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 enmanuelmag · MCP Server · ★ 182
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-harness-kit safe to install? View the security audit →
@cardor/agent-harness-kit A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase. Instead of letting AI agents roam freely through your project with no memory, no coordination, and no audit trail, agent-harness-kit gives them a shared structure: a task backlog, a defined workflow, a persistent log of every action taken, and a health gate that must be green before any work begins. You stay in control. The agents stay on track. Table of Contents @cardor/agent-harness-kit Table of Contents Why this exists How it works Features Requirements Installation Commands - - - - - - [](#ahk-e
| Stars | 182 |
| Forks | 9 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 74.7560304494645/100 |
| Last Updated | 2026-09-21 |
| Created | 2026-05-04 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~19k |
These tools work well together with agent-harness-kit for enhanced workflows:
Looking for a agent-harness-kit alternative? If you're comparing agent-harness-kit with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
The governed runtime for Python agents you can let act: policy on every action, durable runs, sandboxes, budge
The minimal interpretable model router that learns & adapts to your agent workflows
MCP Fusion - The framework for AI-native MCP servers.
An MCP Server for Ollama
Explore other popular mcp server tools:
agent-harness-kit is A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.. It is categorized as a MCP Server with 182 GitHub stars.
agent-harness-kit is primarily written in TypeScript. It covers topics such as agent, agent-harness, claude-code.
You can find installation instructions and usage details in the agent-harness-kit GitHub repository at github.com/enmanuelmag/agent-harness-kit. The project has 182 stars and 9 forks, indicating an active community.
agent-harness-kit is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agent-harness-kit on Agent Skills Hub include sandboxed.sh, agnix, omnicoreagent. 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: