agentrigs
+ submit rig
~ / rigs / ykdojo / safeclaw

ykdojo/safeclaw

The easiest way to run multiple Claude Code sessions, each in its own container, with a dashboard to manage them all. Quick setup with battle-tested sensible defaults and skills.

↗ GitHub ★ 184 MIT updated 12d ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.2k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/ykdojo/safeclaw

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 ykdojo/safeclaw/setup/skills/gdoc .claude/skills/gdoc
$ npx degit ykdojo/safeclaw/setup/skills/slack .claude/skills/slack
$ npx degit ykdojo/safeclaw/setup/skills/yt-dlp .claude/skills/yt-dlp

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)

gdocslackyt-dlp

Similar rigs

azmym/agent-skills
Plug-and-play skills that supercharge Claude Code, Cursor, Codex & other AI agents. Talk to Slack, audit your setup, and more.
★ 2 collection Claude Code 3 skills 4mo ago
Minimalist 253 tok ·
earlyaidopters/claudeclaw
Claude Code CLI as a personal Telegram bot — voice, memory, scheduled tasks, all your skills from your pocket.
★ 173 project Claude Code 6 skills 6mo ago
Pragmatist 4.2k tok ·
rohaquinlop/claude-config
Sanitized Claude Code config: skills, agents, hooks, settings
★ 0 setup Claude Code 8 skills 1mo ago
Pragmatist 2.0k tok ·
RealTapeL/SkillPilot
Universal Agent Skill Router — Route agent skills before LLM inference. Zero-config skill fingerprinting, conflict-aware routing, and self-learning feedback loop. Supports OpenClaw, Claude Code, LangChain, and more.
★ 4 project Claude Code 10 skills 6mo ago
Skill Collector 220 tok ·
copied ✓