by unbrowse-ai · Codex Skill · ★ 329
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
The forge that forges itself. Self-writing meta-extension for OpenClaw.ai
| Stars | 329 |
| Forks | 28 |
| Language | JavaScript |
| Category | Codex Skill |
| Quality Score | 56.4587505525749/100 |
| Last Updated | 2026-04-04 |
| Created | 2026-01-30 |
| Platforms | node |
| Est. Tokens | ~102k |
Looking for a foundry alternative? If you're comparing foundry 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.
The forge that forges itself. Self-writing meta-extension for OpenClaw.ai
terminally online
A personal 24x7 AI assistant like OpenClaw that runs on your messaging platforms. Send a message on WhatsApp,
PowerContext: The Next Generation of PowerMem.
PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect you
Explore other popular codex skill tools:
foundry is The forge that forges itself. Self-writing meta-extension for OpenClaw.ai. It is categorized as a Codex Skill with 329 GitHub stars.
foundry is primarily written in JavaScript. It covers topics such as agents, clawdbot, clawdbot-plugin.
You can find installation instructions and usage details in the foundry GitHub repository at github.com/unbrowse-ai/foundry. The project has 329 stars and 28 forks, indicating an active community.
The top alternatives to foundry on Agent Skills Hub include openclaw-foundry, milady, secure-openclaw. 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: