block /

chalkline

Snap a line before your agents build

A new way for AI to search for data
View on GitHub
14GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 45a4735213 (2026-10-08).

Selected work

David Hamilton
@daveh-beep

“Clarify sharing readiness and bound local corpus ingestion”. 5 files, 198 lines in tests, tools, the project root.

Licence

The repository

Apache-2.0

Checked by a person at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-19. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

agentsagents-mdai-agentscontent-designmcpstyle-guidetemplate-repositorywriting

Example questions

The prompt

Paste it into your AI agent. It clones block/chalkline at the pinned commit and indexes it on your machine.

Search the GitHub repository block/chalkline with XERJ (https://hub.xerj.org/corpus/block--chalkline).
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/block/chalkline chalkline && git -C chalkline checkout 45a4735213a28267a008aa10bb8cddfb624e5d06
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./chalkline --url http://127.0.0.1:9200 --prefix chalkline --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: Apache-2.0. Keep the copyright notice and credit the authors.

Related

David HamiltonAI, prompts and agents corporaagentscopeagnofastmcpkushalBanda/AI-Engineeragentprojectcontext/apxgeminik23/ai-agents

Selected work and consent: the XERJ registry.