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 ryanmac · Agent Tool · ★ 111
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is code-conductor safe to install? View the security audit →
🎼 Code Conductor Orchestrate multiple AI coding agents. Ship 10x faster. The Problem You're using Claude Code to ship features, but you're still working sequentially. One task at a time. One PR at a time. Meanwhile, your backlog keeps growing. The Solution Code Conductor lets you run multiple AI agents in parallel—each working on different features simultaneously. No conflicts. No coordination overhead. Just pure, parallelized productivity. Transform your workflow: 🚀 Hours, not weeks - Multiple agents tackle your backlog in parallel 🔒 Zero merge conflicts - Each agent works in isolated git worktrees 🤖 Works with Claude Code - Your favorite AI assistant, multiplied 🎯 Self-managing - Agents claim tasks, implement, and ship autonomously Quick Start One command. 60 seconds. Done. The installer auto-detects your stack (React, Python, Go, etc.) and configures everything. No GitHub tokens needed. No complex setup. ✨ What you get: ✅ GitHub Actions workflows that use built-in authentication ✅ No manual token creation or repository secrets required ✅ AI code reviews work automatically on all PRs ✅ Language-agnostic setup (no Python CI/CD added to non-Python projects) For
| Stars | 111 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.0413399147576/100 |
| Open Issues | 3 |
| Last Updated | 2026-03-30 |
| Created | 2025-07-22 |
| Platforms | claude-code, python |
| Est. Tokens | ~36k |
These tools work well together with code-conductor for enhanced workflows:
Looking for a code-conductor alternative? If you're comparing code-conductor 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.
Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and g
ADE( Agentic Development Environment) The spec-driven environment for AI coding agents, where your planning be
Safely run OpenCode, Codex, Claude Code with full permissions.
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
Run Claude Desktop’s Cowork mode natively on Linux — no macOS or VM required
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen
Explore other popular agent tool tools:
code-conductor is Ship 10x faster by running multiple Claude Code sub agents in parallel. GitHub-native orchestration for AI coding agents—no conflicts, no complexity, just pure parallelized productivity.. It is categorized as a Agent Tool with 111 GitHub stars.
code-conductor is primarily written in Python. It covers topics such as agentic, agentic-ai, agentic-ai-development.
You can find installation instructions and usage details in the code-conductor GitHub repository at github.com/ryanmac/code-conductor. The project has 111 stars and 11 forks, indicating an active community.
code-conductor is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to code-conductor on Agent Skills Hub include research-units-pipeline-skills, Frame, code-container. 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: