Intercept bash tool calls before execution to block Claude from reading, writing, or accessing secret and sensitive files, preventing unintended exposure of credentials and private data in your dev workflow.
npx claudepluginhub agentic-dev3o/devx-plugins --plugin secrets-guardAI writes the code. You design the system.
Battle-tested Claude Code plugins, curated from daily use.
Installation • Plugins • Philosophy
Most plugins in the wild are vibe-coded in an afternoon and never touched again.
These are different.
Every command in this marketplace comes from real, daily usage — refined over months, not as experiments, but as core tools in an actual development workflow.
1. Add the marketplace
/plugin marketplace add agentic-dev3o/devx-plugins
2. Browse and install plugins
/plugin
| Plugin | What it does | Install |
|---|---|---|
| devx-git | Conventional commits & PR creation (skills: /commit, /pr) | /plugin install devx-git@devx-plugins |
| devx-qa | Architecture analysis with ASCII diagrams & skill improvement | /plugin install devx-qa@devx-plugins |
| secrets-guard | Blocks Claude from accessing sensitive files (70+ patterns) | /plugin install secrets-guard@devx-plugins |
| landing-page | Structured copywriting & Astro 5 landing page generation | /plugin install landing-page@devx-plugins |
| nano-banana-ultimate | Image generation via Gemini with 8 domain-specialized skills | /plugin install nano-banana-ultimate@devx-plugins |
Battle-tested — Every command exists because it solved a real problem, repeatedly.
Opinionated — Conventional commits. Proper PR descriptions. ASCII diagrams. Decisions are made so you don't waste time configuring.
Honest — If something doesn't work well, it gets fixed or removed.
Minimal — No dependencies. No build steps. Just markdown that Claude understands.
Built by Pierre Tomasina — building tools for AI-native development.
Dev3o — Teaching developers the 10% that AI can't figure out.
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Prevents sensitive data (secrets, PII) from reaching AI servers by scanning files before they are read into conversation
Blocks secrets and PII before they reach the Anthropic API
665 safety hooks for Claude Code — prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions
Battle-tested Claude Code plugin for engineering teams — 50 agents, 188 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim