agentrigs
+ submit rig
~ / rigs / lora-sys / Init-codebase

lora-sys/Init-codebase

Init-codebase Claude skill — bootstraps any repo into a Claude-Code-ready workspace with rules, agents, and skills wired up.

↗ GitHub ★ 1 no license 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
~1.4k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/lora-sys/Init-codebase

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 lora-sys/Init-codebase/assets/loop-engineer-harness/dot-claude/skills/dev-local-setup .claude/skills/dev-local-setup
$ npx degit lora-sys/Init-codebase/assets/loop-engineer-harness/dot-claude/skills/e2e-setup .claude/skills/e2e-setup
$ npx degit lora-sys/Init-codebase/assets/loop-engineer-harness/dot-claude/skills/new-loop .claude/skills/new-loop
$ npx degit lora-sys/Init-codebase/assets/loop-engineer-harness/dot-claude/skills/pr .claude/skills/pr
$ npx degit lora-sys/Init-codebase/assets/loop-engineer-harness/dot-claude/skills/setup-codebase-harness .claude/skills/setup-codebase-harness

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 (5)

dev-local-setupe2e-setupnew-loopprsetup-codebase-harness

Similar rigs

AI-Builder-Club/skills
Codebase harness + loop engineer
★ 1,285 collection Claude Code 11 skills 24d ago
Skill Collector 340 tok ·
matchai/dotfiles
💻 Public repo for my personal dotfiles
★ 210 setup Codex 4 skills 1d ago
Minimalist 1.2k tok ·
ramarlina/agx
agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.
★ 28 project Claude Code 4 skills 5mo ago
Minimalist 167 tok ·
devoxx/DevoxxGenieIDEAPlugin
DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Devel
★ 683 collection Claude CodeCodexGemini CLI 6 skills 18d ago
Pragmatist 3.4k tok ·
copied ✓