agentrigs
+ submit rig
~ / rigs / MiguelAxcar / ai-rpi-protocol

MiguelAxcar/ai-rpi-protocol

Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the wor

↗ GitHub ★ 28 mit updated 7mo ago project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.3k tokens
Moderate · 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 MiguelAxcar/ai-rpi-protocol/agents ./rig-ai-rpi-protocol/agents

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.

$ curl -fsSL --create-dirs -o .claude/agents/challenger.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/challenger.md
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/architecture-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/conventions-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/conventions-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/documentation-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/documentation-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/patterns-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/patterns-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-quality-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-review/test-quality-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/codebase-mapper.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/codebase-mapper.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/documentation-researcher.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/documentation-researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/packaging-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/packaging-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/performance-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/standards-discovery.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/standards-discovery.md
$ curl -fsSL --create-dirs -o .claude/agents/web-researcher.md https://raw.githubusercontent.com/MiguelAxcar/ai-rpi-protocol/main/agents/web-researcher.md

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 *)"
    ]
  }
}

Subagents (15)

challenger—
architecture-reviewer—
conventions-reviewer—
documentation-reviewer—
patterns-reviewer—
security-reviewer—
test-quality-reviewer—
code-reviewer—
codebase-mapper—
debugger—
documentation-researcher—
packaging-reviewer—
performance-reviewer—
standards-discovery—
web-researcher—

Similar rigs

IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
★ 5 setup Claude CodeCodex 2 agents 26d ago
Pragmatist 3.0k tok ·
triat/claude-projects-template
A structured Claude Code template with persistent task management, enforced TDD workflows, 9 specialized agents, and a design system — copy into any project to make Claude consistently excellent.
★ 0 project Claude Code 3 mcp 9 agents 2 hooks 8mo ago
Orchestrator 22.8k tok ·
braden-w/claude-config
My personal Claude Code configuration - coding preferences, conventions, and read-only permissions for safe codebase exploration
★ 4 setup Claude Code 4 agents 5mo ago
Minimalist 776 tok ·
flsteven87/claude-code-setup
Personal Claude Code configuration — settings, hooks, skills, commands, rules
★ 1 setup Claude Code 1 mcp 2 skills 2 agents 12 hooks 1d ago
YOLO Cowboy 6.3k tok ·
copied ✓