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 aigorahub · Claude Skill · ★ 218
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is elves safe to install? View the security audit →
Elves They work while you sleep. Elves is an open-source Agent Skill for autonomous, multi-batch development. It gives AI coding agents (Claude Code, Codex, or any agent that supports the Agent Skills standard) the ability to execute large development plans unattended (with testing, review, and documentation) while surviving context compaction across long runs. You write the plan and own the merge decision. The agent does everything in between. Running Elves is a two-stage process: first you stage the run, then in a separate call you start it. Staging lines up the plan, branch, PR, and survival guide, then stops. Launching is a short second prompt that turns the agent loose. Keeping the two calls separate is the single biggest thing that prevents "the elves stopped" failures. See Stage, then launch. This is still early. The system I use in production at Aigora is more elaborate than what you see here. It includes custom review tools, proprietary verification infrastructure, and integration with our internal deployment pipeline.
| Stars | 218 |
| Forks | 14 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 65.9117064435578/100 |
| Last Updated | 2026-09-06 |
| Created | 2026-03-21 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~25k |
Looking for a elves alternative? If you're comparing elves 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.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.
Chat, specs, tasks, and code. An autonomous engineering platform. Full autonomy when you trust it. Full contro
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Explore other popular claude skill tools:
elves is Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.. It is categorized as a Claude Skill with 218 GitHub stars.
elves is primarily written in Python. It covers topics such as agent-skills, ai-agents, autonomous-coding.
You can find installation instructions and usage details in the elves GitHub repository at github.com/aigorahub/elves. The project has 218 stars and 14 forks, indicating an active community.
elves is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to elves on Agent Skills Hub include smart-ralph, clay, wallfacer. 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: