By nitromike502
Safe file deletion system that moves files to .deleted/ trash folder instead of permanently deleting them. Includes PreToolUse hook to block rm commands and redirect to safe deletion skill.
Executes bash commands
Hook triggers when Bash tool is used
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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 claimValidate and fix YAML frontmatter in Claude Code agent and command files
Documentation management plugin with Diátaxis framework support. Create, organize, and maintain project documentation following industry standards.
Multi-agent development workflow toolkit with SWARM methodology for coordinated software development
Summarize Claude Code sessions for seamless continuation across context windows. Maintains session history and enables work resumption.
npx claudepluginhub nitromike502/meckert-claude-code-marketplace --plugin file-deleterBlocks destructive commands outside the project directory. Allows file operations within the project (refactoring, cleanup) but prevents accidental damage outside it.
Safety hooks to block or require user approval for dangerous commands (rm, git operations, .env access, file size limits)
Детект команд на удаление (rm, rmdir, shred, git rm/clean/reset --hard/push --force, docker rm/volume rm/prune/compose down -v, SQL DROP/TRUNCATE/DELETE FROM) → запрос подтверждения y/n. Работает даже в bypassPermissions. Звук + macOS-баннер при детекте. Разбор по токенам — без ложных срабатываний на perform/transform/terraform.
Block destructive git and filesystem commands before execution
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.