A plugin marketplace package containing two plugins with short commands for commonly used Claude Code skills and agents. Its commands cover tasks such as questions, brainstorming, debugging, code review, security checks, prompt refinement, and interface design.

Use its commands to ask read-only questions, investigate bugs, review code, apply standards, improve prompts, plan work, and assess or refine user interfaces.

It reduces repeated typing when you use the same development workflows often.

rapid-stack — Plugin by artttj

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add artttj/rapid-stack

agentmods

npx agentmods add plugins/artttj/rapid-stack/marketplace

Clone the repo

git clone --depth 1 https://github.com/artttj/rapid-stack

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

rapid-stack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  "name": "rapid-stack",
  "owner": {
    "name": "Artem Iagovdik",
    "url": "https://github.com/artttj"
  },
  "metadata": {
    "description": "Short slash commands that wrap the Claude Code skills you already use.",
    "version": "1.4.0"
  },
  "plugins": [
    {
      "name": "rs",
      "source": "./plugins/rs",
      "description": "Short slash commands aliasing skills and agents you reach for often. /ask is read-only Q&A. /brn is a brainstorm with a recommended execution path. /dbg runs systematic debugging (reproduce, hypothesize, isolate). /10x runs product strategy analysis. /trim, /cr, /sec wrap their agents. /hum runs the-humanizer. /jobs channels Steve Jobs. /ui calls ui-ux-pro-max. /vibe audits UI quality across eight dimensions and catches AI sameness. /mimic learns any brand and generates a design system. /polish enforces minimal dashboard design. /std and /prm wrap their respective skills.",
      "version": "1.3.0",
      "author": {
        "name": "Artem Iagovdik",
        "url": "https://github.com/artttj"
      },
      "homepage": "https://github.com/artttj/rapid-stack",
      "license": "MIT",
      "category": "productivity",
      "keywords": [
        "shortcuts",
        "aliases",
        "slash-commands",
        "brainstorm",
        "debugging",
        "humanizer",
        "code-review",
        "design",
        "vibe-check",
        "brand-design",
        "mimic",
        "steve-jobs"
      ]
    },
    {
      "name": "op",
      "source": "./plugins/op",
      "description": "The operator layer. /op:go classifies any ask and routes it (bug, small fix, or feature). Features run a scaled gate: /op:spec writes a self-approved spec, /op:plan pins a build plan to it by content hash, /op:build executes with TDD and capped review. /op:ship commits, deploys, and verifies the live site cache-busted. /op:sync pulls prod state to localhost. /op:show screenshots

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 65 lines scan A 8bf2d5c9c60e

Subscribe to this mod's changes

rapid-stack is a plugin published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Debugging Security agent-skills ai-agents claude-code developer-tools opencode slash-commands

rapid-stack

Getting it into your agent

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other plugins, from other repositories

borski

superset

claude

claude-architect

3xa-harness

subagent-model-routing