# quick-plan

quick-plan turns requirements into structured implementation blueprints stored in the specs/ folder. Useful before starting complex refactoring or new feature work.

- command · `type=command` · Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI · ★ 1573 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-multi-agent-observability/tree/HEAD/.claude/commands/quick-plan.md
- Updated: 2026-02-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/quick-plan

## What it does

The command processes raw user requirements, evaluates technical decisions, and drafts an engineering specification. It creates a markdown blueprint. The file gets a descriptive kebab-case name and lands directly in the `specs/` directory. Each spec outlines problem goals, architecture choices, sequential rollout steps, edge cases, and a verification plan.

Execution relies on filesystem capabilities, specifically `Read`, `Write`, `Edit`, `Glob`, `Grep`, and `MultiEdit`. Without file write permissions, the assistant cannot persist the plan. Once the file is written, the command prints a brief checklist of the core components.

## Install

### Claude Code (native platform)

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

### Codex

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

### GitHub Copilot

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

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/quick-plan.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-multi-agent-observability/tree/HEAD/.claude/commands/quick-plan.md

## When to use it
- draft an engineering blueprint before writing production code
- document architecture decisions and testing criteria in `specs/`
- break complex features into sequential implementation steps

## Example prompts
- /quick-plan design a migration workflow from session auth to JWT tokens
- /quick-plan outline the architecture for a Redis caching layer

## Similar
- [plan](https://affpapa.org/en/nevibecode/commands/disler-plan.md) — command · ★ 3990 repo stars
- [plan-review](https://affpapa.org/en/nevibecode/skills/plan-review.md) — skill · ★ 8928 repo stars
- [spec](https://affpapa.org/en/nevibecode/skills/spec.md) — skill · 5000 installs
- [rpi-plan](https://affpapa.org/en/nevibecode/skills/rpi-plan.md) — skill · ★ 1627 repo stars
- [speckit-plan](https://affpapa.org/en/nevibecode/skills/speckit-plan.md) — skill · 2600 installs
- [planning-and-task-breakdown](https://affpapa.org/en/nevibecode/skills/planning-and-task-breakdown.md) — skill · 80700 installs

From the same set: [disler/claude-code-hooks-multi-agent-observability](https://affpapa.org/en/nevibecode/by/disler/claude-code-hooks-multi-agent-observability.md) — 20 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
