Try “Claude Code skills”, “MCP servers for Cursor” or “Codex” · Esc to close

AI-Driven Development 🤖 Agent Open source

Cross-agent skills for disciplined AI development, plus a Bash safety hook for Claude Code

Agent workflows & frameworks · Open source ★ 151 · +2 this week · MIT · updated 2026-10-02

6.5editor score
View on GitHub ↗
GitHub stars
151
Stars this week
+2
Forks
13
Licence
MIT
Last push
2026-10-02
Maintainer
CodeAlive-AI
Installnpx skills add CodeAlive-AI/ai-driven-development

Third-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.

Works with

About AI-Driven Development

What it does

AI-Driven Development is CodeAlive-AI's umbrella collection of Agent Skills plus one Bash safety hook. The skills aim to make coding agents follow repeatable engineering habits and to let an agent manage its own setup, such as MCP servers, hooks, settings and plugins, so you do not have to hand-edit JSON, YAML or TOML config files.

What is inside

  • Agent self-configuration: skills for managing MCP servers across many coding agents, hooks, settings, skills (including an optimisation loop for training skills against held-out checks), plugin packaging, repository "agentic readiness" audits, and installing developer CLIs without leaking tokens into chat or shell history.
  • Engineering practice: an eight-step bug-fix protocol that also asks why the tests missed the bug, a plan-first gate that waits for approval before editing, a git history investigator, a complexity-control skill, a prompt-engineering reference set, a C# Roslyn rename helper and a repository activity summariser.
  • Research and docs: Semantic Scholar deep search, URL-to-Markdown fetching and a domain-language (DDD) thesaurus manager.
  • Extras: OpenRouter provider ranking, macOS and Windows machine-health skills, a clipboard helper and a Windows desktop QA skill.
  • bash-guard hook: a Go PreToolUse hook for Claude Code that parses shell commands properly and asks for confirmation before destructive file, database, infrastructure and cloud operations.

Works with

The skills follow the Agent Skills standard. The README names Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI and Antigravity. The bash-guard hook is for Claude Code only.

How to install

npx skills add CodeAlive-AI/ai-driven-development
npx skills add CodeAlive-AI/ai-driven-development --skill prompt-engineering

In Claude Code you can also add the repository as a plugin marketplace:

/plugin marketplace add CodeAlive-AI/ai-driven-development
/plugin install ai-driven-development@ai-driven-development

Maintenance and safety

The project is MIT-licensed and actively maintained, with semantic versioning on the plugin manifest. The hook's installer is a curl-to-shell script served from the project's own GitHub repository, so read it before running it. The macOS and Windows cleanup skills can delete files, although their riskier steps are off by default and ask for confirmation.

Who should use it

It suits developers who switch between several coding agents and want shared, disciplined workflows. Install single skills rather than the whole set, because some (such as the OS-health and C# skills) are niche.

agent-skills engineering-practices safety-hook cross-agent prompt-engineering

Pros

  • Skills follow the open Agent Skills standard, so they work across many coding agents
  • Covers practical workflows: bug-fix protocol, plan gate, agent self-configuration
  • bash-guard hook asks before destructive shell, DB and infra commands

Cons

  • Broad grab-bag; some skills (OS health, C# rename) are niche
  • The hook installs via a curl-to-shell script you should read first

Similar subagents & agents

All agent workflows & frameworks →

Spec Kit 🤖 AgentFree

GitHub's toolkit for spec-driven development with AI coding agents

★ 140k · +898 this week

8.5 Visit ↗

Task Master 🤖 AgentFree

AI task management that turns a PRD into tasks your coding agent works through

★ 28k · +39 this week

Fast Agent 🤖 AgentOpen source

Python framework for building, orchestrating and evaluating MCP-native AI agents

★ 3.9k · +9 this week

8.0 Visit ↗

OpenSpec 🤖 AgentFree

Lightweight spec-driven development: agree on changes before the agent codes

★ 71k · +564 this week

7.9 Visit ↗

CC Safety Net 🤖 AgentOpen source

Pre-execution guard that blocks destructive commands and secret access for coding agents

★ 1.6k · +11 this week

7.9 Visit ↗

BMAD Method 🤖 AgentFree

Agile AI-driven development with analyst, PM, architect, developer and UX agents

★ 54k · +269 this week

7.8 Visit ↗

Popular searches