verdict

Code review any coding agent can run: fetch, review, gate, post. Evidence-graded findings, cost rollups, one static binary: no server, no…

A new way for AI to search for data
View on GitHub
1GitHub stars

shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 561e316ad8 (2026-10-30).

Selected work

Sutu Sebastian
@SutuSebastian

“structured local knowledge base (learn verb, kb recall, flip-ti…”. 4 files, 990 lines in scripts, evals, the project root.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-31. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

ai-agentscode-reviewcoding-agentsgithubllmpull-requestsagent-skillscli

Example questions

The prompt

Paste it into your AI agent. It clones stainless-code/verdict at the pinned commit and indexes it on your machine.

Search the GitHub repository stainless-code/verdict with XERJ (https://hub.xerj.org/corpus/stainless-code--verdict).
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/stainless-code/verdict verdict && git -C verdict checkout 561e316ad8243e6702a5eee431219c74a4a1fcc0
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./verdict --url http://127.0.0.1:9200 --prefix verdict --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

Selected work and consent: the XERJ registry.