Nisconder

What an agent can do with the npm-safe corpus

nisconder/npm-safe: Local-first npm supply-chain security scanner: static + optional LLM analysis, CLI/CI gates, desktop app, and AI-agent skills

• Look up how npm-safe implements cli, desktop-app, llm, with answers cited to file and line.
• Reuse a worked example: the commit “repair install gate execution and validation” (20 files · TypeScript, JavaScript).
• Answer from npm-safe's real TypeScript source instead of memory (AI, prompts and agents).

• Where does npm-safe handle “repair install gate execution and validation”?
• How does npm-safe implement cli?
• What does packages/core do in npm-safe?

Search the GitHub repository nisconder/npm-safe with XERJ (https://hub.xerj.org/corpus/nisconder--npm-safe).
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/nisconder/npm-safe npm-safe && git -C npm-safe checkout 2894f4baf96293f2c8cad9b980f853b735829bc4
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./npm-safe --url http://127.0.0.1:9200 --prefix npm-safe --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus nisconder--npm-safe · AI, prompts and agents
Related corpora: lego, owasp-cheatsheets, profullstack/threatcrush, ilyasbozdemir/workdesk-360
AI search and retrieval with XERJ · Case study: reference coding for agents