No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by osovv · Codex Skill · ★ 246
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is grace-marketplace safe to install? View the security audit →
GRACE Framework - AI Agent Skills GRACE (Graph-RAG Anchored Code Engineering) is a methodology for AI-driven code generation with semantic markup, knowledge graphs, contracts, and log-driven verification. Originally created by Vladimir Ivanov (@turboplanner). This repository packages GRACE as reusable skills for coding agents. The current workflow is opinionated around: contract-first planning verification-first execution semantic markup for navigation and patching knowledge-graph synchronization controller-managed sequential or multi-agent implementation Current packaged version: What Changed In This Version is now a first-class GRACE artifact. now owns testing, traces, and log-driven evidence instead of being a light add-on. and now consume verification-plan excerpts in their execution packets. was removed from the public workflow. The supported implementation paths are now and . Repository Layout - Agent Skills format - Claude Code marketplace packaging - OpenPackage metadata Installation Via OpenPackage (recommended) Install the OpenPackage CLI first (), then: bash Install GRACE to your workspace opkg install gh
| Stars | 246 |
| Forks | 55 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.9868949060839/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-24 |
| Created | 2026-02-17 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~15k |
These tools work well together with grace-marketplace for enhanced workflows:
Looking for a grace-marketplace alternative? If you're comparing grace-marketplace with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Agent skills for Spec Kit
The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants
Shep AI CLI & UI - Multi-Session SDLC Control Center for AI Coding Agents
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Explore other popular codex skill tools:
grace-marketplace is GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.. It is categorized as a Codex Skill with 246 GitHub stars.
grace-marketplace is primarily written in TypeScript. It covers topics such as agent-skills, ai-code-generation, ai-engineering.
You can find installation instructions and usage details in the grace-marketplace GitHub repository at github.com/osovv/grace-marketplace. The project has 246 stars and 55 forks, indicating an active community.
grace-marketplace is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to grace-marketplace on Agent Skills Hub include ai-maestro, agent-skills, speckit-agent-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: