sealed classes, pattern matching, Optional usage | | jpa-patterns | Java/DB | Entity design, relationships, query optimization, transactions, auditing, pagination | | postgres-patterns | Database | Query optimization, schema design, indexing strategies, security best practices | | kafka-patterns | Java/Messaging | Spring Kafka producers/consumers, manual offset commits, idempotent consumers, dead letter topics | | python-patterns | Python | Pythonic idioms, PEP 8, type hints, dataclasses, best practices | | python-testing | Python | pytest, TDD methodology, fixtures, mocking, parametrization, coverage | | frontend-patterns | React/JS | React patterns, state management, performance optimization, UI best practices | | backend-patterns | Node.js | API design, database optimization, server-side patterns for Express/Next.js | | iterative-retrieval | AI/Agents | Progressive context retrieval for solving the subagent context problem in RAG systems | | eval-harness | AI/Dev | Eval-driven development (EDD) framework — define success criteria before implementation | | security-review | Security | Comprehensive security checklist: secrets, input validation, SQLi, XSS, CSRF, auth |

---

Hooks (4 hooks)

Hooks are automated guardrails that run before or after Claude uses a tool. They catch mistakes in real-time without you having to remember to check.

Pre-Tool Hooks (run before execution)

| Hook | Trigger | Action | |------|---------|--------| | Block dangerous commands | git push --force, git reset --hard, rm -rf | Blocks execution with error message | | Git push r