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 scarletkc · Claude Skill · ★ 219
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agents safe to install? View the security audit →
Agents Shared standards and skills for AI coding agents: Claude Code, Codex CLI, and anything else that reads or the SKILL.md format. Featured in Awesome Agent Skills Contents : project-agnostic base guidelines. Copy it into a repository and prepend the project-specific sections (structure, commands, domain notes). : user-level collaboration preferences, kept separate from the project-level guidelines. : cross-agent skills; each skill is a directory containing a plus optional resources. Skills Each summary is generated from the skill's own metadata. Open its for the complete activation description and instructions. Hold a change to the size the request defines: no unrequested surfaces, no speculative layers, no half-a
| Stars | 219 |
| Forks | 12 |
| Language | Python |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 68.709534859099/100 |
| Last Updated | 2026-09-18 |
| Created | 2026-07-12 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~14k |
Looking for a agents alternative? If you're comparing agents 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.
Agent skills for Spec Kit
90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anth
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an ad
Explore other popular claude skill tools:
agents is Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.. It is categorized as a Claude Skill with 219 GitHub stars.
agents is primarily written in Python. It covers topics such as agent-skills, agents-md, ai-agents.
You can find installation instructions and usage details in the agents GitHub repository at github.com/scarletkc/agents. The project has 219 stars and 12 forks, indicating an active community.
agents is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agents on Agent Skills Hub include speckit-agent-skills, agent-skills, parallel-code. 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: