Skip to main content
command CX Codex

rapid — Claude Code slash command: what it does, how to install

rapid puts Claude into a speed-first development mode: code right away, planning and docs kept short. Built for prototypes and MVPs.

MIT ★ 1,424 updated 2026-10-06

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

What rapid does

The command flips the agent into a fast mode: it writes code straight away instead of drawing up a plan, and takes a plain solution over a clever one. Rough edges such as error handling, input checks or caching get left as TODO comments rather than blocking the work.

The file rapid.md carries the rule set: what to do, what to skip, how to talk, plus a short code sample. Replies get shorter, code shows up first, questions come only when the agent is stuck. Tests go on critical paths, docs stay thin, and an existing library wins over a hand-rolled one.

It is meant for prototypes and MVPs. The file itself says to leave the mode before production, for security-sensitive work, for core business logic, and when a team shares the code. Pointing it at code that ships is a bad trade.

What it helps with

  • sketch a UI screen before the spec is settled
  • build a working MVP skeleton to test an idea
  • ship a small fix without docs or new abstractions
  • get runnable code now and park the polish as TODOs

Example prompts for the agent

  • /rapid build the signup form and its handler, leave error handling as a TODO
  • /rapid scaffold the tasks API, tests only on create and delete
  • /rapid move this module onto the existing library, no new abstractions

How to install rapid

Manually: put the files in place

.claude/commands/rapid.md

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

Questions about rapid

How do I install rapid in Claude Code?

Put the command file in your project at .claude/commands/rapid.md. The /rapid call is then available in Claude.

What does rapid do?

It switches Claude into a fast development mode where the agent implements directly and defers polish. Gaps are marked with TODO comments.

When should I leave rapid mode?

Before the code goes to production, on security-sensitive features, in core business logic, and whenever other people work on the same code.

Source text

rapid.md · MIT
---
description: Fast-paced development mode for quick iterations. Minimal ceremony, maximum speed. Best for prototypes, MVPs, and time-sensitive tasks.
---

# Rapid Development Mode

You are in rapid development mode. Speed is prioritized while maintaining basic quality standards.

## Principles

1. **Ship Fast** - Get working code out quickly
2. **Iterate** - Perfect is the enemy of good
3. **Minimal Overhead** - Skip ceremony, keep docs light
4. **Working > Pretty** - Functionality first, polish later

## Behavior

### Do
- Implement features directly without extensive planning
- Use simple, proven solutions over clever ones
- Add TODO comments for future improvements
- Write inline comments only where logic is complex
- Run tests only for critical paths
- Use existing libraries instead of building custom

### Don't
- Over-engineer or premature optimization
- Write extensive documentation
- Create unnecessary abstractions
- Spend time on edge cases (note them as TODOs)
- Perfect code style (formatters handle this)

## Communication Style

- Be concise - shorter responses
- Show code immediately
- Ask questions only when truly blocked
- Suggest improvements as "future TODOs" not blockers

## Code Style in Rapid Mode

```javascript
// Rapid mode: Get it working
// TODO: Add proper error handling
// TODO: Add input validation  
// TODO: Consider caching
function getData(id) {
  return fetch(`/api/data/${id}`).then(r => r.json());
}
```

## When to Exit Rapid Mode

Switch to a different mode when:
- Code is going to production
- Security-sensitive features
- Core business logic
- Team collaboration needed

© CloudAI-X · MIT · CloudAI-X/claude-workflow-v2

Similar slash commands

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

From the same set46

The whole set →
add-tests The add-tests command adds tests for a chosen file or function, or targets recently changed code when no argument is given. It runs the tests afterward. CX Codex +1 ★ 1,424repo stars metrics Turns the log kept by the track-metrics hook into a short report: how many turns ran, which files changed, what got committed. CX Codex +1 ★ 1,424repo stars commit-push-pr commit-push-pr prepares a conventional commit from staged diffs, pushes the branch, and opens a GitHub pull request. Prevents accidental commits to the default branch. CX Codex +1 ★ 1,424repo stars summarize-changes summarize-changes reads Git history and changed files to prepare standup notes, reports, or a PR description. Use it when a recent change summary needs a clear structure. CX Codex +1 ★ 1,424repo stars architect Switches Claude Code into a software architect mode to plan architectures, evaluate trade-offs, and draft ADRs before coding. CX Codex +1 ★ 1,424repo stars validate-build The validate-build command detects a project’s build system and runs checks for Node.js, Python, Go, or Rust. Use it after changes and before committing. CX Codex +1 ★ 1,424repo stars mentor mentor puts the assistant into teaching mode: it explains the reasoning behind code, walks through how it works and suggests what to try next. CX Codex +1 ★ 1,424repo stars review Sets Claude Code to run strict engineering reviews, triaging issues from critical security flaws to minor stylistic fixes. CX Codex +1 ★ 1,424repo stars

Project sponsors

Companies that keep this analytics open