agentrigs
+ submit rig
~ / rigs / chekusu / wanman

chekusu/wanman

wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.

↗ GitHub ★ 633 apache-2.0 updated 4mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~192 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/chekusu/wanman

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 chekusu/wanman/packages/core/skills/artifact-naming .claude/skills/artifact-naming
$ npx degit chekusu/wanman/packages/core/skills/artifact-quality .claude/skills/artifact-quality
$ npx degit chekusu/wanman/packages/core/skills/cross-validation .claude/skills/cross-validation
$ npx degit chekusu/wanman/packages/core/skills/research-methodology .claude/skills/research-methodology
$ npx degit chekusu/wanman/packages/core/skills/wanman-cli .claude/skills/wanman-cli
$ npx degit chekusu/wanman/packages/core/skills/workspace-conventions .claude/skills/workspace-conventions

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 (6)

artifact-namingartifact-qualitycross-validationresearch-methodologywanman-cliworkspace-conventions

Similar rigs

vstorm-co/pydantic-deepagents
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
★ 1,076 collection Claude CodeCodex 16 skills 24d ago
Skill Collector 5.0k tok ·
cinicu/opencode-dotfiles
OpenCode dotfiles — 19 AI agent skills + 8 MCP servers + persistent memory (memory-keeper). Cross-platform install, screenshot OCR, custom CLI toolchain. Research methodology, systematic reviews, critical analysis, skill-creator.
★ 10 setup Claude CodeCodex 19 skills 2 agents 4mo ago
Skill Collector 1.1k tok ·
aneja5/forge-skills
An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.
★ 3 collection Claude CodeCodex 42 skills 13 agents 5mo ago
Orchestrator 7.7k tok ·
KhaledSaeed18/dotclaude
Reusable Claude Code extension registry. skills, subagents, slash commands, and hooks for engineering, git, testing, and security workflows. Distributed as a shadcn GitHub registry and as installable plugins.
★ 5 setup Claude Code 82 skills 17 agents today
Orchestrator 9.5k tok ·
copied ✓