agentrigs
+ submit rig
~ / rigs / michael-berardi / steak-pi

michael-berardi/steak-pi

Pi, cooked properly — native subagents with machine-wide capacity caps, deterministic $0 compaction, automatic verification, and a native TUI for the Pi coding agent.

↗ GitHub ★ 1 MIT updated today project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~155 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit michael-berardi/steak-pi/skills ./rig-steak-pi/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit michael-berardi/steak-pi/skills/memory .claude/skills/memory
$ npx degit michael-berardi/steak-pi/skills/todo .claude/skills/todo
$ npx degit michael-berardi/steak-pi/skills/ultraterm-subagent-protocol .claude/skills/ultraterm-subagent-protocol

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (3)

memorytodoultraterm-subagent-protocol

Similar rigs

kitfunso/hippo-memory
Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps
★ 772 project Claude CodeCodex 1 skills 4d ago
Minimalist 1.2k tok ·
brobertsaz/claude-os
—
★ 430 project Claude Code 3 skills 8mo ago
Minimalist 2.1k tok ·
plasma-ai/fractal
Hierarchical agent loops with recursive self-organization.
★ 781 project Claude CodeCodex 4 skills 4d ago
Pragmatist 7.3k tok ·
julianprincipe/windows-pc-optimizer
Windows PC optimization plugin for Claude Code — adaptive diagnostic + fix for gaming, audio production, dev and office setups
★ 31 project Claude Code 5 skills 7mo ago
Pragmatist 49 tok ·
copied ✓