engineering-pack
Craft Capabilities: portable engineering workflows and deterministic tooling for AI coding agents across Claude Code, Codex, Gemini, Cursor, and more
What XERJ indexed
Snapshot
The whole repository at commit 952c93bf9d (2026-10-27). main is 10 commits ahead.
Selected work
“readable layout and state-clean”. 45 files, 2,625 lines in platform, engine, application.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. 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
agent-skillsagentic-workflowsai-agentsclaude-codecodexcoding-agentsdeveloper-toolsgemini-cli
Example questions
- How does engineering-pack implement agent-skills?
- Where does engineering-pack handle “readable layout and state-clean”?
- What does platform do in engineering-pack?
Inside the indexed corpus
- 481 files, 14.4 MB in total, about 30.7 KB per file.
- The selected commit changed 45 of those files (9.4%).
- Languages by size: Rust 70.6%, JavaScript 29.4%.
- On GitHub since 2026-10-16, last push 2026-10-29, 26 commits on main.
- The pin is 10 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Aliaksie/engineering-pack on 2026-10-29, and the LICENSE file at commit 952c93bf9d was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Aliaksei (@Aliaksie) has 1 selected repository on the hub.
Using XERJ with engineering-pack
- A local search tool for Codex and Cursor engineering-pack is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best MCP servers for local code search in 2026, compared
The prompt
Paste it into your AI agent. It clones Aliaksie/engineering-pack at the pinned commit and indexes it on your machine.
Search the GitHub repository Aliaksie/engineering-pack with XERJ (https://hub.xerj.org/corpus/aliaksie--engineering-pack). 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/Aliaksie/engineering-pack engineering-pack && git -C engineering-pack checkout 952c93bf9ddc9729315fea730034395ff1039a96 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./engineering-pack --url http://127.0.0.1:9200 --prefix engineering-pack --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
AliakseiAI, prompts and agents corporaharpervanguard-context-burntexiojustn-hyeok/brgrainz-dg/triad-plus-engineering-loopmarkoblogo/abvx-agent-skills
Stats: GitHub API, fetched 2026-10-29. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.