By st0nefish
Bash command safety classifier with shfmt-based compound parsing, extensible custom patterns, and WebFetch domain management
Executes bash commands
Hook triggers when Bash tool is used
No model invocation
Executes directly as bash, bypassing the AI model
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 st0nefish/agent-toolkit --plugin permission-managerPull/edit/push workflow for remote or privileged files — bridges SSH and sudo boundaries using rsync
Configurable status line for Claude Code — git status, model, context, API usage, cost segments with ANSI colors
List, search, and read files inside JARs without extraction
Markdown linting and formatting — check, format, setup
GitHub and Gitea CLI wrapper — issues, pull requests, CI runs, with auto-detected platform and normalized JSON output
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
Safety hooks to block or require user approval for dangerous commands (rm, git operations, .env access, file size limits)
Block destructive git and filesystem commands before execution
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.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.