A disciplined AI-assisted development workflow with specification-first development, test-driven implementation, ADRs, and traceable task management. Inspired by the Rue language development process.
npx claudepluginhub rand/disciplined-process-plugin --plugin disciplined-processManage Architecture Decision Records
Decompose specifications into dependency-aware work items
Show system health and diagnostics
Show help and workflow reference
Interactive setup wizard for the disciplined development workflow.
Migrate between task tracker providers
Generate structured progress reports from project state (Beads, git). Reports are timestamped Markdown files with a machine-readable JSON companion.
Attempt automatic repair of system issues
Reset degradation to full mode
Run a structured code review against current changes.
Session management for work context preservation
Manage specifications with [SPEC-XX.YY] IDs
Show current degradation status
Task tracking via configured provider
Code and test traceability validation
Unlock degradation level
Goal-backward verification of task completion
Hyper-critical code reviewer for VDD workflow
Specialized code review agent that evaluates changes against the disciplined process checklist. Use when performing detailed code reviews, when /dp:review needs deeper analysis, or when reviewing PRs.
Specification decomposition subagent. Produces structured JSON work graphs from spec documents. Fresh context ensures maximum working memory for analysis.
Architecture Decision Record format and process. Use when making architectural decisions, documenting technical choices, evaluating alternatives, or when asked about past decisions. Triggers on ADR creation, architecture discussions, or "why did we choose" questions.
Core orchestration for disciplined AI-assisted development. Auto-invokes when starting new features, implementing tasks, or working on any development that should follow the spec-first, test-driven process. Triggers on task planning, feature implementation, bug fixes, refactoring work, or when beads/bd tasks are referenced.
Specification authoring with traceable paragraph IDs. Use when writing specifications, updating specs, adding new features to specs, or when implementing code that needs to reference spec paragraphs. Triggers on spec creation, implementation traceability, or coverage verification.
Use when working from decomposed task files or Beads issues created by spec-decompose. Guides proper task pickup, context loading, implementation, and handoff. Triggers when working with decomposed tasks, task files in docs/tasks/, or Beads issues with hole labels.
Test-driven development methodology with four test types - unit, integration, property, and e2e. Use when writing tests, planning test strategy, implementing features test-first, or verifying test coverage. Triggers when tests are mentioned, test files are being created, or test-first approach is needed.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.