~ / rigs / yohey-w / multi-agent-shogun

yohey-w/multi-agent-shogun

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

↗ GitHub ★ 1,420 mit updated 2mo ago project Claude CodeCodexCursorCopilot
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~4.3k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Blocks destructive commands · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit yohey-w/multi-agent-shogun/.claude ./rig-multi-agent-shogun  # 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 yohey-w/multi-agent-shogun/.cursor/skills/inbox-write .claude/skills/inbox-write
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-agent-status .claude/skills/shogun-agent-status
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-bloom-config .claude/skills/shogun-bloom-config
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-model-list .claude/skills/shogun-model-list
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-model-switch .claude/skills/shogun-model-switch
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-readme-sync .claude/skills/shogun-readme-sync
$ npx degit yohey-w/multi-agent-shogun/skills/shogun-screenshot .claude/skills/shogun-screenshot
$ npx degit yohey-w/multi-agent-shogun/skills/skill-creator .claude/skills/skill-creator
$ curl -fsSL --create-dirs -o .claude/agents/system.md https://raw.githubusercontent.com/yohey-w/multi-agent-shogun/main/agents/default/system.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 /mnt/*)",
      "Bash(rm -rf /mnt/c/*)",
      "Bash(rm -rf ~",
      "Bash(rm -rf ~*)",
      "Bash(sudo *)",
      "Bash(su *)",
      "Bash(kill *)",
      "Bash(killall *)",
      "Bash(pkill *)",
      "Bash(git push --force*)",
      "Bash(git push -f *)",
      "Bash(git reset --hard*)",
      "Bash(tmux kill-server*)",
      "Bash(tmux kill-session*)",
      "Bash(mkfs*)",
      "Bash(dd if=*)",
      "Bash(chmod -R * /)",
      "Bash(chown -R * /)"
    ]
  }
}

Skills (8)

Subagents (1)

systemKimi K2 CLI + tmux multi-agent parallel dev platform with sengoku military hierarchy

Hooks (2)

eventmatcherruns
SessionStart*bash scripts/session_start_hook.sh
Stop*bash scripts/stop_hook_inbox.sh

Permissions

deny (20)
Bash(rm -rf /)
Bash(rm -rf /*)
Bash(rm -rf /mnt/*)
Bash(rm -rf /mnt/c/*)
Bash(rm -rf ~
Bash(rm -rf ~*)
Bash(sudo *)
Bash(su *)
Bash(kill *)
Bash(killall *)
Bash(pkill *)
Bash(git push --force*)
Bash(git push -f *)
Bash(git reset --hard*)
Bash(tmux kill-server*)
Bash(tmux kill-session*)
Bash(mkfs*)
Bash(dd if=*)
Bash(chmod -R * /)
Bash(chown -R * /)
ask (0)
—
allow (0)
—

Similar rigs

copied ✓