Roman Sodermans
Roman Sodermans'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 @romansod 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 gh-comments corpus
romansod/gh-comments: Read a GitHub PR's or issue's discussion as compact, grep-friendly text, review threads and their resolution state included. gh extension…
- Look up how gh-comments implements agent-skills, claude-code, claude-code-plugin, with answers cited to file and line.
- Reuse a worked example: the commit “measure the token cost of gh-comments on public targets” (10 files · Python).
- Answer from gh-comments's real Python source instead of memory (AI, prompts and agents).
- Where does gh-comments handle “measure the token cost of gh-comments on public targets”?
- How does gh-comments implement agent-skills?
- What does bench do in gh-comments?
Search the GitHub repository romansod/gh-comments with XERJ (https://hub.xerj.org/corpus/romansod--gh-comments). 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/romansod/gh-comments gh-comments && git -C gh-comments checkout 8c141e013daf82bb0a0ed985ef0fda4ba9948a26 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./gh-comments --url http://127.0.0.1:9200 --prefix gh-comments --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 romansod--gh-comments · AI, prompts and agents
Related corpora: xerj-blogposts, andreiverdes/bluedoc, crisperity/crisperity-skills
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
romansod/gh-comments
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.
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/romansod)
Included with the author's permission (email, 2026-10-22), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.