Silas

Corpus Hub contributor since 2026-10-23

Silas's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

12files

1,465lines

★ 1GitHub stars on repo

Totals across every corpus @SilasSolivagus appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the codex-kanban corpus

SilasSolivagus/codex-kanban: The Codex-native task board: four columns, approvals, blockers and durable repository state

Look up how codex-kanban implements agents, codex, kanban, with answers cited to file and line.
Reuse a worked example: the commit “import existing codex sessions into the board” (12 files · JavaScript).
Answer from codex-kanban's real JavaScript source instead of memory (AI, prompts and agents).

Example questions

Where does codex-kanban handle “import existing codex sessions into the board”?
How does codex-kanban implement agents?
What does plugin do in codex-kanban?

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

Search the GitHub repository SilasSolivagus/codex-kanban with XERJ (https://hub.xerj.org/corpus/silassolivagus--codex-kanban).
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/SilasSolivagus/codex-kanban codex-kanban && git -C codex-kanban checkout e193c28fbcd939cf88aedbc8a71b86513347eb2a
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./codex-kanban --url http://127.0.0.1:9200 --prefix codex-kanban --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.

corpus silassolivagus--codex-kanban · AI, prompts and agents
Related corpora: r2r-mcp, agentscope, calven-ai/marketing-as-code, DKotsyuba/agent-run
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 1

SilasSolivagus/codex-kanban

e193c28fbc feat: import existing codex sessions into the board

selected commit: 12 files · 1,465 lines · JavaScript · plugin, test, the project root

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus silassolivagus--codex-kanbanAIMITagentscodexkanbanmcptask-board agreed 2026-10-23

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/SilasSolivagus/badge.svg)](https://hub.xerj.org/contributors/SilasSolivagus)

Included with the author's permission (email, 2026-10-23), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.