Plugin

rapid

Name: rapid
Author: pragnition

RAPID - Rapid Agentic Parallelizable and Isolatable Development for Claude Code

npx claudepluginhub pragnition/pragnition-public-plugins --plugin rapid

Component Overview

Agents

Skills

Component Details

Agents (27)

RAPID Agent Identity

/rapid-auditor

RAPID Agent Identity

/rapid-bug-hunter

RAPID Agent Identity

/rapid-bugfix

RAPID Agent Identity

/rapid-codebase-synthesizer

RAPID Agent Identity

/rapid-conflict-resolver

RAPID Agent Identity

/rapid-context-generator

RAPID Agent Identity

/rapid-devils-advocate

RAPID Agent Identity

/rapid-executor

RAPID Agent Identity

/rapid-judge

RAPID Agent Identity

/rapid-merger

RAPID Agent Identity

/rapid-plan-verifier

RAPID Agent Identity

/rapid-planner

RAPID Agent Identity

/rapid-research-architecture

RAPID Agent Identity

/rapid-research-features

RAPID Agent Identity

/rapid-research-oversights

RAPID Agent Identity

/rapid-research-pitfalls

RAPID Agent Identity

/rapid-research-stack

RAPID Agent Identity

/rapid-research-synthesizer

RAPID Agent Identity

/rapid-research-ux

RAPID Agent Identity

/rapid-reviewer

RAPID Agent Identity

/rapid-roadmapper

RAPID Agent Identity

/rapid-scoper

RAPID Agent Identity

/rapid-set-merger

RAPID Agent Identity

/rapid-set-planner

RAPID Agent Identity

/rapid-uat

RAPID Agent Identity

/rapid-unit-tester

RAPID Agent Identity

/rapid-verifier

Skills (29)

Dual-Mode Operation Reference

/add-set

Add a new set to an existing project mid-milestone with discovery and contract generation

Dual-Mode Operation Reference

/assumptions

Surface Claude's mental model and assumptions about a set before execution begins

/rapid:audit-version -- Milestone Audit

/audit-version

Audit a completed milestone for gaps between planned requirements and actual delivery

Autopilot

/autopilot

Backend-managed autopilot poller that claims kanban cards from autopilot-enabled columns and dispatches agent runs

/rapid:backlog -- Capture Backlog Item

/backlog

Capture out-of-scope feature ideas as backlog items in .planning/backlog/

Dual-Mode Operation Reference

/branding

Conduct a structured branding interview with codebase-aware visual/UX brand guidelines, artifact gallery, and live-reloading webserver

Dual-Mode Operation Reference

/bug-fix

Investigate and fix bugs -- user describes a bug, model investigates and applies a fix

/rapid:bug-hunt -- Adversarial Bug Hunt Pipeline

/bug-hunt

Run adversarial bug hunt on a scoped set -- reads REVIEW-SCOPE.md

/rapid:cleanup -- Worktree Cleanup with Branch Deletion

/cleanup

Clean up completed set worktrees with safety checks and optional branch deletion

/rapid:context -- Codebase Analysis and Context Generation

/context

Analyze codebase and generate project context files (CLAUDE.md, style guide, conventions)

Dual-Mode Operation Reference

/discuss-set

Capture developer implementation vision for a set via structured discussion or auto-generate context with --skip

/rapid:documentation -- Documentation Generation

/documentation

Generate, update, and maintain project documentation from git history and RAPID artifacts

/rapid:execute-set -- Set Execution

/execute-set

Execute all waves in a set -- parallel dispatch for independent waves, sequential commits, artifact-based re-entry

/rapid:help -- Command Reference

/help

Show all available RAPID commands and workflow guidance

/rapid:install -- v7.0.1 Plugin Installation and Setup

/install

Install and configure RAPID v7.0.1 plugin for Claude Code

/rapid:merge -- Merge Pipeline Orchestrator (v2.2)

/merge

Merge completed sets into main -- subagent delegation per set, fast-path merge-tree, 5-level conflict detection, 4-tier resolution, adaptive conflict resolution via resolver agents, DAG-ordered merging, bisection recovery, rollback

/rapid:migrate -- Version Migration

/migrate

Migrate .planning/ state from older RAPID versions to current version

Dual-Mode Operation Reference

/new-version

Complete current milestone and start a new version with adaptive research pipeline and roadmap generation

/rapid:pause -- Pause Set Execution

/pause

Pause a set and save state for later resumption

/rapid:plan-set -- Set Planning

/plan-set

Plan all waves in a set with a single command -- researcher, planner, verifier pipeline (2-4 agent spawns)

Dual-Mode Operation Reference

/quick

Ad-hoc changes without set structure -- planner, verifier, executor pipeline

/rapid:register-web -- Register Project with Mission Control

/register-web

/rapid:resume -- Resume a Paused Set

/resume

Resume a paused set from its last checkpoint

/rapid:review -- Review Scoping

/review

Scope a completed set for review -- produces REVIEW-SCOPE.md

Dual-Mode Operation Reference

/scaffold

Generate project-type-aware foundation files for the target codebase

/rapid:start-set -- Set Initialization

/start-set

Initialize a set for development -- creates isolated worktree (or solo mode without worktree) and generates scoped CLAUDE.md

/rapid:status -- v7.0.1 Set Dashboard

/status

Show project dashboard with set statuses, last activity, and next actions

/rapid:uat -- User Acceptance Testing

/uat

Run user acceptance testing on a scoped set -- reads REVIEW-SCOPE.md

/rapid:unit-test -- Unit Test Pipeline

/unit-test

Run unit test pipeline on a scoped set -- reads REVIEW-SCOPE.md

README

_{Made with :heart: by @fishjojo1}

[!NOTE] RAPID is still in beta. Therefore, features may be broken/unpolished. Feedback is always welcome.

