claude-forge — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by sangrokjung · Claude Skill · ★ 822

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

🔒 Is claude-forge safe to install? View the security audit →

About claude-forge

Turn Claude Code into a full development environment What's New v3.0 &

agentsai-assistantai-codingai-frameworkai-pair-programminganthropicautomationclaude-codeclaude-code-agentscli-tools

Quick Facts

Stars822
Forks176
LanguageShell
CategoryClaude Skill
LicenseMIT
Quality Score65.3850055094599/100
Open Issues30
Last Updated2026-09-03
Created2026-02-23
Platformsclaude-code, cli
Est. Tokens~19k

Compatible Skills

These tools work well together with claude-forge for enhanced workflows:

  • ai-marketing-claude-code-skills — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • agent-safehouse — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • dotfiles — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • claude-code-ultimate-guide — semantic(0.32)+complementary+rare_topics+similar_pop+shared_platform (56%)
  • my-ai-tools — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

claude-forge alternative? Top 6 similar tools

Looking for a claude-forge alternative? If you're comparing claude-forge 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.

  • pro-workflow by rohitg00 · ⭐ 2.8k

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng

  • Claude-Command-Suite by qdhenry · ⭐ 1.3k

    Professional slash commands for Claude Code that provide structured workflows for software development tasks

  • agentsys by agent-sh · ⭐ 984

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • Software-Engineer-AI-Agent-Atlas by syahiidkamil · ⭐ 316

    ATLAS: a senior-engineer layer for Claude Code. Explore with wireframes & prototypes, clarify the essentials,

  • navigator by alekspetrov · ⭐ 232

    Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is claude-forge?

claude-forge is oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.. It is categorized as a Claude Skill with 822 GitHub stars.

What programming language is claude-forge written in?

claude-forge is primarily written in Shell. It covers topics such as agents, ai-assistant, ai-coding.

How do I install or use claude-forge?

You can find installation instructions and usage details in the claude-forge GitHub repository at github.com/sangrokjung/claude-forge. The project has 822 stars and 176 forks, indicating an active community.

What license does claude-forge use?

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

What are the best alternatives to claude-forge?

The top alternatives to claude-forge on Agent Skills Hub include pro-workflow, Claude-Command-Suite, agentsys. 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 Claude Skill tools