agentrigs
+ submit rig
~ / rigs / bi-boo / claude-code-config

bi-boo/claude-code-config

我的 Claude Code 个人配置——CLAUDE.md 规则、Agent、记忆机制，以及 Ghostty 终端配置

↗ GitHub ★ 19 no license updated 5mo ago personal setup Claude Code
share on X
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
CONTEXT TAX · EVERY TURN
~1.4k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit bi-boo/claude-code-config/agents ./rig-claude-code-config/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/analyst.md https://raw.githubusercontent.com/bi-boo/claude-code-config/main/agents/analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/bi-boo/claude-code-config/main/agents/explorer.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(rm -rf /)",
      "Bash(rm -rf ~)",
      "Bash(rm -rf *)",
      "Read(.env)",
      "Read(.env.*)",
      "Read(~/.ssh/**)",
      "Read(**/*.pem)",
      "Read(**/*.key)",
      "Read(**/id_rsa*)",
      "Read(**/*.p12)"
    ],
    "ask": [
      "Bash(git push *)",
      "Bash(npm publish *)",
      "Bash(sudo *)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Agent",
        "hooks": [
          {
            "type": "command",
            "command": "~/.claude/scripts/agent-start.sh"
          }
        ]
      }
    ]
  }
}

Subagents (2)

analyst
model: opus
Use this agent for deep analysis, complex reasoning, architecture decisions, code review, and problem-solving that requires careful thought. Best for tasks like "analyze this system", "what's the best
explorer
model: haiku
Use this agent for quickly reading files, searching codebases, listing directories, and exploring project structure. Best for tasks like "find this file", "search for this function", "read this file",

Hooks (2)

eventmatcherruns
PreToolUseAgent~/.claude/scripts/agent-start.sh
PostToolUseAgent~/.claude/scripts/agent-stop.sh

Plugins (9)

ai-skills@claude-starter-completedocument-skills@anthropic-agent-skillsfigma@claude-plugins-officialplaywright-skill@playwright-skillrevealjs@revealjs-skillrust-analyzer-lsp@claude-plugins-officialsuperpowers@superpowers-devswift-lsp@claude-plugins-officialtoon-formatter@claude-starter-complete

Permissions

deny (10)
Bash(rm -rf /)
Bash(rm -rf ~)
Bash(rm -rf *)
Read(.env)
Read(.env.*)
Read(~/.ssh/**)
Read(**/*.pem)
Read(**/*.key)
Read(**/id_rsa*)
Read(**/*.p12)
ask (3)
Bash(git push *)
Bash(npm publish *)
Bash(sudo *)
allow (8)
Read
Glob
Grep
Edit
Write
WebFetch
WebSearch
Bash(*)

Similar rigs

jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
★ 12 project Claude CodeCodex 3 agents today
Minimalist 341 tok ·
RonaldPrecieux/claude-code-playbook
Le guide opérationnel pour transformer Claude Code en workflow de développement autonome — CLAUDE.md template, sous-agents, workflow autonome
★ 0 project Claude Code 3 agents 7mo ago
Minimalist 771 tok ·
tungdc88/claude-code-template
Professional Claude Code template system for solo developers — hooks, agents, commands, skills, plan workflow
★ 0 project Claude Code 1 mcp 2 skills 2 agents 1 hooks 5mo ago
Pragmatist 4.2k tok ·
RandallLiuXin/GodotMaker
Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
★ 550 project Claude Code 7 agents 22d ago
Orchestrator 1.5k tok ·
copied ✓