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 Osteoporosis · Agent Tool · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is luna-chat-coder safe to install? View the security audit →
Luna Chat Coder 한국어 README Version 0.1.5 Use ordinary ChatGPT Web conversations for real GitHub repository work—without running a local coding agent, opening a tunnel, or giving the chat access to your computer. ChatGPT already has a sandbox that can run code. The catch is that network restrictions can stop repository work when the chat needs source, dependencies, or a reliable way to publish a larger change. Luna teaches the model to keep the development loop in that built-in sandbox and use connected GitHub access only for the missing pieces. What you get A useful built-in workspace. Editing, building, testing, and debugging stay in the chat sandbox whenever it can do the job. Fewer dead ends. If the normal path cannot complete a step reliably, Luna can use GitHub for that step instead of giving up or moving the whole workflow elsewhere. Safer recovery. If the chat or sandbox disappears, Luna resumes from exact GitHub state rather than trying to recreate code from conversation history. Reliable handoff.
| Stars | 62 |
| Forks | 11 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 62.9200001992709/100 |
| Last Updated | 2026-09-06 |
| Created | 2026-08-17 |
| Platforms | browser |
| Est. Tokens | ~6k |
These tools work well together with luna-chat-coder for enhanced workflows:
Looking for a luna-chat-coder alternative? If you're comparing luna-chat-coder 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.
Canvas LMS MCP server — up to 102 tools and 8 agent skills for students & educators. Works with Claude, Cursor
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your L
Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Give your AI Agent a whole IDE, not just the files
Explore other popular agent tool tools:
luna-chat-coder is Agent Skill and repository template for end-to-end software development entirely inside ordinary Web AI chat.. It is categorized as a Agent Tool with 62 GitHub stars.
You can find installation instructions and usage details in the luna-chat-coder GitHub repository at github.com/Osteoporosis/luna-chat-coder. The project has 62 stars and 11 forks, indicating an active community.
luna-chat-coder is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to luna-chat-coder on Agent Skills Hub include canvas-mcp, claudepro-directory, ask-user-questions-mcp. 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: