guardrails-lite
Pattern-based PreToolUse-style checks that deny .env reads (Read/Grep/Glob and Bash readers), git force pushes, and recursive rm on /, ~ or $HOME before Claude Code runs them…
Plugin-Paket · von edtrackai
Überblick
guardrails-lite ist ein Plugin-Paket für KI-Coding-Tools von edtrackai. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-16 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-22.
Pattern-based PreToolUse-style checks that deny .env reads (Read/Grep/Glob and Bash readers), git force pushes, and recursive rm on /, ~ or $HOME before Claude Code runs them. About 75 lines of dependency-free JavaScript.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add davepoon/buildwithclaude
/plugin install guardrails-lite@buildwithclaudeWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz davepoon/buildwithclaude (Quelle auf GitHub öffnen) | Gelistet | 0.1.0 | Forks (GitHub): 0 Sterne (GitHub): 0 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| buildwithclaude | davepoon/buildwithclaude | 3 670 |
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
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…
-
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…
-
Block destructive git and filesystem commands before execution
-
Safety guardrails for running Claude Code with reduced supervision. The guard-destructive PreToolUse hook matches against a normalized view of each command (heredoc bodies and…
-
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…
-
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…
-
A pre-tool-use hook plugin that automatically scans code for security vulnerabilities before Claude writes it to disk. Detects eval usage, Function constructor abuse, hardcoded…
-
Runtime security hooks: CLAUDE.md injection scanner (SessionStart) + Bash prompt injection detector (PreToolUse)
-
Blocks Claude Code from writing or committing leaked secrets.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
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…
-
Block destructive git and filesystem commands before execution
-
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…
-
A pre-tool-use hook plugin that automatically scans code for security vulnerabilities before Claude writes it to disk. Detects eval usage, Function constructor abuse, hardcoded…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
Gelistet auf 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.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
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…
Gelistet auf 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…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
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
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Codex Security workflows for security scans, analysis, and investigation.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Qodo setup, code intelligence, and review workflows.
Gelistet auf Community GitHub marketplaces (4)
-
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…
-
Safety guardrails for running Claude Code with reduced supervision. The guard-destructive PreToolUse hook matches against a normalized view of each command (heredoc bodies and…
-
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…
-
Runtime security hooks: CLAUDE.md injection scanner (SessionStart) + Bash prompt injection detector (PreToolUse)
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
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…
-
Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable, and high-performance applications.
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
-
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management…
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
power-automate
Build, edit, run, and debug Power Automate cloud flows via the FlowAgent MCP server — connection lifecycle, surgical edits, copy across environments, run management, and validated…
Gelistet auf Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
-
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.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
Gelistet auf Docker MCP Catalog (5)
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
A comprehensive security scanner for MCP servers with YARA rules and static analysis capabilities.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
Gelistet auf Official MCP Registry (5)
-
Read-only context and complete checks against patterns learned from git history. Local; no LLM.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
cra-readiness-audit io.github.jmshinhwa/cra-readiness-audit
Flags the lines in your repo that break the EU Cyber Resilience Act - default passwords, disabled TL
-
ai-code-scanner io.github.4hmetuyar/ai-code-scanner
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
-
codesafer io.github.goldmembrane/codesafer
Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats.
Gelistet auf 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.
-
Compare dotenv files and report which keys are missing or extra, by name only.
-
Run SQL queries and inspect database schemas through safe, visible MCP tools.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.