agentrigs
+ submit rig
~ / rigs / xrgarcia / slashbin-ai-team

xrgarcia/slashbin-ai-team

Run a team of AI coworkers in Discord. Powered by Claude Code — safe enough to leave running.

↗ GitHub ★ 13 MIT updated today project Claude Code Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~303 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/xrgarcia/slashbin-ai-team

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 xrgarcia/slashbin-ai-team/skill-pack/skills/bot-state .claude/skills/bot-state
$ npx degit xrgarcia/slashbin-ai-team/skill-pack/skills/land .claude/skills/land
$ npx degit xrgarcia/slashbin-ai-team/skill-pack/skills/remember .claude/skills/remember
$ npx degit xrgarcia/slashbin-ai-team/skill-pack/skills/schedule .claude/skills/schedule

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 (4)

bot-statelandrememberschedule

Similar rigs

Digital-Process-Tools/claude-remember
Persistent memory for Claude Code — identity, context, and continuity across sessions
★ 196 project Claude CodeGemini CLI 1 skills today
Minimalist 545 tok ·
sacredvalentin/who-made-the-call
A decision ledger for work done with AI agents. It records every fork and who decided it, and it must not write a reason the person did not give.
★ 0 project Claude Code 3 skills today
Minimalist 130 tok ·
hatawong/claude-recap
Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.
★ 33 project Claude Code 4 skills 7mo ago
Minimalist 217 tok ·
HLIntel/thea-software
Thea Software — the engineering layer for AI, by Heartland Intel. Any chat, agent or model asks Thea which command proves a change; the build refuses what drifted.
★ 1 project Claude CodeCodexCopilot 4 skills 3d ago
Minimalist 1.2k tok ·
copied ✓