agentrigs
+ submit rig
~ / rigs / qingye-lab / rootloom

qingye-lab/rootloom

Inspectable engineering workflows for OpenAI Codex.

↗ GitHub ★ 10 MIT updated 1mo ago project Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.2k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/qingye-lab/rootloom

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 qingye-lab/rootloom/experiments/rootloom-memory/skills/project-memory .claude/skills/project-memory
$ npx degit qingye-lab/rootloom/plugins/rootloom/skills/operating-code-review .claude/skills/operating-code-review
$ npx degit qingye-lab/rootloom/plugins/rootloom/skills/operating-coding-change .claude/skills/operating-coding-change
$ npx degit qingye-lab/rootloom/plugins/rootloom/skills/project-guidance .claude/skills/project-guidance
$ npx degit qingye-lab/rootloom/plugins/rootloom/skills/setup-rootloom .claude/skills/setup-rootloom

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)

project-memoryoperating-code-reviewoperating-coding-changeproject-guidancesetup-rootloom

Similar rigs

tdiprima/claude-config
Claude Code dotfiles and bootstrap script to configure a new machine with rules, skills, and settings in one command.
★ 0 setup Claude Code 7 skills 13d ago
Pragmatist 686 tok ·
GhostwheeI/Master-Planner
A production-grade, evidence-driven Cursor AI planning harness that converts vague intent into source-grounded software plans. Features adaptive routing, adversarial plan grilling, and structural anti-rationalization.
★ 0 project Cursor 8 skills 3mo ago
Pragmatist 3.1k tok ·
maystudios/maxsimcli
Solve context rot in AI coding. Spec-driven development system for Claude Code, OpenCode, Gemini CLI, and Codex — with parallel subagents, atomic commits, and a live dashboard.
★ 11 project Codex 16 skills 6mo ago
Skill Collector 3.1k tok ·
PoLP0ot/claude-harness
Reusable .claude/ harness: skills, rules, agents, hooks, settings for Claude Code under Hermes orchestration
★ 0 setup Claude Code 17 skills 7 agents 13d ago
Orchestrator 1.7k tok ·
copied ✓