By kuklaph
Research → Plan → TDD → Commit workflow with PM collaboration. Systematic development with quality gates, test-driven implementation, and intelligent documentation management.
Verify and ship with quality gates
Configure RPTC workflow in project CLAUDE.md - sync with current version
Team-based feature development with parallel research, planning, implementation, and review agents
Research → Plan → TDD → Verify in one seamless flow
Team-based bug fixing with parallel reproduction, root cause analysis, fix, and review agents
Implementation planning specialist. Maps file changes, designs TDD-first test strategies, identifies dependencies and risks. For medium-to-complex features requiring structured TDD.
Code review specialist with confidence-based reporting. REPORT ONLY - does not make changes. Identifies KISS/YAGNI violations, complexity issues. Main context handles fixes.
Documentation review specialist with confidence-based reporting. REPORT ONLY - does not make changes. Identifies stale docs, missing updates, breaking changes. Main context handles fixes.
Unified research specialist for codebase exploration and web research. Mode A uses 4-phase code-explorer methodology. Mode B consults 20+ sources with cross-verification. Mode C combines both with gap analysis.
Unified quality reviewer combining code review, security analysis, and documentation checks. REPORT ONLY - does not make changes. Provides real-time feedback to implementation agents in team workflows. Covers KISS/YAGNI violations, OWASP Top 10, and documentation sync.
Agent Teams execution mode for RPTC. Invoke explicitly when coordinating multiple independent work streams across parallel agent sessions — batch features, parallel bug fixes, or sprint items that don't share files. Orchestrates team creation with RPTC-compliant spawn prompts, file ownership boundaries, approval flow, and completion integration. For team-based single-feature or single-bug workflows, prefer `/rptc:feat-team` or `/rptc:fix-team` — this skill targets multi-stream batch work.
Planning methodology for the RPTC architect-agent. Covers incremental sub-agent delegation, implementation constraints generation (5 categories), 6-phase planning methodology (context analysis, test strategy, implementation steps, dependencies/risk, self-critique, output), context management strategy, quality standards, best practices, and anti-patterns. Produces TDD-ready implementation plans.
Use during planning phases to explore user intent, requirements, and design through structured dialogue before implementation.
Code review methodology for the RPTC code-review agent. Covers hierarchical review framework (4 tiers), over-engineering checklist, integration completeness check, behavioral testing checklist, assertion quality checklist, false positive guidance, confidence scoring (>=80 threshold), domain-specific checks, and structured output format. Report-only mode.
Shared principles for RPTC agents. Loaded at session start by all agents. Contains Surgical Coding, Simplicity Directives, Pattern Reuse (Rule of Three), SOP references, and evidence-based rationale. Must be read before any work begins.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Research -> Plan -> TDD -> Commit workflow for Claude Code and Codex.
Version: 3.16.6 Status: Beta License: MIT
The distributable plugin lives in plugins\rptc.
Use plugins\rptc\README.md as the canonical user documentation for installation, commands, Codex skill entrypoints, agent behavior, and workflow details.
.
├── .claude-plugin\marketplace.json # Claude marketplace entry pointing to plugins\rptc
├── plugins\rptc\ # Distributable plugin package
├── scripts\ # Maintainer release/version scripts
├── tests\ # Development tests
├── CHANGELOG.md # Release history
├── CONTRIBUTING.md # Contribution guidance
└── README.md # Repository landing page
Before committing a release:
./scripts/verify-version.sh
claude plugin validate plugins/rptc
git diff --check
On Windows, run the scripts with Git Bash if bash resolves to WSL:
& "$env:LocalAppData\Programs\Git\bin\bash.exe" scripts/verify-version.sh
To bump all release version locations:
./scripts/sync-version.sh X.Y.Z
The version scripts verify these seven locations:
plugins\rptc\.claude-plugin\plugin.json.claude-plugin\marketplace.json metadata version.claude-plugin\marketplace.json plugin versionplugins\rptc\.codex-plugin\plugin.jsonREADME.mdplugins\rptc\README.mdCHANGELOG.mdnpx claudepluginhub kuklaph/rptc-workflow --plugin rptcCascade CMS MCP server with 37 tools for reading, editing, searching, auditing, publishing, and managing Cascade CMS content.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
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.