Guardrails plugins

nizos/probity

Plugin Claude Code

Bundles 1 hook

TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.

Clear-Sights/Makoto

Plugin Claude Code

Bundles 6 hooks

Form-based session record holds before writes, commit/push and final answers.

studioKjm/ai-harness-template

Plugin Claude Code

Bundles 2 skills, 44 commands, 12 agents · 1,869 tokens together

Specification-first AI harness: 11 structural gates, 11 Ouroboros commands, 11 agent personas, and 3-tier architecture enforcement. v2.1: Pair Mode (Navigator-Driver + independent test design + /review command).

railyard-dev/railguard

Plugin Claude Code

Bundles 3 hooks

A secure runtime for Claude Code. Intercepts every tool call with policy-based allow/block/ask decisions, evasion detection, path fencing, file snapshots, and audit logging.

IgorGanapolsky/ThumbGate

Plugin Claude Code

Bundles 74 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins · 6,303 tokens together

One 👎 becomes a hard rule the agent cannot bypass. Captures thumbs-down feedback, distills it into PreToolUse Pre-Action Checks, enforced across every future Claude Code session.

MaxwellCalkin/sentinel-ai

Plugin Claude Code

Bundles 1 skill, 5 commands, 1 MCP server · 52 tokens together

Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.

zyx77550/sparda

Plugin Claude Code

Lists 1 plugin

Plugin marketplace listing 1 plugin: sparda-gate.

zakariagharzouli/sparda

Plugin Claude Code

Bundles 1 hook

The behavior gate for AI edits — proves each edit lost no auth guard, dropped no route, and grew no blast radius. Deterministic, <2s, offline, zero API key.

fatmo666/Caushell

Plugin Claude Code

Bundles 2 skills, 5 hooks · 41 tokens together

Session-aware shell guardrails for Claude Code backed by the Caushell runtime.

Codoop/codoop-flow

Plugin Claude Code

Bundles 12 skills, 14 agents · 1,203 tokens together

In-session orchestration for the codoop-flow Agent-Centric ticket pipeline: pick -> build -> verify -> review -> ship, driven by a skill plus a deterministic guardrail CLI.

karanb192/bouncer

Plugin Claude Code

Bundles 1 hook

A one-file PreToolUse door-guard that bounces destructive Bash commands (rm -rf, DROP TABLE, curl|sh, force-push, device wipes) before they run. Blocks 45/45 known footguns, 0 false positives.

alelaguard/agentguards-plugins

Plugin Claude Code

Bundles 3 skills, 3 hooks · 143 tokens together

LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a…

matanryngler/deployshield

Plugin Claude Code

Bundles 2 skills, 1 command, 2 hooks · 43 tokens together

Production safety guardrails that block write/mutating operations on cloud, database, IaC, and deployment CLIs.

mauhpr/agentlint-plugin

Plugin Claude Code

Bundles 2 commands, 3 agents, 7 hooks, 1 MCP server · 65 tokens together

Claude Code marketplace wrapper for AgentLint's AI-agent guardrail engine. 77 rules across 8 packs, hybrid AgentChute security feeds, circuit-breaker visibility, inline-ignore reasons.

trycoin-ai/agentrisk

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 64 tokens together

Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

sodam-ai/SoDam-Loop-Eng

Plugin Claude Code

Bundles 9 skills, 9 commands, 1 agent, 4 hooks · 878 tokens together

A Korean-language safety loop for non-developers who ask an AI to keep repairing a task until it works. Its description says it currently supports a single repair mode with 14 safety guardrails enabled by default.

kubeleash/kubeleash

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 129 tokens together

Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.

ofershap/vibe-guard

Plugin Claude Code

Bundles 1 skill, 2 commands · 60 tokens together

Always-on security guardrails for AI-generated code. Catches hardcoded secrets, missing auth, insecure database rules, and the 20 things AI agents forget before you deploy.

MohamedEmbarak/SLL

Plugin Claude Code

Bundles 2 hooks

Three hooks, no agents. A stated test result must reproduce, a fabricated import never reaches disk, and every command's real output is recorded. Active in every project the moment it is installed.

SSHdotCodes/auto-cc

Plugin Claude Code

Bundles 1 hook

Automatic tool-call review for Claude Code. A local encoder scores every proposed tool call before it runs, approving safe work and blocking dangerous calls with an explanation the agent can act on.