By sdui-hq
Pre-execution validator that blocks dangerous bash commands before they run
Sdui's marketplace for AI tools
This repository provides shared configurations for Claude Code.
| Configuration | Description | Location |
|---|---|---|
| settings.json | Shared Claude Code settings (sandbox, env vars, etc) | .claude/settings.json |
| DevContainer | Containerised environment with network isolation | .devcontainer/ |
Shared CLI configuration .claude/settings.json can be found in the .claude directory.
A pre-configured development container with filesystem + network isolation. See README.md for details.
[!NOTE] DevContainers are recommended for autonomous Claude sessions that require additional security layers.
for quick tasks with fewer permission prompts, use Sandboxing
Add this marketplace to Claude Code:
/plugin marketplace add sdui-hq/ai-marketplace
# or via CLI
claude plugin marketplace add sdui-hq/ai-marketplace
| Plugin | Description | Type | Install |
|---|---|---|---|
| sdui-pr-review | Automated PR code review with GitHub comment (/sdui-pr-review:review) | Command | sdui-pr-review@ai-marketplace |
| sdui-telemetry | Configure Coralogix telemetry for Claude Code (/sdui-telemetry:setup) | Command | sdui-telemetry@ai-marketplace |
| command-safety | Blocks dangerous bash commands before execution | Hook | command-safety@ai-marketplace |
| lint-runner | Runs linting when Claude completes tasks | Hook | lint-runner@ai-marketplace |
| notifications | Cross-platform desktop notifications for Claude Code events | Hook | notifications@ai-marketplace |
| better-init | Enhances CLAUDE.md initialization with best practices and guidelines | Skill | better-init@ai-marketplace |
| sdui-eng-design | Generate feature design docs (/feature-design-doc) | Command | sdui-eng-design@ai-marketplace |
| statusline | Statusline with git integration, PR and context window progress bar | Hook | statusline@ai-marketplace |
Install any plugin:
/plugin install <plugin>@ai-marketplace
How to create a new plugin: Claude Code Plugins
claude --plugin-dir /path/to/ai-marketplace/plugins/command-safety
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 sdui-hq/ai-marketplace --plugin command-safetyEnhances CLAUDE.md initialization with best practices and guidelines
Engineering design document command for structured feature planning
Statusline showing directory, session name, git branch and context window usage
Configure Coralogix telemetry for Claude Code
Cross-platform desktop notifications for Claude Code
PreToolUse hook that auto-approves safe Bash commands by parsing them into an AST and matching against configurable 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
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
Displays risk level and recovery info before every Bash command execution
Block destructive git and filesystem commands before execution
Auto-approve compound Bash commands (pipes, chains, subshells) by parsing each segment via shfmt AST and checking against allow/deny lists