Portage
Let your agent go to the store (chill, you approve every payment ). CLI, Claude Code plugin and Ruby gems for MCP/UCP
What XERJ indexed
Snapshot
The whole repository at commit e5060ec1cf (2026-10-18). main is 30 commits ahead.
Selected work
“Give generated MCP tools real descriptions, param docs and annotations”. 5 files, 232 lines in portage-ucp.
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
bigcommercecli-toolecommerceetsyinstagrammagentomcpruby
Example questions
- How does Portage implement bigcommerce?
- Where does Portage handle “Give generated MCP tools real descriptions, param docs and annotations”?
- What does portage-ucp do in Portage?
Inside the indexed corpus
- Languages by size: Ruby 95.3%, TypeScript 3%, JavaScript 1.3%, Shell 0.2%, HTML 0.1%.
- On GitHub since 2026-08-14, last push 2026-10-22, 647 commits on main.
- The pin is 30 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for tomtom87/Portage on 2026-10-29, and the LICENSE file at commit e5060ec1cf was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Tom Whitbread (@tomtom87) has 4 selected repositories on the hub.
Their other repository pages: tomtom87/blog, tomtom87/homebrew-portage, tomtom87/latest.
Using XERJ with Portage
- Code search MCP for Claude Code: cite file:line, not grep Portage is tagged mcp on GitHub.
- What is an MCP memory server?
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- ripgrep vs a code index for coding agents: 30 tasks
The prompt
Paste it into your AI agent. It clones tomtom87/Portage at the pinned commit and indexes it on your machine.
Search the GitHub repository tomtom87/Portage with XERJ (https://hub.xerj.org/corpus/tomtom87--portage). 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/tomtom87/Portage Portage && git -C Portage checkout e5060ec1cf00d0ae11238dcc4bee165428e6084e 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Portage --url http://127.0.0.1:9200 --prefix portage --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
Tom WhitbreadAI, prompts and agents corporafluentdlicenseeavrotomtom87/homebrew-portagewbasmayor/ai-liteyotamon/Liquid-Loom
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.