Plugin marketplace

shakhoff-claude-marketplace

Claude Code plugins for AI-driven software development: complete SDLC kit, sprint orchestration with discipline, deep audit, and more. Schemas at schemas/, validator at scripts/validate-marketplace.sh.

Add this marketplace

Then install any plugin below by name — each page has its exact command.

ai-scrum

claude

Universal sprint orchestrator for AI agents. Applies Scrum-like discipline to any development task: context investigation, task decomposition with AC/DoR/DoD, hard execution gates, internal SE review, optional Codex external review, HTML reports with design system integration, LSP-based code analysis, issue tracker MCP integration. Adds /sprint:doctor preflight, /sprint:metrics, /sprint:from-ticket, /sprint:loop, /sprint:replay, /sprint:fork, /sprint:edit-plan and /sprint:codex-status. Works as a platform - any plugin can declare sprint_required and ai-scrum orchestrates execution.

25 skills · 23 commands · 5 agents · hooks

0

solo-sdlc

claude

Complete SDLC kit for solo developers using Claude Code. Six-phase pipeline (Discovery → Requirements → Architecture → Implementation → Verification → Ship) with TDD methodology, multi-perspective code review, deep verification, ADR/PRD writing, DDD modeling, design system management, autonomous overnight loops, and Karpathy code discipline. Now emits machine-readable verification reports consumable by ai-scrum DoD. Complements ai-scrum (which adds hard discipline hooks and sprint state machine).

21 skills · 9 commands · 13 agents · hooks

0

Deep one-shot SDLC audit: architecture, domain logic, code, tests, security, docs, deployment, plus optional performance and UX/accessibility phases. Generates actionable backlog with business-weighted prioritization, audit-trends across snapshots, and a sprint-bridge that exports findings as ai-scrum plans. Multi-language: Python, JS/TS, Go.

17 skills · 16 commands · 10 agents

0

Cross-model code review: four OpenRouter models (Gemini 3.5 Flash, GPT-5.5, GLM-5.1, Qwen3.7-Max) independently judge a diff against the repo's AGENTS.md contract in one call, aggregated to a single PASS/FAIL gate. The agent injects context (code path, test evidence, commit SHA); models never read files or run tests. Emits a machine-readable verification-report consumable by ai-scrum DoD. Complements ai-scrum Codex external review as a heavier multi-family panel.

1 command · 1 MCP server

0

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins4 plugins