agent-flow
Explicitly invoked Codex skill for verified Agent Flow workflows
A new way for AI to search for data
21GitHub stars
What XERJ indexed
Selected work
“Publish only Codex plugin archives in numbered releases”. 5 files, 355 lines in scripts.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-13. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
Example questions
- Where does agent-flow handle “Publish only Codex plugin archives in numbered releases”?
The prompt
Paste it into your AI agent. It clones svishniakov/agent-flow at the pinned commit and indexes it on your machine.
Search the GitHub repository svishniakov/agent-flow with XERJ (https://hub.xerj.org/corpus/svishniakov--agent-flow). 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/svishniakov/agent-flow agent-flow && git -C agent-flow checkout 7441cc98ea5a26d5c870e92870cbe6f8e9581dae 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./agent-flow --url http://127.0.0.1:9200 --prefix agent-flow --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.
Related
Sergey VishniakovAI, prompts and agents corpora
Selected work and consent: the XERJ registry.