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 LarsCowe · Claude Skill · ★ 406
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is bmalph safe to install? View the security audit →
bmalph BMAD-METHOD planning + Ralph autonomous implementation, wired through platform-specific instructions, skills, and command indexes. What is bmalph? bmalph bundles and installs two AI development systems: BMAD-METHOD — Planning agents and workflows (Phases 1-3) Ralph — Autonomous implementation loop (Phase 4) bmalph provides: — Install both systems — Update to latest versions — Check installation health — Transition from BMAD to Ralph — Start Ralph loop with live dashboard — Check for upstream updates bma
| Stars | 406 |
| Forks | 50 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.4291328342461/100 |
| Open Issues | 57 |
| Last Updated | 2026-09-19 |
| Created | 2026-01-23 |
| Platforms | claude-code, cli, node |
| Est. Tokens | ~21k |
Looking for a bmalph alternative? If you're comparing bmalph 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.
BMAD Method skills for Claude Code - Auto-detection, Memory integration, Slash commands. Transform Claude Code
Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Cod
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin
A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops
Boss Skill - BMAD 全自动研发流水线（多 Agent 编排）
🧠 Context Engineering Research - Not just another agent collection, but using research and context engineerin
Explore other popular claude skill tools:
bmalph is Unified AI Development Framework - BMAD phases with Ralph execution loop. It is categorized as a Claude Skill with 406 GitHub stars.
bmalph is primarily written in TypeScript. It covers topics such as ai-development, bmad, claude-code.
You can find installation instructions and usage details in the bmalph GitHub repository at github.com/LarsCowe/bmalph. The project has 406 stars and 50 forks, indicating an active community.
bmalph is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to bmalph on Agent Skills Hub include claude-code-bmad-skills, open-ralph-wiggum, pydantic-deepagents. 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: