89 tagged policy as code, measured the same way as everything else here.
Browse within: AI Safety 61agent-governance 60credentials 60python 60agent-infrastructure 13devtools 13open-source 5
Skill Claude CodeCodex
Infrastructure as Code (IaC) security scanning using Checkov with 750+ built-in policies for Terraform, CloudFormation, Kubernetes, Dockerfile, and ARM templates. Use when: (1) Scanning IaC files for security misconfigurations and compliance violations, (2) Validating cloud infrastructure against CIS, PCI-DSS, HIPAA…
LF-Decentralized-Trust-labs/gitmesh
Skill Claude CodeCodex
GitMesh Agents UI design system. Invoke this skill when creating new components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language. Covers component creation, design tokens, typography, status/priority systems, composition…
LF-Decentralized-Trust-labs/gitmesh
Skill Claude CodeCodex
GitMesh: Policy-as-Code Engine for Open Source AI Agent Orchestration.
LF-Decentralized-Trust-labs/gitmesh
Skill Claude CodeCodexGemini CLI
GitMesh: Policy-as-Code Engine for Open Source AI Agent Orchestration.
Skill Claude CodeCodex
Create a Google Calendar event with title, time, and attendees.
Skill Claude CodeCodex
List upcoming Google Calendar events for a given timerange.
Skill Claude CodeCodex
Anti-pattern detector and design rules for AI coding agents. Catches the specific mistakes AI makes when generating UI: gray text on color, nested cards, broken buttons, missing states. Use before shipping any frontend.
Skill Claude CodeCodex
Check a side-effectful action against this organization's approved gnt rules before taking it, and stop on a blocked or needshuman verdict.
Skill Claude CodeCodex
Drive Assay's install-to-evidence golden path and interpret its stdout and exit codes. Use when an agent must operate or diagnose Assay; do not use it to infer provider execution, external side effects, or a clean result from missing output.
Skill Claude CodeCodex
: bad yaml.
Skill Claude CodeCodex
This file intentionally omits Claude Skill frontmatter with name or description.
Skill Claude CodeCodex
Review SkillOps reference repository changes.
Skill Claude CodeCodex
Guard an autonomous agent's x402 payment with the live IntentFence service before it signs. Use when an agent receives a PAYMENT-REQUIRED challenge, is about to pay an x402 endpoint, needs to enforce a USDC price ceiling or payee allowlist, or needs signed evidence that an exact Base USDC quote was checked. Also use…
Skill Claude CodeCodex
Inspect a public x402 endpoint before an agent pays it. Use when an agent discovers an unfamiliar x402 URL, needs to confirm that a live route returns a valid PAYMENT-REQUIRED challenge, wants to enforce a maximum Base USDC price or recipient allowlist, or needs signed readiness evidence without paying the target…
Skill Claude CodeCodex
Screen a Base recipient before an autonomous USDC transfer or x402 payment. Use when an agent is about to pay a new Base address, send USDC, approve a Base merchant, evaluate counterparty risk, or enforce a pre-transaction AML, sanctions, phishing, mixer, or malicious-address policy. The check is fail-closed, costs…
Skill Claude CodeCodex
Multi-vendor code review council — runs the Claude code-reviewer agent alongside external second opinions (codex, gemini) in parallel, then synthesizes with citation verification, source tagging, and disagreement surfacing. Optionally seats grok (--with-grok) and/or an OpenRouter free-tier advisor (--with-free) as…
Skill Claude CodeCodex
Agent-driven, read-only self-audit of the harness — run the machine integrity layer once as a dry-run, present a per-check pass/fail table, cite the P1-1 doc-reality result, and for any failure give root-cause + fix + backlog follow-up. Consumes the machine gates; it does not reimplement them. NOT for auditing a…
Skill Claude CodeCodex
Dispatch a multi-wave plan to specialist agents with audit + risk-area abort. Supports --auto-push, --auto-merge, --goal-mode for budgeted runs, --verify-blocking for a hard completion-claim gate. NOT for writing the plan itself (that is /spec), and NOT for a single small edit with no waves — just make the edit.