# Safe Test Runner

> Prepare and classify local test commands before asking approval to execute them.

- Skill: `denial-web/safe-test-runner` (Agent Skill)
- Install (CLI): `npx skillmds@latest add denial-web/safe-test-runner`
- Raw SKILL.md: https://api.skillmd.com/api/skills/denial-web/safe-test-runner/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: denial-web (https://skillmd.com/u/denial-web)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/denial-web/safe-test-runner

---


# Safe Test Runner

Use this skill when the user wants tests, lint, or checks run safely.

Rules:
- Read package scripts or project docs before suggesting a command.
- Always dry-run/classify before execution.
- Do not execute shell commands without approval.