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 zhnt · Codex Skill · ★ 1.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is loushang safe to install? View the security audit →
Loushang English | 中文 Loushang is a method-native AI work system for running complex work from intent to verified delivery. Current focus: , a CLI and terminal workbench for software development with model routing, persistent sessions, tools, extensions, and method-guided delivery. Why Loushang Modern AI agents can plan and act, but complex work still breaks down when context is lost, execution cannot be resumed, tools are hard to govern, and results are not verified. Loushang treats methods, stages, roles, tools, sessions, and work products as runtime objects. The goal is not just to make agents smarter, but to make complex work more reliable, recoverable, auditable, and deliverable. What You Can Use Today : a coding-focused CLI and terminal workbench. : a provider-aware AI SDK with model registry, streaming, tool calls, and cost helpers. Sessions: persistent coding sessions with resume, fork, export, and diagnostics. Tools: built-in coding tools and configurable tool surfaces. Extensions: project-level extension hooks, custom tools, dynamic resources, and commands. Methods and skills: method-guided coding turns and reusable workflow assets.
| Stars | 1,492 |
| Forks | 239 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 64.0110280813611/100 |
| Open Issues | 43 |
| Last Updated | 2026-09-19 |
| Created | 2026-05-29 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~14k |
Looking for a loushang alternative? If you're comparing loushang 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.
🧑🎨 A collection of Golang agentic skills that works
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & e
Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent w
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
Explore other popular codex skill tools:
loushang is AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, K. It is categorized as a Codex Skill with 1.5k GitHub stars.
loushang is primarily written in Python. It covers topics such as agent, agent-harness, agentic.
You can find installation instructions and usage details in the loushang GitHub repository at github.com/zhnt/loushang. The project has 1.5k stars and 239 forks, indicating an active community.
loushang is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to loushang on Agent Skills Hub include cc-skills-golang, agentsys, the-pair. 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: