Yuwangzhi

Corpus Hub contributor since 2026-10-26

Yuwangzhi's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

8files

877lines

★ 2GitHub stars on repo

Totals across every corpus @Yuwangzhi appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the claude-codex-loop corpus

Yuwangzhi/claude-codex-loop: Claude plans, Codex executes: a two-mode local workflow with verification, repair loops, and shared project memory

Look up how claude-codex-loop implements ai-agents, automation, claude-code, with answers cited to file and line.
Reuse a worked example: the commit “Fix desktop hooks and reuse the last execution mode” (8 files · Python, JavaScript).
Answer from claude-codex-loop's real Python source instead of memory (AI, prompts and agents).

Example questions

Where does claude-codex-loop handle “Fix desktop hooks and reuse the last execution mode”?
How does claude-codex-loop implement ai-agents?
What does tests do in claude-codex-loop?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository Yuwangzhi/claude-codex-loop with XERJ (https://hub.xerj.org/corpus/yuwangzhi--claude-codex-loop).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Yuwangzhi/claude-codex-loop claude-codex-loop && git -C claude-codex-loop checkout 64391eece51fe639f6502d9c4a10a8cbd3aec613
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./claude-codex-loop --url http://127.0.0.1:9200 --prefix claude-codex-loop --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus yuwangzhi--claude-codex-loop · AI, prompts and agents
Related corpora: caldera, gatling, arthurcuri/mcp-instructure-canvas, CruxExperts/LocalSetup
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 2

Yuwangzhi/claude-codex-loop

64391eece5 Fix desktop hooks and reuse the last execution mode

selected commit: 8 files · 877 lines · Python, JavaScript · tests, the project root, desktop-plugin

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

live on the hub · licence clearedcorpus yuwangzhi--claude-codex-loopAIMITai-agentsautomationclaude-codecodexpython agreed 2026-10-26

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/Yuwangzhi/badge.svg)](https://hub.xerj.org/contributors/Yuwangzhi)

Included with the author's permission (email, 2026-10-26), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.