dsh-learn
Persistent learning for DeepSeek Harness: turn a session's corrections, failures and fixes into ordinary DSH skills. Zero extra model calls
What XERJ indexed
Selected work

“v0.3.13: host-semantics recheck: cache, guards, and failure recovery”. 10 files, 523 lines in lib, scripts, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-21. 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
cordisdeepseek-harnessdshdsh-pluginlearningmemoryskills
Example questions
- How does dsh-learn implement cordis?
- Where does dsh-learn handle “v0.3.13: host-semantics recheck: cache, guards, and failure recovery”?
- Show the deepseek-harness code in dsh-learn.
The prompt
Paste it into your AI agent. It clones xiex16070-jpg/dsh-learn at the pinned commit and indexes it on your machine.
Search the GitHub repository xiex16070-jpg/dsh-learn with XERJ (https://hub.xerj.org/corpus/xiex16070-jpg--dsh-learn). 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/xiex16070-jpg/dsh-learn dsh-learn && git -C dsh-learn checkout ab4d9cf6acf31d6753fc11bd4f891d1615a85f66 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./dsh-learn --url http://127.0.0.1:9200 --prefix dsh-learn --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
Akari AkazaAPI design and specification corpora12-factor-agentsagent-session-trajectoriesatoma-run--atomaIanzhyh/workbuddy-to-dshPhysicolor/dsh-widgetsAI-Scarlett/DSH-Store
Selected work and consent: the XERJ registry.