Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By fprochazka
Automatically validate AI tool commands for safety and correctness using LLM backends like Vertex AI. Triggers validation on permission requests matching exit from plan mode, running plan annotation to ensure secure tool use before execution.
npx claudepluginhub fprochazka/claude-code-plugins --plugin ai-tool-use-validatorA collection of Claude Code plugins by Filip Procházka.
Add this marketplace to Claude Code:
claude plugin marketplace add fprochazka/claude-code-plugins
Then install plugins:
claude plugin install skill-keyword-reminder@fprochazka-claude-code-plugins
To upgrade installed plugins to the latest version:
claude plugin marketplace update fprochazka-claude-code-plugins
claude plugin update skill-keyword-reminder@fprochazka-claude-code-plugins
| Plugin | Description |
|---|---|
| skill-keyword-reminder | Automatically reminds Claude to load relevant skills when keyword triggers appear in user prompts |
| gemini-cli | Skill and review agent for using Gemini CLI with massive context windows (1M tokens) for codebase analysis and second opinions |
| gemini-deep-research | Skill for conducting autonomous deep research using Google's Gemini Deep Research Agent |
| glab | Skill for interacting with GitLab using the glab CLI |
| glab-discussion | Standalone CC plugin + CLI for reading and managing GitLab MR discussion threads |
| glab-mr | GitLab MR tools - fix failed CI, resolve comments, and more |
| ai-tool-use-validator | AI-powered tool use validation using LLM backends (Vertex AI, etc.) to evaluate command safety and correctness |
| slackcli | Skill for interacting with Slack workspaces using the slackcli CLI |
| migrate-to-uv | Skill for migrating Python projects from Poetry, pipx, or pip to uv |
| metabasecli | Skill for interacting with Metabase using the metabase CLI |
| gogcli | Skill for interacting with Google services (Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasks, Forms, Chat, People) using the gog CLI |
| rabbitmqadmin | Skill for inspecting RabbitMQ instances using the rabbitmqadmin CLI (rabbitmqadmin-ng) |
| searxngcli | Skill for searching the web using a SearXNG instance via the searxngcli CLI |
| web-researcher | Iterative web research agent that searches, discovers new directions, and synthesizes findings |
| code-review | Multi-agent branch code review — conventions, architecture, bugs, security, and git history reviewed in parallel |
plugins/<name>/ directoryplugins/<name>/.claude-plugin/plugin.json with name, version, descriptionplugins/<name>/README.md.claude-plugin/marketplace.json with matching versionplugins/<name>/.claude-plugin/plugin.json.claude-plugin/marketplace.jsonclaude plugin update <name>@fprochazka-claude-code-plugins to get updatesMIT
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
Validates Claude Code plugin structure against official Anthropic spec and Intent Solutions enterprise standard
734 safety hooks for Claude Code — prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions
Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Smart command safety filter for Claude Code — parses shell pipelines and evaluates per-command safety rules to auto-approve safe commands and block dangerous ones
Skill for searching the web using a SearXNG instance via the searxngcli CLI
Skill for migrating Python projects from Poetry, pipx, or pip to uv
Skill for using Gemini CLI with massive context windows (1M tokens) for codebase analysis and second opinions
GitLab MR tools - fix failed CI, resolve comments, and more
Skill for conducting autonomous deep research using Google's Gemini Deep Research Agent
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