Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
Back to list

LazyCodex Bug-Fix Contribution Skill

Debugs a LazyCodex or upstream Codex CLI defect in a throwaway workspace and ships it as a fork PR or a patch-embedded verified-fix issue.

Dev & CodingAdvanced67,5315,507AI score 8/10Last updated: Aug 9, 2026

What it does

  • Reads the bug report and routes ownership: LazyCodex / lazycodex-ai / omo-codex / bundled skills → code-yeongyu/lazycodex; core Codex CLI defects → openai/codex.
  • Syncs both source checkouts under $TMPDIR, validates cached clones, and quarantines corrupt ones so the fix cannot land in the wrong repo.
  • Enforces a strict pipeline: reproduce and save logs → write a failing regression test (RED) → smallest correct fix → passing test (GREEN) → real-surface QA command.
  • Delivers differently per target: a fork PR for openai/codex, and a never-a-PR verified-fix issue with the unified diff embedded for code-yeongyu/lazycodex (that repo is a generated mirror).
  • Adds the lazycodex-generated label plus footer tag, then removes temporary worktrees and clones.

Who it's for

  • LazyCodex / omo-codex users who want to contribute real fixes instead of just filing reports.
  • Developers unfamiliar with the upstream Codex CLI fork-and-PR workflow.
  • Teams that want to ban vague fixes with no repro log and no regression test.

Example uses

  1. "The lazycodex installer fails under zsh — find the cause and submit the fix" → repro logs from a temp clone, root cause with source evidence, issue containing the tested patch.
  2. "Codex CLI ignores the --model flag; open an upstream PR" → fork openai/codex, add a failing test, apply the minimal fix, build the PR body via scripts/create-pr-body.mjs, open the PR.
  3. "I can't tell whether this is a LazyCodex or Codex bug" → both checkouts are synced and compared, and if ownership is still ambiguous the skill stops and asks one narrow question.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/lcx-contribute-bug-fix/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone --depth=1 https://github.com/code-yeongyu/oh-my-openagent /tmp/omo && mkdir -p ~/.claude/skills && cp -r /tmp/omo/packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix ~/.claude/skills/

This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: install git, node, and the GitHub CLI (gh), then run gh auth login with fork and issue-creation permissions.
  2. Clone the repo: git clone --depth=1 https://github.com/code-yeongyu/oh-my-openagent /tmp/omo.
  3. Copy the skill folder: mkdir -p ~/.claude/skills && cp -r /tmp/omo/packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix ~/.claude/skills/.
  4. Verify the bundled script: ls ~/.claude/skills/lcx-contribute-bug-fix/scripts/create-pr-body.mjs.
  5. Restart Claude Code and try a prompt like "debug this bug and open a PR" to confirm the skill triggers.
  6. First-run tip: all work happens in /tmp workspaces — run git status in your current project afterwards to confirm nothing local was modified.
View source on GitHubLicense: NOASSERTION