ultimate-pi

Custom pi package starter

Package details

extensionskill

Install ultimate-pi from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:ultimate-pi
Package
ultimate-pi
Version
0.1.2
Published
Apr 25, 2026
Downloads
253/mo · 253/wk
Author
aryaniyaps
License
MIT
Types
extension, skill
Size
2.2 MB
Dependencies
0 dependencies · 0 peers
Pi manifest JSON
{
  "extensions": [
    "./extensions"
  ],
  "skills": [
    "./.agents/skills"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

Ultimate PI banner

(Beta) The ultimate AI coding harness on top of pi.dev.

Goal

Ship a production-grade coding harness where the agent:

  1. uses compressed context before raw tool spam,
  2. stays concise and deterministic in output style,
  3. remains easy to extend with skills and extensions.

Included skills (upstream repositories)

Skill Upstream repo What it does
caveman juliusbrussee/caveman Ultra-compressed response style for token-efficient, high-signal communication.
compress juliusbrussee/caveman Compresses memory/context files into caveman format while preserving technical content.
lean-ctx yvgude/lean-ctx Context runtime and compression toolkit for reads/search/shell/edit flows.
context7-cli upstash/context7 Pulls current library docs and manages Context7 skills/config from CLI.
emil-design-eng emilkowalski/skill UI/design craftsmanship guidance: interaction polish, motion, and component quality.
scrapling-official D4Vinci/Scrapling Official Scrapling skill for web extraction/scraping with adaptive parsing, JS rendering, stealth fetchers, and anti-bot handling.

Runtime guardrail extension

  • extensions/lean-ctx-enforce.ts
    • Detects lean-ctx availability.
    • Blocks built-ins (read, write, edit, grep, find, ls, raw bash) when lean-ctx exists.
    • Allows shell only via lean-ctx -c <command>.
    • Adds status commands:
      • /lean-ctx-status
      • /system-prompt-status

Design choices (concise)

  1. Lean-ctx-first execution
    Reason: cut context/token waste and keep tool usage structured.

  2. Caveman-by-default response style
    Reason: short, exact, low-noise outputs for coding loops.

  3. Policy in system prompt + enforcement in extension
    Reason: prompt sets intent; extension guarantees behavior.

  4. Skill-based composition
    Reason: easy to swap/upgrade capabilities without rewiring core package.

  5. Model-agnostic compression path
    Reason: compress skill calls PI CLI, so provider/model can change per environment.

Use locally

From repo root:

pi install . -l

Then restart PI or run /reload.