by ruiwang20010702 · Codex Skill · ★ 103
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Personal-memory-driven AI work twin that uses Codex to work inside real projects.
| Stars | 103 |
| Forks | 2 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 54.0431458849492/100 |
| Last Updated | 2026-09-03 |
| Created | 2026-07-31 |
| Platforms | codex, node |
| Est. Tokens | ~13k |
These tools work well together with foursday for enhanced workflows:
Looking for a foursday alternative? If you're comparing foursday 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.
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
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
agent wiki +engineering skills
Explore other popular codex skill tools:
foursday is Personal-memory-driven AI work twin that uses Codex to work inside real projects.. It is categorized as a Codex Skill with 103 GitHub stars.
foursday is primarily written in JavaScript. It covers topics such as ai-agents, codex, developer-tools.
You can find installation instructions and usage details in the foursday GitHub repository at github.com/ruiwang20010702/foursday. The project has 103 stars and 2 forks, indicating an active community.
foursday is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to foursday on Agent Skills Hub include meridian, adhdev, daymon. 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: