agentrigs
+ submit rig
~ / rigs / benyoskovitz / claude-code-workflow

benyoskovitz/claude-code-workflow

A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup

↗ GitHub ★ 8 MIT updated 15d ago personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~127 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit benyoskovitz/claude-code-workflow/commands ./rig-claude-code-workflow/commands
$ npx degit benyoskovitz/claude-code-workflow/skills ./rig-claude-code-workflow/skills
$ npx degit benyoskovitz/claude-code-workflow/hooks ./rig-claude-code-workflow/hooks

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 benyoskovitz/claude-code-workflow/skills/assess .claude/skills/assess
$ npx degit benyoskovitz/claude-code-workflow/skills/code-watch .claude/skills/code-watch
$ npx degit benyoskovitz/claude-code-workflow/skills/humanizer .claude/skills/humanizer
$ npx degit benyoskovitz/claude-code-workflow/skills/pre-commit .claude/skills/pre-commit
$ npx degit benyoskovitz/claude-code-workflow/skills/systematic-debugging .claude/skills/systematic-debugging

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 (5)

assesscode-watchhumanizerpre-commitsystematic-debugging

Slash commands (6)

/audit-instructions/blast-radius/project-health/session-audit/session-end/worktree-janitor

Similar rigs

Aboudjem/humanizer-skill
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
★ 264 collection Codex 1 skills 1mo ago
Minimalist 1.7k tok ·
GrassHeadd/dotfiles
Personal dotfiles: fish, ghostty, nvim, tmux, aerospace, Claude Code + Codex configs
★ 0 setup Claude CodeCodex 2 mcp 1 skills 3mo ago
Pragmatist 5.0k tok ·
robonuggets/agentic-ai-starter-kit
Beginner-friendly setup for Claude Code and other agentic AI tools. Personalised CLAUDE.md, safety rails, 2 starter skills.
★ 17 project Claude Code 2 skills 5mo ago
Minimalist 96 tok ·
Land-o-Clusters/sleight
Let Claude Code drive Mac apps in the background through the computer-use engine bundled with the ChatGPT desktop app.
★ 2 project Claude Code 2 skills today
Minimalist 405 tok ·
copied ✓