130 tagged Guardrails, measured the same way as everything else here.
Browse within: AI Safety 117agent-reliability 86thompson-sampling 86gemini 24copilot 21dotnet 21saas 21ai-coding 19LLM 18claude-code-plugin 16codex-cli 16safety 16ai-gateway 15gateway 15
Skill Claude CodeCodex
Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails…
Skill Claude CodeCodex
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…
Skill Claude CodeCodex
Use when audited OpenClaw conversations or outgoing Feishu/Slack/channel messages contain concrete business numbers such as revenue, percentages, stock prices, contract values, costs, market share, or funding and need evidence checks plus red/yellow/green audit stamps after sends.
Skill Codex
Audit system prompts, agent prompts, router prompts, tool/function-call prompts, and coding-agent instructions as executable contracts. Use before writing or seeding prompts; blocks vague "fix this / write code" tasks missing ownership and verification. Works with Hermes, Claude Code, Codex, OpenCode, OpenClaw.
Skill Claude CodeCodex
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
Skill Claude CodeCodex
Use when the user explicitly asks to install, uninstall, diagnose, or look up rules in VibeGuard. Ordinary coding, review, build failures, and generic safety requests do not activate this skill.
Skill Claude Code
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude CodeCodex
Charter — an operating contract system for autonomous agents. Use when the user invokes /charter or /goal, says they want to start/track/resume long-running work, gives vague intent to operationalize, or when you must own and update a durable charter contract with approval gates, ledger, and receipts. Object model…
Skill Claude Code needs its repo
Run a comprehensive Clean Code audit against the codebase — module size, function complexity, long parameter lists, TODO/FIXME markers, commented-out code, duplication (DRY), Boy Scout delta, dead exports, test smells, shell-parity (PS/Bash twins), dep boundaries (cross-package imports), frozen-arrays drift…
zscaler/zguard-ai-integrations
Skill Claude Code
Scan prompts, AI responses, and code for security threats using Zscaler AI Guard. Supports 19 prompt detectors and 21 response detectors including: prompt injection, toxicity, DLP, PII, PII DeepScan, personal data, secrets, malicious URLs, code, gibberish, invisible text, brand risk, competition, language, legal…
Skill Claude CodeCodex
Runtime guardrails for AI coding agents. Recorded-budget preflight, loop, retry, and timeout checks in instrumented Python. Zero dependencies, local-first, MIT licensed.
Skill Claude CodeCodex
Use this skill to audit an AI system for security vulnerabilities including prompt injection, sensitive data exposure, excessive agent permissions, unsafe tool calls, and insecure output handling. Grounded in OWASP GenAI LLM Top 10 (2026). Activates before production deployment of any LLM-based application, agent, or…
Skill Claude Code needs its repo
AI agent guardrails — defends prompts against injection attacks, jailbreaks, and evasion; scans LLM responses for leaked secrets and harmful content. Up to 36 inline defenses (24 default), 3 output scanners, and adaptive ranking. Keywords: shield, guardrails, prompt injection, defense, security, scan.
Skill Claude CodeCodex
Read and change a database safely through Gatekeeper. You propose SQL, a human approves and runs it in Beekeeper Studio, and the rows come back to you; you never connect to the DB or run SQL yourself. Reads are the default; a write runs only if a human arms write mode. Use this whenever you need to read data, run a…
Skill Claude CodeCodex
A coordination skill for routing complex requests across research, discussion, review, and other roles or providers. A provider is the service that performs a delegated task.
Skill Claude CodeCodex
Write and test Supabase/Postgres Row-Level Security policies so users can only access their own rows. Use when a table holds user data, when enabling RLS, or when auditing access control on Supabase.
Skill Claude CodeCodex
MASTER SKILL — Single entry point for creating Power BI dashboards from CSV/Excel. Mandatory for any Power BI task, dashboard creation, PBIP generation, DAX modeling, or visual report editing. Automatically loads sub-skills and enforces 6 guardrails, 5 core styling principles, and script verification.
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Topic-based content filtering to block harmful or unauthorized content in agent output.
Skill Codex
Fully automatic GitHub PR review and production deployment gate for trusted repos. Use when configuring or operating a scheduled PR gate that checks open PRs, downloads them locally, runs complete containerized validation with mocked external services, comments or rejects failing PRs, promotes passing PRs through…
a1024053774/design-integrity-guardrails
Skill Claude Code
Audit whether tests, evals, benchmarks, autoresearch tasks, generated artifacts, public APIs, or user-visible workflows provide independent behavioral evidence, including acceptance and release verdicts for model-driven Agent products. Use at a completion checkpoint, not for ordinary implementation or…
Skill Claude Code
Use when an agent, harness, or CI pipeline produces a scientific/numeric prediction and you need an INDEPENDENT third-party adjudication of whether that claim is trustworthy before acting on it. Also use when you need to turn "the agent said it validated itself" into a blocking gate with a real exit code. Covers…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: