agentrigs
+ submit rig
~ / rigs / ozzaii / codex-claude-loop

ozzaii/codex-claude-loop

Gated Claude x Codex build loop for Claude Code: Codex plans and implements from one persistent thread, Claude approves the plan and reviews the diff. Zero deps, 20-test smoke suite.

↗ GitHub ★ 6 MIT updated 3mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~216 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/ozzaii/codex-claude-loop

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 ozzaii/codex-claude-loop/plugin/skills/codex-claude-loop .claude/skills/codex-claude-loop
$ npx degit ozzaii/codex-claude-loop/plugin/skills/doctor .claude/skills/doctor
$ npx degit ozzaii/codex-claude-loop/plugin/skills/prompt .claude/skills/prompt
$ npx degit ozzaii/codex-claude-loop/plugin/skills/status .claude/skills/status
$ npx degit ozzaii/codex-claude-loop/plugin/skills/wave .claude/skills/wave

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)

codex-claude-loopdoctorpromptstatuswave

Similar rigs

NotTahaAli/sessclone
Claude Code usage and cost for a whole team: laptops, cloud sessions and CI in one priced ledger. Open source, free to self-host.
★ 2 project Claude CodeCodex 2 skills 1 hooks 7d ago
Minimalist 2.0k tok ·
outbit/claude-code-tokenbudget
Claude code plugin to implement a budget or quota across all backends (Bedrock, Vertex, direct API) and provides guardrails against surprise token costs. No surprise bills, no config beyond a single env var, no external dependencies.
★ 2 project Claude Code 2 skills 5mo ago
Minimalist 51 tok ·
hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
★ 784 project Codex 3 skills 3d ago
Minimalist 397 tok ·
Abhi902/headroom-plugin
Claude Code plugin that keeps big outputs out of your context with the local, offline headroom engine: hcat compress-on-read, an automatic read gate, Dangi nudges, a savings badge in the status line, and a doctor that repairs setup with you
★ 11 collection Claude Code 1 mcp 2 skills 6d ago
Pragmatist 2.7k tok ·
copied ✓