codegrab — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 epilande · Agent Tool · ★ 95

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is codegrab safe to install? View the security audit →

About codegrab

CodeGrab ✋ An interactive CLI tool for selecting and bundling code into a single, LLM-ready output file. ❓ Why? When working with LLMs, sharing code context is essential for getting accurate responses. However, manually copying files or creating code snippets is tedious. CodeGrab streamlines this process by providing a clean TUI (Terminal UI), alongside a versatile CLI (Command-Line Interface). This allows you to easily select files from your project, generate well-formatted output, and copy it directly to your clipboard, ready for LLM processing. ✨ Features 🎮 Interactive Mode: Navigate your project structure with vim-like keybindings in a TUI environment 💻 CLI Mode: Run non-interactively ( flag) to grab all valid files based on filters, ideal for scripting 🧹 Filtering Options: Respect rules, handle hidden files, apply customizable glob patterns, and skip large files 🔍 Fuzzy Search: Quickly find files across your project ✅ File Selection: Toggle files or entire directories (with child items) for inclusion or exclusion 📄 Multiple Output Formats: Generate Markdown, Plain Text, or XML output ⏳ Temp File: Generate the output file in your system's temporary directory 📋 Clipboard...

aiartificial-intelligencebubbleteabundleclicommand-linecontextdevtoolsgenaigo

Quick Facts

Stars95
Forks10
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score65.7602886928437/100
Open Issues4
Last Updated2026-01-02
Created2025-03-31
Platformscli, go
Est. Tokens~15k

codegrab alternative? Top 6 similar tools

Looking for a codegrab alternative? If you're comparing codegrab 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.

  • gptree by travisvn · ⭐ 290

    A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or c

  • mcpsnoop by kerlenton · ⭐ 347

    Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP ser

  • gob by juanibiapina · ⭐ 72

    Process manager for AI agents (and humans)

  • chief by MiniCodeMonkey · ⭐ 471

    Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • sec-edgar-mcp by stefanoamorelli · ⭐ 357

    A SEC EDGAR MCP (Model Context Protocol) Server

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is codegrab?

codegrab is ✋ Interactive CLI tool for selecting and bundling code into a single, LLM-ready output file. It is categorized as a Agent Tool with 95 GitHub stars.

What programming language is codegrab written in?

codegrab is primarily written in Go. It covers topics such as ai, artificial-intelligence, bubbletea.

How do I install or use codegrab?

You can find installation instructions and usage details in the codegrab GitHub repository at github.com/epilande/codegrab. The project has 95 stars and 10 forks, indicating an active community.

What license does codegrab use?

codegrab is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codegrab?

The top alternatives to codegrab on Agent Skills Hub include gptree, mcpsnoop, gob. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools