ysq
ysq'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.
Totals across every corpus @yangshiqi 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 ZackEyes corpus
yangshiqi/ZackEyes: Native macOS Dynamic Island for AI coding agents: watches Claude Code & Codex sessions, surfaces permission requests, shows usage limits…
- Look up how ZackEyes implements agent-tools, ai-coding-assistant, claude-code, with answers cited to file and line.
- Reuse a worked example: the commit “notify active Codex users of extra reset announcements (…” (14 files · Swift).
- Answer from ZackEyes's real Swift source instead of memory (AI, prompts and agents).
- How does ZackEyes implement agent-tools?
- What does Sources do in ZackEyes?
Search the GitHub repository yangshiqi/ZackEyes with XERJ (https://hub.xerj.org/corpus/yangshiqi--zackeyes). 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/yangshiqi/ZackEyes ZackEyes && git -C ZackEyes checkout 7a1eb3da013cf74116a26fb6603bdb68f5b95c6a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./ZackEyes --url http://127.0.0.1:9200 --prefix zackeyes --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 yangshiqi--zackeyes · AI, prompts and agents
Related corpora: mkcert, agent-manager, AllenReder/not-boring-notch, Mohamed-Elshesheny/sigstop
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
yangshiqi/ZackEyes
Native macOS Dynamic Island for AI coding agents: watches Claude Code & Codex sessions, surfaces permission requests, shows usage limits, jumps to the right terminal tab
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/yangshiqi)
Included with the author's permission (email, 2026-10-25), 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.