by mvanhorn · Codex Skill · ★ 849
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
go install github.com/mvanhorn/agentcookie/cmd/agentcookie@v1.0.0Taken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 849 |
| Forks | 72 |
| Language | Go |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 71/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-07 |
| Created | 2026-05-16 |
| Platforms | browser, cli, go |
| Est. Tokens | ~19k |
agentcookie Your agent runs on a Linux box (a Grok Bot VM, a cloud agent runtime, a homelab server) and needs to act as you on every site you're already logged into. agentcookie keeps that box's Chrome session in sync with your Mac's, continuously, encrypted over your Tailscale tailnet, with zero per-site auth ceremony. Cookie-authenticated sites show the logged-in UI after live CDP inject.
Looking for a agentcookie alternative? If you're comparing agentcookie with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundred
471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: