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 rawwerks · Codex Skill · ★ 381
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ypi safe to install? View the security audit →
ypi ypi — a recursive coding agent built on Pi. Named after the Y combinator from lambda calculus — the fixed-point combinator that enables recursion. is Pi that can call itself. ( already has another connotation.) Inspired by Recursive Language Models (RLM), which showed that an LLM with a code REPL and a function can recursively decompose problems, analyze massive contexts, and write code — all through self-delegation. The Idea Pi already has a bash REPL. We add one function — — and a system prompt that teaches Pi to use it recursively. Each child gets its own jj workspace for file isolation. That's the whole trick. ┌──────────────────────────────────────────┐ │ ypi (depth 0) │ │ Tools: bash, rlmquery │ │ Workspace: default │ │ │ │ grep -n "bug" src/.py │ │ sed -n '50,80p' src/app.py \ │ │ | rlmquery "Fix this bug" │ │ │ │ │ ▼ │ │ ┌────────────────────────────┐ │ │ │ ypi (depth 1) │ │
| Stars | 381 |
| Forks | 35 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.2472713586315/100 |
| Open Issues | 9 |
| Last Updated | 2026-06-22 |
| Created | 2026-02-09 |
| Platforms | cli |
| Est. Tokens | ~13k |
These tools work well together with ypi for enhanced workflows:
Looking for a ypi alternative? If you're comparing ypi 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.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succee
A programmable tool and agent runtime for Pi
The control plane for AI coding agents.
A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, mul
The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your A
将 AI 命令行工具以最为原生的方式，集成到微信 ClawBot / 企业微信 bot 中，目前支持集成 Codex、Claude Code、OpenCode、Pi Agent。 支持微信和本地终端线程（thread/s
Explore other popular codex skill tools:
ypi is A recursive coding agent inpired by RLMs. It is categorized as a Codex Skill with 381 GitHub stars.
ypi is primarily written in Shell. It covers topics such as agents, cli, openclaw.
You can find installation instructions and usage details in the ypi GitHub repository at github.com/rawwerks/ypi. The project has 381 stars and 35 forks, indicating an active community.
ypi is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ypi on Agent Skills Hub include autocontext, pi-fabric, ai-devkit. 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: