Analyze changes and propose CLAUDE.md updates. Accepts an optional argument describing what changed (e.g., `/claude-md we switched from Jest to Vitest`). Use when the user says "update claude.md", "sync claude.md", "document this in claude.md", after finishing a task that introduced new patterns or conventions, when new tools/commands/dependencies were added, or when project architecture changed. Do NOT trigger for simple questions about CLAUDE.md content, reading CLAUDE.md, or general project questions.
Create clean conventional commits. Use when the user wants to commit changes, make a commit, save progress, or says "commit". Enforces single-line conventional commit format with automatic task number detection from branch names. Never adds Co-Authored-By lines.
Interview the user relentlessly about a plan, design, or architecture until every branch of the decision tree is resolved. Use when the user wants to stress-test a plan, get grilled on their design, poke holes in an idea, play devil's advocate, challenge an approach, or says things like "grill me", "what am I missing?", "is this plan solid?", "review my architecture", "tear this apart", or "challenge my thinking". Also use when someone presents a plan and seems uncertain or asks for feedback on a design decision.
A comprehensive plugin suite for Claude Code that streamlines software development workflows from task creation through development planning to architectural review.
This repository contains two integrated plugins that work together to create a complete development workflow:
Create well-structured tasks for software development projects with standardized formatting and comprehensive details.
Features:
Transform tasks into detailed development plans and ensure architectural quality through comprehensive reviews.
Features:
Use the /task:create command to create a structured task with a detailed description:
/task:create I need to implement Redis caching for the additional amenities API endpoint.
Currently, the endpoint fetches data directly from MongoDB using an aggregation pipeline,
which takes around 100-300ms. We need to cache this data since amenities change infrequently.
The cache should be company-specific and automatically invalidated when properties are updated.
Please review the existing implementation in @api/modules/property/controllers/PropertyController.php
and follow patterns from @api/components/services/cache/WebsitesettingRedisCacheService.php.
The endpoint is used by the frontend property form at @frontend/src/components/PropertyForm.tsx.
Use the /dev-plan:create command to transform your task into a detailed implementation plan:
/dev-plan:create Create a development plan for task gh-7097. The task involves implementing
Redis caching for the additional amenities API endpoint. Make sure to analyze the current
implementation and propose a cache-first strategy with automatic invalidation.
Use the /dev-plan:review command to conduct architectural review:
/dev-plan:review @docs/dev-plans/gh-7097-redis-caching-amenities.md
Contributions are welcome! Please feel free to submit issues or pull requests.
For issues, questions, or feature requests, please open an issue on GitHub.
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.
npx claudepluginhub mrstroz/claude-code-plugins --plugin utilsMulti-agent PR review system with specialized agents for architecture, code quality, bugs, security, tests, and performance
Agent Teams-powered collaborative code review with cross-reviewer communication, AI Slop detection, and unified professional reports
JIRA integration for task creation, feedback, release notes, product roadmaps, daily summaries, release testing scenarios, and direct API data fetching
Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry, fix-spec recovery, and per-phase memory writeback. Works on Claude Code and Codex.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
End-to-end development workflow: design → draft-plan → orchestrate → review → pr-create → pr-review → pr-merge
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
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