agentrigs
+ submit rig
~ / rigs / yuyuan1019 / ai-console

yuyuan1019/ai-console

AI Console — 集中式 Web 控制台 + 出站 Agent，统一管理多台 Linux/macOS 开发机上 AI 编码 CLI（Codex CLI、Claude Code、Gemini CLI、OpenCode、Pi、Hermes）的配置、凭据与模型下发，无需 SSH。Centralized web console + outbound agent for managing AI coding CLI configs, credentials, and model

↗ GitHub ★ 0 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
~5.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/yuyuan1019/ai-console

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 yuyuan1019/ai-console/.agents/skills/dev-workflow .claude/skills/dev-workflow

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 (1)

dev-workflow

Similar rigs

gurenjs/framework-comparison
The same fullstack blog app implemented in Guren, Hono, and Next.js — measuring code, config, and AI-agent context, not throughput
★ 0 project Claude CodeCodex 1 mcp 11 skills 4 agents 3 hooks 8d ago
Skill Collector 7.8k tok ·
xstongxue/best-skills
通用高质量 Skills 合集🔥
★ 2,835 collection Claude Code 16 skills 26d ago
Skill Collector 828 tok ·
usrrname/cursorrules
A wicked npx-able lib of Cursor rules with Otaku AI agents, optional lean workflow 🎀
★ 11 project Claude CodeCodexCursor 2 mcp 16 skills 2 hooks 6mo ago
Fort Knox 13.7k tok ·
xhqing/CapabilityManagerAgent
Prometheus — the common-capability backbone for the Claude Code agent fleet: global skills, rules, settings, and cross-project sync. | Prometheus —— Claude Code 智能体舰队的通用能力底座：全局 skills、rules、settings 及跨项目同步
★ 0 project Claude Code 17 skills today
Skill Collector 7.6k tok ·
copied ✓