agentrigs
+ submit rig
~ / rigs / FanaticsKang / claude_config

FanaticsKang/claude_config

my claude code config

↗ GitHub ★ 1 no license updated 5mo ago personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~621 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 FanaticsKang/claude_config/agents ./rig-claude_config/agents
$ npx degit FanaticsKang/claude_config/commands ./rig-claude_config/commands
$ npx degit FanaticsKang/claude_config/skills ./rig-claude_config/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 FanaticsKang/claude_config/skills/ask-me .claude/skills/ask-me
$ npx degit FanaticsKang/claude_config/skills/json_analysis .claude/skills/json_analysis
$ npx degit FanaticsKang/claude_config/skills/update-claude-md .claude/skills/update-claude-md
$ curl -fsSL --create-dirs -o .claude/agents/algorithm.md https://raw.githubusercontent.com/FanaticsKang/claude_config/master/agents/algorithm.md
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/FanaticsKang/claude_config/master/agents/architect.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 *)"
    ]
  }
}

Skills (3)

ask-mejson_analysisupdate-claude-md

Subagents (2)

autoDrive-algorithm-specialist
model: opus
specialized AI agent focused on the research, development, and application of autonomous driving algorithms. Core expertise covers algorithm design, simulation, optimization, and deployment support fo
autoDrive-architect-specialist
model: opus
作为自动驾驶领域的架构设计师，负责系统级的技术整合与数据流治理。主要使命是确保感知、决策、控制等模块之间的数据接口无缝衔接，同时深度介入模块内部实现逻辑的一致性验证，最终输出高可靠性、高可扩展性的系统架构方案。

Slash commands (2)

/simplify_your_code/summary_and_commit

Similar rigs

vichannnnn/ccstart
Quick setup for projects or repositories using Claude Code with built-in agents, ticket system, and planning tools.
★ 56 project Claude Code 7 skills 9mo ago
Pragmatist 3.0k tok ·
TechHU-GS/cc-discipline
Guardrails for Claude Code. Shell hooks that actually block bad behavior — edit loops, skipped verification, destructive git — not just markdown that asks nicely.
★ 0 project Claude Code 8 skills 4 agents 16 hooks 12d ago
Automator 7.6k tok ·
mikoflip/dotclaude
Dotfiles-style configuration manager for Claude Code. Version-controlled hooks, skills, plugins, and settings symlinked into ~/.claude.
★ 0 setup Claude Code 13 skills 1mo ago
Skill Collector 1.4k tok ·
billbuchanan-code/claude-code-power-setup
Production-grade Claude Code configuration: 23 agents, 27 skills, 12 safety hooks, MCP integrations. A complete guide to building an enterprise-level Claude Code setup.
★ 2 setup Claude Code 3 mcp 29 skills 23 agents 2mo ago
Orchestrator 11.2k tok ·
copied ✓