agentrigs
+ submit rig
~ / rigs / wondping0 / wondev

wondping0/wondev

Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.

↗ GitHub ★ 0 MIT updated 8d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~229 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/wondping0/wondev

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 wondping0/wondev/templates/skills/code-review .claude/skills/code-review
$ npx degit wondping0/wondev/templates/skills/debugging .claude/skills/debugging
$ npx degit wondping0/wondev/templates/skills/git-workflow .claude/skills/git-workflow
$ npx degit wondping0/wondev/templates/skills/planning-work .claude/skills/planning-work
$ npx degit wondping0/wondev/templates/skills/verify-before-done .claude/skills/verify-before-done
$ npx degit wondping0/wondev/templates/skills/writing-tests .claude/skills/writing-tests

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "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(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (6)

code-reviewdebugginggit-workflowplanning-workverify-before-donewriting-tests

Similar rigs

bchox/agent-practices
Portable, practical repository guidance for AI-assisted software development.
★ 2 project Codex 10 skills 22d ago
Skill Collector 978 tok ·
timwuhaotian/the-pair
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.
★ 363 project Claude CodeCodex 1 skills 9d ago
Pragmatist 5.5k tok ·
sortie-ai/sortie
Turn tracker tickets into autonomous agent sessions
★ 197 project CodexCopilot 1 skills today
Minimalist 1.3k tok ·
rios0rios0/dotfiles
Personal dotfiles managed with chezmoi and 1Password. Cross-platform configs for Kali Linux WSL, Windows 11, and Termux with Zsh, PowerShell, and Windows Terminal.
★ 5 setup Claude CodeCopilot 1 skills 9d ago
Pragmatist 18.4k tok ·
copied ✓