~ / rigs / NZRTnetwork / 000CLA

NZRTnetwork/000CLA

Pattern for running multiple scoped AI agents in Claude Code — role codes, tier system, access boundaries, CLAUDE.md config

↗ GitHub ★ 0 no license updated 2d ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~730 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit NZRTnetwork/000CLA/claude-code-multi-agent-setup/.claude ./rig-000cla  # 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.

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

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "*",
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/pre-tool-use.sh"
          }
        ]
      }
    ]
  }
}

Hooks (1)

eventmatcherruns
PreToolUse*bash .claude/hooks/pre-tool-use.sh

Permissions

deny (0)
—
ask (0)
—
allow (3)
Bash(git status)
Bash(git log*)
Bash(git diff*)

Similar rigs

copied ✓