agentrigs
+ submit rig
~ / rigs / claude-code-best / claude-code

claude-code-best/claude-code

原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

↗ GitHub ★ 22.8k no license updated 2mo ago project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.8k 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 claude-code-best/claude-code/.claude ./rig-claude-code  # inspect, then merge into .claude/

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 claude-code-best/claude-code/.claude/skills/interview .claude/skills/interview
$ npx degit claude-code-best/claude-code/.claude/skills/teach-me .claude/skills/teach-me
$ curl -fsSL --create-dirs -o .claude/agents/hello-agent.md https://raw.githubusercontent.com/claude-code-best/claude-code/main/.claude/agents/hello-agent.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 (2)

interviewteach-me

Subagents (1)

hello-agentA friendly greeting agent that introduces the project

Similar rigs

iamvenuti/garrick
An AI chief of staff for knowledge work: remembers your work and knows whose confidences you hold. Runs on Claude Code or Codex, in files you own.
★ 1 project Codex 7 skills today
Pragmatist 1.9k tok ·
itw-creative-works/workkit
The issue-pipeline workflow system as a Claude Code plugin: GitHub Issues as the work-item SSOT, labels as the pipeline, guard hooks, a manager crew, and the skills from build to ship.
★ 2 project Codex 9 skills 7d ago
Pragmatist 3.9k tok ·
ThbltLmr/claude-config
User-level configuration for Claude Code
★ 1 setup Claude Code 9 skills 1 hooks 6d ago
YOLO Cowboy 488 tok ·
skullninja/coco-workflow
Autonomous spec-driven development plugin for Claude Code. Describe a feature, get merged, tested, reviewed code. Full pipeline from PRD to PR with dependency-aware task tracking, AI code review, and zero dependencies beyond bash + jq.
★ 7 project Claude Code 6 skills 4 agents 1mo ago
Pragmatist 8.5k tok ·
copied ✓