# Lixpi Lixpi Terminal Via Pylance

> Terminal-Via-Pylance

- Skill: `tomevault-io/lixpi-lixpi-terminal-via-pylance` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add tomevault-io/lixpi-lixpi-terminal-via-pylance`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/lixpi-lixpi-terminal-via-pylance/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tomevault-io (https://skillmd.com/u/tomevault-io)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tomevault-io/lixpi-lixpi-terminal-via-pylance

---


# Terminal-Via-Pylance

This skill is the discoverable companion to the always-on instructions file at [.github/instructions/terminal-via-pylance.instructions.md](.github/instructions/terminal-via-pylance.instructions.md).

Before running any command, follow the Docker-only command rule in `AGENTS.md` and `documentation/development-workflow/AGENT-SKILLS.md`: never run `npm`, `npx`, `pnpm`, or `pnpx` on the host, including through Pylance.

That instructions file is the source of truth. Read it for:

- The full list of prohibited (mutating) command categories.
- The full list of allowed (read-only) commands.
- The exact `subprocess.run(...)` snippet template to use with `mcp_pylance_mcp_s_pylanceRunCodeSnippet`.
- The mandatory three-step self-check to run before every shell action.

Do not improvise — follow the instructions file exactly.

---
> Source: [Lixpi/lixpi](https://github.com/Lixpi/lixpi) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-06-16 -->

