~ / rigs / matthewwong525 / WongStack

matthewwong525/WongStack

Repo-native workflow for AI coding agents: your team's process, plans, and decisions live in the repo, so Claude Code and Codex run the same explore → plan → apply → ship loop.

↗ GitHub ★ 7 MIT updated 5d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.2k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

$ git clone --depth 1 https://github.com/matthewwong525/WongStack

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 matthewwong525/WongStack/.agents/plugins/access/skills/services .claude/skills/services
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/apply .claude/skills/apply
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/close .claude/skills/close
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/continue .claude/skills/continue
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/explore .claude/skills/explore
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/plan .claude/skills/plan
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/save .claude/skills/save
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/ship .claude/skills/ship
$ npx degit matthewwong525/WongStack/.agents/plugins/loop/skills/verify .claude/skills/verify
$ npx degit matthewwong525/WongStack/.agents/plugins/memory/skills/dream-memory .claude/skills/dream-memory
$ npx degit matthewwong525/WongStack/.agents/skills/agent-browser .claude/skills/agent-browser
$ npx degit matthewwong525/WongStack/.agents/skills/connect .claude/skills/connect
$ npx degit matthewwong525/WongStack/.agents/skills/improve-code .claude/skills/improve-code
$ npx degit matthewwong525/WongStack/.agents/skills/lesson .claude/skills/lesson
$ npx degit matthewwong525/WongStack/.agents/skills/paste-this-into-your-ai .claude/skills/paste-this-into-your-ai
$ npx degit matthewwong525/WongStack/.agents/skills/reply-link .claude/skills/reply-link
$ npx degit matthewwong525/WongStack/.agents/skills/update-dependencies .claude/skills/update-dependencies
$ npx degit matthewwong525/WongStack/.agents/skills/wong-setup .claude/skills/wong-setup
$ npx degit matthewwong525/WongStack/.agents/skills/wong-sync .claude/skills/wong-sync

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

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

Skills (19)

Similar rigs

copied ✓