maid-runner
A deterministic CLI for manifest-driven AI development. MAID Runner turns change requirements into enforceable contracts for planning, TDD, implementation, review, and validation: helping AI coding agents deliver disciplined, evidence-backed changes with less drift
What XERJ indexed
Snapshot
The whole repository at commit dd0640ab2c (2026-10-23). main is 8 commits ahead.
Selected work

“discover Deno tests selected with dependency flags or Deno.test”. 6 files, 636 lines in tests, manifests, maid_runner.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-28. 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
agentic-codingai-agentsai-assisted-developmentai-developmentclicode-validationcoding-agentsdeveloper-tools
Example questions
- How does maid-runner implement agentic-coding?
- Where does maid-runner handle “discover Deno tests selected with dependency flags or Deno.test”?
- What does manifests do in maid-runner?
Inside the indexed corpus
- 2,239 files, 36.9 MB in total, about 16.9 KB per file.
- The selected commit changed 6 of those files (0.3%).
- Languages by size: Python 98.7%, CSS 0.4%, HTML 0.4%, JavaScript 0.3%, Makefile 0.1%.
- On GitHub since 2025-09-17, last push 2026-10-23, 1,314 commits on main.
- The pin is 8 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for mamertofabian/maid-runner on 2026-10-31, and the LICENSE file at commit dd0640ab2c was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Mamerto Fabian Jr (@mamertofabian) has 1 selected repository on the hub.
Using XERJ with maid-runner
- Index a monorepo so your agent stops reading the whole repo The pinned tree has 2,239 files.
- 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
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones mamertofabian/maid-runner at the pinned commit and indexes it on your machine.
Search the GitHub repository mamertofabian/maid-runner with XERJ (https://hub.xerj.org/corpus/mamertofabian--maid-runner). 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/mamertofabian/maid-runner maid-runner && git -C maid-runner checkout dd0640ab2c46089c5d0438a5c35556503ccd948f 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./maid-runner --url http://127.0.0.1:9200 --prefix maid-runner --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
Mamerto Fabian JrAI, prompts and agents corporatexiogossesanacore/engineering-constitutionAppVerk/av-marketplacemarkoblogo/abvx-agent-skills
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.