agentrigs
+ submit rig
~ / rigs / 7bata / claude-workflow-kit

7bata/claude-workflow-kit

Doc-driven multi-agent dev workflow for Claude Code (Conductor/Executor/Reviewer) · 文档驱动的多代理开发工作流

↗ GitHub ★ 2 MIT updated 2d ago personal setup Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~423 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/7bata/claude-workflow-kit

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 7bata/claude-workflow-kit/plugins/send-to-en/skills/send-to .claude/skills/send-to
$ npx degit 7bata/claude-workflow-kit/plugins/speak-human-en/skills/speak-human .claude/skills/speak-human
$ npx degit 7bata/claude-workflow-kit/plugins/ui-sweep-en/skills/ui-sweep .claude/skills/ui-sweep
$ npx degit 7bata/claude-workflow-kit/plugins/workflow-codex/skills/parallel-do .claude/skills/parallel-do
$ npx degit 7bata/claude-workflow-kit/plugins/workflow-codex/skills/scaffold .claude/skills/scaffold
$ npx degit 7bata/claude-workflow-kit/plugins/workflow-codex/skills/sop-generate .claude/skills/sop-generate
$ npx degit 7bata/claude-workflow-kit/plugins/workflow-codex/skills/whats-next .claude/skills/whats-next

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 (7)

send-tospeak-humanui-sweepparallel-doscaffoldsop-generatewhats-next

Similar rigs

jaharris87/agentic-dev-framework
Multi-agent adversarial dev workflow templates: Claude Code (builder) + Codex (reviewers) + GitHub Actions (orchestrator)
★ 0 project Claude CodeCodex 3 skills 7mo ago
Pragmatist 5.0k tok ·
peterkimpro/claude-code-powerpack
Drop-in Claude Code config for efficient AI-assisted development. Includes CLAUDE.md template, permission allowlist, agents, skills, and memory system.
★ 1 project Claude Code 3 skills 2 agents 3 hooks 7mo ago
Pragmatist 4.4k tok ·
OdinMB/ops-workflow
Structured non-code project and knowledge management for Claude Code. (Before Karpathy made this fashionable...)
★ 7 project Claude Code 9 skills 3mo ago
Pragmatist 405 tok ·
BytesFromToby/plumbline
A "trust, but verify" workflow of AI-agent skills: prompt to verified code, every step trackable and deviations logged — plus an autonomous maintenance loop to keep a built project honest.
★ 3 project Claude Code 9 skills 2mo ago
Pragmatist 1.7k tok ·
copied ✓