goal-instruction-writer
Preview agent loops and write durable Goals for coding, game development, and research, with evidence, drift control, proportional verification, and clear stop conditions
What XERJ indexed
Snapshot
The whole repository at commit 9103705dc3 (2026-10-18). main is 5 commits ahead.
Selected work
“package the skill for OpenAI plugins”. 3 files, 188 lines in scripts, packaging, 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 2026-10-26. 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
agent-workflowsai-agentsautomationcodexcodex-skilldeveloper-toolsdrift-detectiongoal-driven-development
Example questions
- How does goal-instruction-writer implement agent-workflows?
- Where does goal-instruction-writer handle “package the skill for OpenAI plugins”?
- What does packaging do in goal-instruction-writer?
Inside the indexed corpus
- 81 files, 3.7 MB in total, about 47.0 KB per file.
- The selected commit changed 3 of those files (3.7%).
- Languages by size: HTML 91%, Python 9%.
- On GitHub since 2026-10-11, last push 2026-10-23, 38 commits on main.
- The pin is 5 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for wu736139669/goal-instruction-writer on 2026-10-31, and the LICENSE file at commit 9103705dc3 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Sebestian (@wu736139669) has 1 selected repository on the hub.
Using XERJ with goal-instruction-writer
- A local search tool for Codex and Cursor goal-instruction-writer is tagged codex 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.
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones wu736139669/goal-instruction-writer at the pinned commit and indexes it on your machine.
Search the GitHub repository wu736139669/goal-instruction-writer with XERJ (https://hub.xerj.org/corpus/wu736139669--goal-instruction-writer). 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/wu736139669/goal-instruction-writer goal-instruction-writer && git -C goal-instruction-writer checkout 9103705dc391ddca2e1294be0336d828684c9fbd 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./goal-instruction-writer --url http://127.0.0.1:9200 --prefix goal-instruction-writer --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
SebestianAI, prompts and agents corporaxobotyi--cc-foundry-ai-helpers-prompt-engineeringxobotyi--cc-foundry-ai-helpersxobotyi--cc-foundry-open-sourceBorstwerk/KI-Regelnmarcmarti9/agentitjuandelossantos/another-agent-skills
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.