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 managedcode · Codex Skill · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MCAF safe to install? View the security audit →
MCAF Concepts Managed Code Coding AI Framework Developed and sustained by Managed Code March 2026 What MCAF Is MCAF is a framework for building real software with AI coding agents. It defines how to: keep durable engineering context in the repository make AI work from plus repo-native docs and skills verify behaviour with tests and static analysis keep AI guidance small, explicit, and versioned The goal of MCAF: Use AI to build real products in a way that is predictable, safe, and repeatable. MCAF has three core elements: Context — code, docs, , and skills live with the repo. Verification — tests and analyzers are the decision makers, not opinions. Instructions — root and local files define how agents work here. These concepts define the framework (the "what" and "why"). is the bootstrap procedure (the "how"). Repository files apply both to a specific solution. 1.1 Bootstrap Surface is skill-first.
| Stars | 52 |
| Forks | 6 |
| Language | CSS |
| Category | Codex Skill |
| License | CC-BY-4.0 |
| Quality Score | 56.3614330732178/100 |
| Last Updated | 2026-06-25 |
| Created | 2025-12-01 |
| Platforms | claude-code, codex, gemini |
| Est. Tokens | ~19k |
Looking for a MCAF alternative? If you're comparing MCAF 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.
Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and mu
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
c4 GenAI Suite
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
The Keystone Framework for AI-Driven Code ! Turn any AI coding assistant into a disciplined, project-aware eng
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Explore other popular codex skill tools:
MCAF is MCAF is a framework for building software products together with AI coding agents.. It is categorized as a Codex Skill with 52 GitHub stars.
MCAF is primarily written in CSS. It covers topics such as ai, ai-agents, ai-framework.
You can find installation instructions and usage details in the MCAF GitHub repository at github.com/managedcode/MCAF. The project has 52 stars and 6 forks, indicating an active community.
MCAF is released under the CC-BY-4.0 license, making it free to use and modify according to the license terms.
The top alternatives to MCAF on Agent Skills Hub include aiwg, AgenticGoKit, c4-genai-suite. 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: