fanout
Fewer broken merges from parallel Claude Code and Codex sessions: tests every branch merged together before main, and tells each session when another changes code it uses. Works with worktrees. No dependencies
What XERJ indexed
Snapshot
The whole repository at commit 54f7a54123 (2026-10-24). main is 60 commits ahead.
Selected work

“v0.14: cheaper session models, safer lean agents, more tests”. 12 files, 1,462 lines in bench, test, skills.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. 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
ai-agentsclaude-codeclaude-code-skillsgit-worktreecodexdeveloper-toolsmerge-conflictsmulti-agent
Example questions
- How does fanout implement ai-agents?
- Where does fanout handle “v0.14: cheaper session models, safer lean agents, more tests”?
- What does bench do in fanout?
Inside the indexed corpus
- 79 files, 528.9 KB in total, about 6.7 KB per file.
- The selected commit changed 12 of those files (15.2%).
- On GitHub since 2026-10-20, last push 2026-10-29, 84 commits on main.
- The pin is 60 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Breadstick-Crumbs/fanout on 2026-10-31, and the LICENSE file at commit 54f7a54123 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Anees (@Breadstick-Crumbs) has 1 selected repository on the hub.
Using XERJ with fanout
- A local search tool for Codex and Cursor fanout is tagged ai-coding-assistant 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.
- ripgrep vs a code index for coding agents: 30 tasks
The prompt
Paste it into your AI agent. It clones Breadstick-Crumbs/fanout at the pinned commit and indexes it on your machine.
Search the GitHub repository Breadstick-Crumbs/fanout with XERJ (https://hub.xerj.org/corpus/breadstick-crumbs--fanout). 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/Breadstick-Crumbs/fanout fanout && git -C fanout checkout 54f7a54123ce44526376e406e011c90dac41d3ba 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./fanout --url http://127.0.0.1:9200 --prefix fanout --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
Anees AI, prompts and agents corporaagent-managerxobotyi--cc-foundry-ai-helpers-skill-engineeringxobotyi--cc-foundry-grafanaHoussemDjeghri/self-reviewdooly6276/claude-bulkheadsaaranshM/unsnooze
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.