bash-classify-hook
Auto-allows low-risk bash commands in Claude Code using bash-classify
Paquete de plugins · de Filip Procházka
Resumen
bash-classify-hook es un paquete de plugins para herramientas de programación con IA publicado por Filip Procházka. Marketplaces que leemos y que lo publican: 1 (Community GitHub marketplaces). Lo vimos por primera vez el 2026-10-18 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-22.
Qué pide
- Se instala como paquete de plugins
- Hooks declarados: 2
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add fprochazka/bash-classify
/plugin install bash-classify-hook@fprochazka-bash-classifyDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Marketplace de la comunidad fprochazka/bash-classify (Abrir el código en GitHub) | Publicado | 0.14.1 | Forks (GitHub): 1 Estrellas (GitHub): 10 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| fprochazka-bash-classify | fprochazka/bash-classify | 10 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Hooks: 2
PermissionRequestPreToolUse
Qué cambió
- Pasó a ser un producto que seguimos
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Runtime security hooks: CLAUDE.md injection scanner (SessionStart) + Bash prompt injection detector (PreToolUse)
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Checks each Claude Code tool call before it runs. Blocks a command that would send one of your keys out, and asks before the agent runs a package or script it copied from…
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block dangerous commands, data exfiltration…
-
Displays risk level and recovery info before every Bash command execution
-
Balanced default runtime security plugin for Claude Code with shell, git, MCP, secret, exfiltration, and inline gateway guardrails.
-
Permission enforcement for Claude Code tool usage with policy-based rules, hierarchical settings, and optional kernel-enforced sandboxing via Landlock/seccomp (Linux) and Seatbelt…
-
macOS security hardening for Claude Code — PreToolUse/PostToolUse hooks that block secret exfiltration, prompt injection, persistence, and self-tampering.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block dangerous commands, data exfiltration…
-
PreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --force`, `python -c` / `node -e` eval…
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
Publicado en Claude Code: claude-plugins-official (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
Publicado en Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
MCP server for terminal commands, file operations, and process management
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Publicado en Community GitHub marketplaces (5)
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Runtime security hooks: CLAUDE.md injection scanner (SessionStart) + Bash prompt injection detector (PreToolUse)
-
Checks each Claude Code tool call before it runs. Blocks a command that would send one of your keys out, and asks before the agent runs a package or script it copied from…
-
Displays risk level and recovery info before every Bash command execution
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Use an installed rhost CLI to run ordinary commands on SSH-reachable Linux hosts with local-like stdin, output, and exit behavior.
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
Publicado en Cursor: cursor/plugins (5)
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Build apps, scripts, and automations with the TypeScript SDK.
Publicado en Docker MCP Catalog (5)
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
MCP server for terminal commands, file operations, and process management
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
Publicado en Official MCP Registry (5)
-
shellward io.github.jnMetaCode/shellward
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
-
bash-vet-mcp io.github.temurkhan13/bash-vet-mcp
Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
-
GuardianShield io.github.sparkvibe-io/GuardianShield
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
-
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
-
mcp-skill-sec io.github.sudo-ai-git/mcp-skill-sec
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
Publicado en npm registry (MCP servers) (5)
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 613 rules, 39 tools, CLI + doctor + host audit.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
-
Run SQL queries and inspect database schemas through safe, visible MCP tools.
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Community GitHub marketplaces. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.