By nityeshaga
Blocks accidental git pushes to the main branch when Claude Code runs in bypass permissions mode, reducing the risk of unintended changes to protected branches.
A marketplace of essential Claude Code plugins for developers.
/plugin to open the plugin managernityeshaga/claude-code-essentialsThen install plugins from the Discover tab.
Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes.
Features:
Usage:
Commands:
/teach-me - Learn something new/quiz-me - Test your retention with spaced repetitionStorage: All tutorials and learning data are stored securely in the cloud, synced automatically across all your devices and Claude platforms. Your data is tied to your account and accessible wherever you use Claude.
Essential Claude Code commands, agents, hooks, and skills for everyday development workflows.
Commands (12):
/cc, /cleanup, /compound, /create-developer-doc, /create-pitch, /depcheck, /gem-upgrade, /logically-commit, /pinpoint, /review, /study, /tidy-commits
Agents (1):
dhh-reviewer - DHH-style code reviewerHooks:
block-main-push - Prevents accidental git pushes to main branchSkills (6):
ai-tool-designer - Designing tools for AI agentsdhh-rails-expert - DHH-style Rails development guidancekamal-deploy - Expert Kamal deployment for containerized appsmcp-builder - MCP server development guideprompt-engineer - Prompt engineering for AI systemsskill-creator - Guide for creating Claude skillsPrevents accidental pushes to main branch in Claude Code bypassPermissions mode.
Important: Install at the user level (~/.claude/settings.json) to protect all repositories.
The vulnerability: If Repo A has basics installed at project level but Repo B has no plugin, Claude running in Repo B can push to Repo A's main branch via git -C /path/to/RepoA push origin main. Project-level hooks don't help - protection depends on where Claude runs, not the target repo.
Hooks:
block-main-push - Blocks git pushes to main branch (PreToolUse on Bash)See safe-push README for installation instructions and technical details.
Want to add a plugin to this marketplace? Open a PR!
MIT
Executes bash commands
Hook triggers when Bash tool is used
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 nityeshaga/claude-code-essentials --plugin safe-pushEssential Claude Code commands, agents, hooks, and skills for everyday development workflows
Chief-of-staff workflows for you and your team — email briefing, action-item tracking, and the operational routines that keep everything moving.
Other AI models for tasks they excel at — Gemini image generation and Gemini thinking.
Creative direction and pixel-perfect UI implementation — websites, apps, products, brands, dashboards, tools. Acts as a creative director who thinks through purpose, story, and feeling before any implementation, and as a precision UI engineer who builds designs with zero visual deviation.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent 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.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Persistent coding companion for Claude Code, Pi, and Oh My Pi. MCP-based terminal pet with ASCII art, stats, reactions, and personality.