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 revfactory · Claude Skill · ★ 9.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is harness safe to install? View the security audit →
Harness Agent Team & Skill Architect — A Claude Code Plugin 한국어 A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. Overview Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a harness for this project" and it automatically generates agent definitions () and skills () tailored to your domain. Key Features Agent Team Design — 6 architectural patterns: Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, and Hierarchical Delegation Skill Generation — Auto-generates skills with Progressive Disclosure for efficient context management Orchestration — Inter-agent data passing, error handling, and team coordination protocols Validation — Trigger verification, dry-run testing, and with-skill vs without-skill comparison tests Workflow Installation Via Marketplace Add the marketplace shell /plugin marketplace add revfactory/harness
| Stars | 9,082 |
| Forks | 1,289 |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 70.8148053485479/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-28 |
| Created | 2026-03-26 |
| Platforms | claude-code |
| Est. Tokens | ~17k |
These tools work well together with harness for enhanced workflows:
Looking for a harness alternative? If you're comparing harness with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Anti
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed
Multi-Agent Harness for Production AI
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering princi
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you thi
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng
Explore other popular claude skill tools:
harness is A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.. It is categorized as a Claude Skill with 9.1k GitHub stars.
You can find installation instructions and usage details in the harness GitHub repository at github.com/revfactory/harness. The project has 9.1k stars and 1289 forks, indicating an active community.
harness is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to harness on Agent Skills Hub include agents, pydantic-ai, hive. 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: