# Code Request Safety

> Code Request Safety

- Skill: `lubochka/code-request-safety-3` (Agent Skill)
- Install (CLI): `npx skillmds@latest add lubochka/code-request-safety-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lubochka/code-request-safety-3/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: lubochka (https://skillmd.com/u/lubochka)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/lubochka/code-request-safety-3

---

# Code Request Safety

## Purpose
Check risk before code actions.

## When to Use
Use before running commands, editing files, deleting files, moving data, or changing configuration.

## Inputs
User request, filesystem scope, command risk, approval policy, project safety rules.

## Steps
1. Identify the intended operation.
2. Identify destructive or broad effects.
3. Verify the allowed scope.
4. Require a gate for unsafe work.

## Gates
Dangerous or unclear operations are blocked or explicitly approved.

## Evidence
Chosen command/edit scope and safety rationale.

## Anti-Patterns
Running destructive commands from guessed paths.

## Related
`code-execution`, `no-secrets`