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 whut09 · MCP Server · ★ 104
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Repo-to-Agent-Context safe to install? View the security audit →
Repo-to-Agent-Context 中文 | English 面向编程 Agent 的 Agent Harness Runtime 控制面。 Repo-to-Agent-Context is an Agent Harness Runtime Control Plane for coding agents. 它不替代 Codex / Claude Code / Cursor 写代码，而是负责任务上下文编译、编辑边界、执行轨迹、策略检查、影响分析、测试推荐和下一步 Loop 决策。核心主线是： 它不是简单 repo summarizer，也不只是 context pack tool。它的目标是给 Codex / Claude Code / Cursor 增加一个静态但可验证的工程控制面：更少乱读、更少乱改，改完知道怎么验证，并能根据 trace、policy、tests、diff 和 freshness 进入下一轮修复或收口。 通过 AI Agent 使用 这个项目的主要用户就是 AI 编程工具。你可以直接在 Codex、Claude Code、Cursor 或其他 Agent 里说： 把 换成本地路径、GitHub 仓库或当前工作区名称即可。真实 key 只写入 ，不要提交。 它解决什么问题？ AI 编程工具通常不是不会写代码，而是没吃对上下文： 上下文丢失：不知道入口文件、模块边界、测试命令和架构约束。 乱读文件：把整个仓库塞进上下文，token 浪费严重。 乱改文件：没有编辑边界，不知道哪些路径是 generated、lockfile、migration、env。 改完不会验证：不知道该跑哪些测试、typecheck、lint 或 diff impact。 Repo-to-Agent-Context 的目标是把“给 Agent 的仓库记忆”升级成可生成、可更新、可验证、可闭环控制的运行时系统。 30 秒怎么用？ bash npx repo-to-
| Stars | 104 |
| Forks | 11 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 61.7732035972002/100 |
| Last Updated | 2026-06-13 |
| Created | 2026-05-24 |
| Platforms | claude-code, codex, mcp, node, vscode |
| Est. Tokens | ~15k |
These tools work well together with Repo-to-Agent-Context for enhanced workflows:
Looking for a Repo-to-Agent-Context alternative? If you're comparing Repo-to-Agent-Context 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.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Benzi is a compiler-backed coding agent that compiles your codebase into a resolved, queryable map of calls, d
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — pla
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T
MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback
Explore other popular mcp server tools:
Repo-to-Agent-Context is # Repo-to-Agent-Context 面向 AI 编程 Agent 的 Context Harness：将代码仓库转化为可读、可检索、可更新、可验证的任务级上下文资产，帮助 Codex / Claude Code / Cursor 减少 token 浪费、上下文丢失、误改与回归风险。 它不是另一个代码生成 Agent，而是 Agent Harness Engineering 基础设施. It is categorized as a MCP Server with 104 GitHub stars.
Repo-to-Agent-Context is primarily written in TypeScript. It covers topics such as agent, claude-code, codex.
You can find installation instructions and usage details in the Repo-to-Agent-Context GitHub repository at github.com/whut09/Repo-to-Agent-Context. The project has 104 stars and 11 forks, indicating an active community.
The top alternatives to Repo-to-Agent-Context on Agent Skills Hub include entroly, agnix, Benzi. 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: