branchbox-devcontainer-guardrails
Use when modifying BranchBox devcontainer/bootstrap workflows, compose templates, feature env-stash behavior, or manual E2E harness/release docs. Apply issue
Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.
Inspect the current Secure Claude Code posture, enabled protections, and recent audit events.
Agent Guardrail MCP Server
Action-level governance for AI agents -- control what they DO, not what they SAY
alchemy-openapi-skill
Operate Alchemy Prices API reads through UXC with a curated OpenAPI schema, path-templated API-key auth, and read-first guardrails.
app-ai-guardrails
Scaffold a greenfield app so the **full guardrail canon** is live in **commit #1** and every one of the 7 **gates** is **verified green** before that commit exists. The canon is stack-agnostic; each stack's mechanics live in one adapter file. The differentiator is **teeth**: gates that *fail* on vio
Zenable
Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails
Io.Github.ExpertVagabond/Guardrails
AI Agent Guardrails MCP server - security layer
Io.Github.Wyattbenno777/Icme Preflight
Jailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.
backend-mvp-guardrails
Use when designing or reviewing a backend MVP with tight budget, evolving schema, and reliance on third-party backends where idempotency, replay, and responsibility attribution are high-risk.
agent-safety
Use when bounding an LLM agent that already runs â scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or RAG (that is `building-agents`).
ab-test-planner
Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.
Stratum MCP
Structured execution for Claude Code — contracts, postconditions, gates, guardrails.
rag-blueprint
NVIDIA RAG Blueprint â deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, and more).
ThinkNEO Control Plane
Enterprise AI governance: spend, guardrails, policy, budgets, compliance, and provider health.
Javelin Guardrails Mcp Server
An MCP server that provides Javelin Standalone Guardrails
engram-architecture-guardrails
Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins. Trigger: Any change that affects system boundaries, ownership, state flow, or cross-package responsibilities.
BrainstormRouter MCP Server
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
gcp-ironclad
Use when securing API keys in GCP, hardening Gemini/Vertex API access against fraud, preventing leaked-key abuse, setting up spend guardrails on Google Cloud, or auditing API key restrictions across a GCP organization. Triggers on phrases like "secure GCP keys", "gemini api fraud", "gcp ironclad", "harden gcp project", "lock down google cloud api keys".
Io.Github.Corbat Tech/Coding Standards
AI coding standards that enforce production-grade code with DDD, SOLID, TDD guardrails.