You are deep into a Claude session -- twenty minutes in, the model has seen your architecture, your test suite, your style conventions. Then it starts repeating itself. It forgets a decision you made five prompts ago. It hallucinates a function signature it generated correctly earlier. That is context rot: as the context window fills, the model loses grip on earlier decisions and artifacts, and quality degrades in ways you cannot predict. RAPID solves this by structuring work into isolated sets with /clear between every command, so each step gets a fresh context window loaded with exactly the artifacts it needs -- nothing more, nothing stale.

Install

[!TIP] Inside Claude Code:

/plugin marketplace add pragnition/pragnition-public-plugins
/plugin install rapid@pragnition-public-plugins

Then,

/rapid:install

Next, restart your terminal/source your shell

Requires Node.js 22+. For alternative installation methods, see DOCS.md.

The /clear Mental Model

After every RAPID command that produces artifacts, a box appears telling you to run /clear and what command comes next. This is intentional -- clearing context between steps keeps each command focused and prevents the degradation that ruins long sessions.

18 of 30 commands show this footer. Informational commands like /rapid:status and /rapid:help do not -- they consume minimal context and produce no artifacts.

Throughout this README, you will see /clear between every command. This is the pattern.

Quickstart

/rapid:init -- Research your project, generate a roadmap, decompose work into sets

/clear
/rapid:start-set 1 -- Create an isolated worktree for the first set

/clear
/rapid:discuss-set 1 -- Capture your implementation vision and design decisions

/clear
/rapid:plan-set 1 -- Research, produce wave-level plans, validate contracts

/clear
/rapid:execute-set 1 -- Execute all planned waves with parallel agents

/clear
/rapid:review 1 -- Scope the set for review (then optionally: unit-test, bug-hunt, uat)

/clear
/rapid:merge -- Integrate the completed set into main

/clear

Each command spawns specialized agents, produces artifacts, and advances the set through its lifecycle. The /clear between each step is not optional -- it is what keeps the whole system working.

[!TIP] RAPID does not confine you to parallel development. Pass --solo to any command to work without worktrees.

Your First Project

This walkthrough assumes you have installed RAPID and have a project you want to work on.

Step 1: Install and configure. Run /plugin install rapid@pragnition/pragnition-public-plugins , then /rapid:install inside Claude Code. Install configures the RAPID_TOOLS environment variable and builds the agent files your project needs. Reload your terminal/shell to source the new environment variable.

/clear

Step 2: Initialize your project. Navigate to your project directory in Claude Code and run /rapid:init. RAPID will ask you questions about your project, then spawn 6 research agents in parallel to analyze your codebase. You will be presented with a roadmap of sets -- independent workstreams that can be developed in parallel. Approve or adjust the roadmap before continuing.

/clear

Step 3(optional): Decide on your theming and branding. Run /rapid:branding. This starts an agent that walks through theming and UI decisions with you, spawning a local server for live testing.

Step 4: Start your first set. Run /rapid:start-set 1. This creates an isolated copy of your repo (a git worktree) where the first set's work will happen. No changes touch your main branch until you explicitly merge.

/clear

Step 5: Discuss implementation. Run /rapid:discuss-set 1. RAPID identifies design decisions where multiple valid approaches exist and asks for your input. Your answers are recorded into CONTEXT.md so the planner knows your intent.

/clear

View full README on GitHub

Similar Plugins

prompts.chat

159.9k

506

Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.

Stats

Version7.0.1

Stars4

MaintenanceExcellent

LicenseMIT

AddedApr 2, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Available In

pragnition-public-plugins

Safety Signals

Caution

Uses power tools

Uses Bash, Write, or Edit tools

Install

[!TIP] Inside Claude Code:

/plugin marketplace add pragnition/pragnition-public-plugins
/plugin install rapid@pragnition-public-plugins

Then,

/rapid:install

Next, restart your terminal/source your shell

Requires Node.js 22+. For alternative installation methods, see DOCS.md.

The /clear Mental Model

18 of 30 commands show this footer. Informational commands like /rapid:status and /rapid:help do not -- they consume minimal context and produce no artifacts.

Throughout this README, you will see /clear between every command. This is the pattern.

Quickstart

/rapid:init -- Research your project, generate a roadmap, decompose work into sets

/clear
/rapid:start-set 1 -- Create an isolated worktree for the first set

/clear
/rapid:discuss-set 1 -- Capture your implementation vision and design decisions

/clear
/rapid:plan-set 1 -- Research, produce wave-level plans, validate contracts

/clear
/rapid:execute-set 1 -- Execute all planned waves with parallel agents

/clear
/rapid:review 1 -- Scope the set for review (then optionally: unit-test, bug-hunt, uat)

/clear
/rapid:merge -- Integrate the completed set into main

/clear

Each command spawns specialized agents, produces artifacts, and advances the set through its lifecycle. The /clear between each step is not optional -- it is what keeps the whole system working.

[!TIP] RAPID does not confine you to parallel development. Pass --solo to any command to work without worktrees.

Your First Project

This walkthrough assumes you have installed RAPID and have a project you want to work on.

/clear

Step 3(optional): Decide on your theming and branding. Run /rapid:branding. This starts an agent that walks through theming and UI decisions with you, spawning a local server for live testing.

/clear

rapid

Component Overview

Component Details

Agents (27)

Skills (29)

README

Install

The /clear Mental Model

Quickstart

Your First Project

Similar Plugins

prompts.chat

rapid

Component Overview

Component Details

Agents (27)

Skills (29)

README

Install

The /clear Mental Model

Quickstart

Your First Project

Similar Plugins

prompts.chat

agent-teams

claude-code-toolkit

plugin-dev

dotnet-skills

compound-engineering