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 JasonxzWen · Claude Skill · ★ 77
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is harness-hub safe to install? View the security audit →
Harness Hub 简体中文 | English Harness Hub is a personal repo harness toolkit for making agent work repeatable across projects. It installs the full standard skill/routing set, initializes the standard target harness when requested, validates the result, and keeps managed files safe through lock-backed lifecycle commands. Imported skills can keep their upstream style; Harness Hub mainly owns routing, source records, harness templates, and lifecycle safety. Agent execution rules live in AGENTS.md. Human-facing workflow detail lives in Development Workflow. First-Use Summary Harness Hub does a small set of bounded jobs: and inspect a target repo and stay read-only. creates the root harness only when you explicitly approve it. installs the standard skill set only; it does not create root harness files. the standard harness includes an LLM Wiki context pack under . and decide continue vs interrupt and can append local Loop ledgers after . creates, builds, validates, and preflights source-backed public posts. For a new target repo, start with a dry run: Move to only after reviewing the planned files. Harness Hub does not create schedules, webhoo
| Stars | 77 |
| Forks | 0 |
| Language | JavaScript |
| Category | Claude Skill |
| Quality Score | 60.0071925323778/100 |
| Last Updated | 2026-07-23 |
| Created | 2026-03-01 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~16k |
Looking for a harness-hub alternative? If you're comparing harness-hub 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.
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your L
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Odoo MCP for AI agents — 41 tools, gated writes, multi-instance. Free hosted: ERPipe → mcp.erpipe.com
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group variou
Explore other popular claude skill tools:
harness-hub is Repository-first deterministic migration and atomic Skill source for Claude Code and Codex.. It is categorized as a Claude Skill with 77 GitHub stars.
harness-hub is primarily written in JavaScript. It covers topics such as agent-skills, agentic-workflow, claude-code.
You can find installation instructions and usage details in the harness-hub GitHub repository at github.com/JasonxzWen/harness-hub. The project has 77 stars and 0 forks, indicating an active community.
The top alternatives to harness-hub on Agent Skills Hub include ask-user-questions-mcp, agent-designer, mcp-odoo. 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: