phantom
Phantom: dual-layer programming language - structured instructions embedded in ordinary Python source
What XERJ indexed
Snapshot
The whole repository at commit c2a52ece64 (2026-10-23). main is 73 commits ahead.
Selected work
“Fix source line counting to match Python”. 11 files, 253 lines in src/phantom, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-26. 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
clicode-generationgood-first-issuehelp-wantedlanguage-designllmopen-sourceparser
Example questions
- How does phantom implement cli?
- Where does phantom handle “Fix source line counting to match Python”?
- What does src/phantom do in phantom?
Inside the indexed corpus
- 121 files, 509.0 KB in total, about 4.2 KB per file.
- The selected commit changed 11 of those files (9.1%).
- Languages by size: Python 90.6%, JavaScript 5%, Shell 3.3%, PowerShell 0.6%, Emacs Lisp 0.4%.
- On GitHub since 2026-10-21, last push 2026-10-31, 98 commits on main.
- The pin is 73 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for alok-108/phantom on 2026-10-31, and the LICENSE file at commit c2a52ece64 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
汐 (@Zhuyuyangyy) has 3 selected repositories on the hub.
Their other repository pages: Zhuyuyangyy/TCM-SD42-Public-Reproducibility, Zhuyuyangyy/PhytoSkill-Spark.
Using XERJ with phantom
- How do I run syntax-aware code search? phantom is tagged parser on GitHub.
- XERJ vs ast-grep: syntax search and an index
- Search an OpenAPI spec so an agent can find endpoints The hub files it under API design and specification.
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones alok-108/phantom at the pinned commit and indexes it on your machine.
Search the GitHub repository alok-108/phantom with XERJ (https://hub.xerj.org/corpus/alok-108--phantom). 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/hayagrivai-labs/phantom phantom && git -C phantom checkout c2a52ece64afe7cd3693ca811de62e74cb365e51 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./phantom --url http://127.0.0.1:9200 --prefix phantom --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
汐API design and specification corporaprismgithub-opensource-guidelicenseeholt-oss/holtgodcodeengine/Godcode-engineRagedPanda/gh-claimcheck
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.