agentrigs
+ submit rig
~ / rigs / dnlbox / ai-protocol

dnlbox/ai-protocol

Start with a concept, not a stack. A harness-agnostic protocol that scaffolds greenfield projects from a rigorous concept instead of a chain of prompts, so AI agents build from shared intent with self-healing and crash-safe state.

↗ GitHub ★ 19 MIT updated 2mo ago project Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/dnlbox/ai-protocol

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 dnlbox/ai-protocol/.agents/skills/concept-intake .claude/skills/concept-intake
$ npx degit dnlbox/ai-protocol/.agents/skills/consolidate-state .claude/skills/consolidate-state
$ npx degit dnlbox/ai-protocol/.agents/skills/plan-implementation .claude/skills/plan-implementation
$ npx degit dnlbox/ai-protocol/.agents/skills/shape-concept .claude/skills/shape-concept
$ npx degit dnlbox/ai-protocol/.agents/skills/sync-protocol .claude/skills/sync-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 (5)

concept-intakeconsolidate-stateplan-implementationshape-conceptsync-protocol

Similar rigs

npolgado/.nporc
personal dotfiles, aliases, claude global files
★ 1 project Claude Code 6 skills 3 agents 6mo ago
Pragmatist 646 tok ·
testdouble/han
Han: AI skills and agents for "Solo" product engineers and small teams
★ 261 collection Claude Code 47 skills 29d ago
Skill Collector 8.7k tok ·
Uniswap/ai-toolkit
🤖 AI Toolkit - Standardized setup for Claude Code AI workflows. Nx monorepo with reusable agents, commands, and generators for enhanced AI-assisted development.
★ 42 project Claude CodeCursor 13 mcp 43 skills 5 agents 2 hooks 1d ago
MCP Hoarder 79.9k tok ·
a5c-ai/babysitter
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
★ 1,833 project Claude CodeCodexCursor 4 mcp 138 skills 2 agents 23d ago
Skill Collector 14.3k tok ·
copied ✓