# sentient

sentient — a test command demonstrating how Claude Code guards projects against destructive operations. Shows the system blocking deletion commands to help you understand safety mechanisms.

- command · `type=command` · Claude Code, Codex, GitHub Copilot, Gemini CLI · ★ 3990 repo stars
- Author: disler
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/disler/claude-code-hooks-mastery/tree/HEAD/.claude/commands/sentient.md
- Updated: 2026-03-04
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/sentient

## What it does

sentient is a demonstration command that illustrates codebase protection in Claude Code. Built with Bash, it reveals how the system can intercept and prevent potentially harmful operations, such as recursive file deletion. This gives developers insight into configuring safeguards for their own projects.

The command runs against a local Git repository and requires Bash to execute. Installation varies by editor: place the file in `.claude/commands/sentient.md` for Claude Code.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/sentient.md` — Call it with /sentient. For all projects use ~/.claude/commands/

### Codex

**Manually: put the files in place**
- File: `~/.codex/prompts/sentient.md` — Call it with /prompts:sentient. Codex marks this format deprecated in favour of skills

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/sentient.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/sentient.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/disler/claude-code-hooks-mastery/tree/HEAD/.claude/commands/sentient.md

## When to use it
- Demonstrate how dangerous commands are blocked
- Show deletion protection in action
- Understand Claude Code's safety mechanisms

## Example prompts
- Run sentient to see how destructive commands are intercepted
- Test the command blocking mechanism with sentient
- Observe the safety demo to learn how to protect your own projects

## Similar
- [careful](https://affpapa.org/en/nevibecode/skills/careful.md) — skill · 417 installs
- [guard](https://affpapa.org/en/nevibecode/skills/guard.md) — skill · 389 installs
- [nah](https://affpapa.org/en/nevibecode/plugins/nah.md) — plugin · ★ 494 repo stars
- [git-safety](https://affpapa.org/en/nevibecode/plugins/git-safety.md) — plugin · ★ 586 repo stars
- [hookify](https://affpapa.org/en/nevibecode/commands/hookify.md) — command · ★ 47914 repo stars
- [safety-guard](https://affpapa.org/en/nevibecode/skills/safety-guard.md) — skill · 6200 installs

From the same set: [disler/claude-code-hooks-mastery](https://affpapa.org/en/nevibecode/by/disler/claude-code-hooks-mastery.md) — 25 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
