guardrails
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…
Plugin bundle · by Francesco Vadicamo
About
guardrails is a plugin bundle for AI coding tools published by Francesco Vadicamo. Marketplaces we read that list it: 1 (Community GitHub marketplaces). We first saw it on 2026-10-19 and have recorded no change since. As of our marketplace pass on 2026-10-22.
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 comments stripped, quoted strings neutralized except interpreter arguments like ssh / sh -c / eval / su / doas), so a command that merely mentions a destructive pattern is not flagged. It hard-blocks catastrophic Bash commands (rm -rf /, rsync --delete, docker volume rm) and makes rm/rmdir scope-aware: operations whose operands all resolve inside the allowed workspace (the session project root, temp dirs, any $GUARD_ALLOWED_EXTRA root, or a variable assigned from a bare mktemp earlier in the same command) run silently, while anything outside it (or any glob/variable/escape it cannot resolve) raises a single reflective confirmation. git reset --hard / clean / restore, shred, dd, mkfs still always prompt.
What it asks for
- Installs as a plugin bundle
- Hooks: 1
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Community GitHub marketplaces declares.
/plugin marketplace add fvadicamo/dev-agent-skills
/plugin install guardrails@dev-agent-skillsWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Community marketplace fvadicamo/dev-agent-skills (Open the source on GitHub) | Listed | 1.7.6 | Forks (GitHub): 6 Stars (GitHub): 72 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
Listed in one community marketplace
| Marketplace | Repository | Stars (GitHub) |
|---|---|---|
| dev-agent-skills | fvadicamo/dev-agent-skills | 72 |
What the bundle contains
As published on Community GitHub marketplaces.
Hooks: 1
PreToolUse
What changed
- Became a product we track
- Community GitHub marketplaces: appeared
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
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…
-
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…
-
Railguard is a safer, context-aware alternative to --dangerously-skip-permissions for Claude Code. Instead of choosing between approving every command manually or giving Claude…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
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…
-
Auto-allows low-risk bash commands in Claude Code using bash-classify
-
Block destructive git and filesystem commands before execution
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on 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…
-
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…
-
Railguard is a safer, context-aware alternative to --dangerously-skip-permissions for Claude Code. Instead of choosing between approving every command manually or giving Claude…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Block destructive git and filesystem commands before execution
Has a listing on 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.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
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…
Has a listing on 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…
-
MCP server for terminal commands, file operations, and process management
-
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…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
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…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
Has a listing on Community GitHub marketplaces (3)
-
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…
-
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…
-
Auto-allows low-risk bash commands in Claude Code using bash-classify
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
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.
-
Use an installed rhost CLI to run ordinary commands on SSH-reachable Linux hosts with local-like stdin, output, and exit behavior.
-
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…
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
Has a listing on 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.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
-
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management…
Has a listing on Cursor: cursor/plugins (5)
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
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.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
Has a listing on Docker MCP Catalog (5)
-
MCP server for terminal commands, file operations, and process management
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
Has a listing on Official MCP Registry (5)
-
Merge gates and safety checks for AI coding agents via MCP.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
agent-guardrail io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
-
Read-only context and complete checks against patterns learned from git history. Local; no LLM.
-
guard io.github.codapult/guard
Local-first architecture guardrails and project context for JS/TS AI coding agents.
Has a listing on 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.
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
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.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.