Skip to main content
command CX Codex

sentient — Claude Code command: codebase protection demo

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.

no license ★ 3,990 updated 2026-03-04

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/sentient.md
Open on GitHub

What sentient 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.

What it helps with

  • Demonstrate how dangerous commands are blocked
  • Show deletion protection in action
  • Understand Claude Code's safety mechanisms

Example prompts for the agent

  • 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

How to install sentient

Manually: put the files in place

.claude/commands/sentient.md

Call it with /sentient. For all projects use ~/.claude/commands/

Questions about sentient

How do I install sentient in Claude Code?

Place the sentient.md file in the .claude/commands/ directory of your project.

What does sentient do?

It demonstrates how Claude Code blocks dangerous file deletion operations to protect your codebase.

What tools does sentient require?

The command uses Bash and requires it to be available in your environment.

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set25

The whole set →
build build reads a plan file, applies it to your codebase and prints the report section from that plan. Useful once the plan is written and only the implementation is left. CX Codex +1 ★ 3,990repo stars prime prime prepares agent context at the start of a session by inspecting project structure, reading core docs, and summarizing findings. CX Codex +1 ★ 3,990repo stars cook_research_only The cook_research_only command runs seven research tasks in parallel: five crypto reviews, market data collection, and a search for AI agent and LLM engineering practices. CX Codex +1 ★ 3,990repo stars hello-world-agent hello-world-agent — a Claude Code subagent that greets the user and asks what they need. It triggers on "hi claude", "hi cc", or "hi claude code". CX Codex ★ 3,990repo stars cook cook dispatches seven parallel sub-agent workflows covering crypto research, LLM engineering trends, and specialized agent creation. CX Codex +1 ★ 3,990repo stars prime_tts The prime_tts command checks the repository’s file structure and reads README.md to prepare a short project overview for a new session. It then runs the tts summary agent. CX Codex +1 ★ 3,990repo stars crypto_news_scanner_agent_prompt crypto_news_scanner_agent_prompt — a slash command that pulls recent crypto headlines and returns the 5 biggest with sources. Handy for a quick market check. CX Codex +1 ★ 3,990repo stars crypto_price_check_agent_prompt crypto_price_check_agent_prompt fetches current cryptocurrency prices in USD directly inside Claude Code. Checks Bitcoin if no token ticker is provided. CX Codex +1 ★ 3,990repo stars

Project sponsors

Companies that keep this analytics open