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 cortexkit · Agent Tool · ★ 246
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is aft safe to install? View the security audit →
AFT Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents. <img src="https://img.shields.io/badge/licens
| Stars | 246 |
| Forks | 28 |
| Language | Rust |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.2536588612219/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-09 |
| Created | 2026-03-15 |
| Platforms | rust |
| Est. Tokens | ~1095k |
Looking for a aft alternative? If you're comparing aft with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Introducing the Assistant Swarm. An extension to the OpenAI Node SDK to automatically delegate work to any ass
Integrate LLM in any pipeline - fit/predict pattern, JSON driven flows, and built in concurency support.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Explore other popular agent tool tools:
aft is Tree-sitter powered code manipulation and analysis tools for AI coding agents. It is categorized as a Agent Tool with 246 GitHub stars.
aft is primarily written in Rust. It covers topics such as agent-framework, ai, ai-agents.
You can find installation instructions and usage details in the aft GitHub repository at github.com/cortexkit/aft. The project has 246 stars and 28 forks, indicating an active community.
aft is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to aft on Agent Skills Hub include DeepMCPAgent, OpenContext, openai-assistant-swarm. 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: