mushi-mushi: Skill for Cursor

.cursor/skills/mushi-setup/SKILL.md

mushi-setup is a skill for Cursor from kensaurus/mushi-mushi. It costs 94 tokens per session (1,379 once invoked), scanned A, original, MIT.

A setup guide for Mushi Mushi, a web-app testing system that maps user stories, captures bugs, and generates Playwright tests. It also explains how to connect the system to a project and coding tools.

In plain words
What is it for?
Use it to install the SDK, configure keys, connect a project, map stories from a live app, and generate TDD tests.
Why use it?
It removes the configuration work needed before Mushi Mushi can inspect an app, connect its console, and create tests.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is kensaurus/mushi-mushi's own configuration. It tells Cursor how to work on mushi-mushi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mushi-mushi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kensaurus/mushi-mushi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kensaurus/mushi-mushi/master/.cursor/skills/mushi-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kensaurus/mushi-mushi

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mushi-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/kensaurus/mushi-mushi/mushi-setup.svg)](https://agentmods.dev/skills/kensaurus/mushi-mushi/mushi-setup)
Your own site
<a href="https://agentmods.dev/skills/kensaurus/mushi-mushi/mushi-setup"><img src="https://agentmods.dev/badge/skills/kensaurus/mushi-mushi/mushi-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01379
Opus 5 $0.00047 $0.00690
Sonnet 5 $0.00019 $0.00276
Haiku 4.5 $0.00009 $0.00138

Measured 7d ago against content hash 6927ee58decc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mushi-setup 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 7d ago.

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.

.cursor/skills/mushi-setup/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mushi Mushi Setup

Overview

Mushi Mushi is a TDD/PDCA engine for web apps: it captures bugs, maps user stories from your live app, auto-generates Playwright tests, and continuously improves them via PDCA loops.

Console URLs

Environment Base URL
Hosted (default) https://kensaur.us/mushi-mushi/admin
Local monorepo http://localhost:6464 after pnpm dev
Override MUSHI_CONSOLE_URL (CLI + browser opens)

Resolution order: env → saved consoleUrl in ~/.config/mushi/config.json → localhost probe → monorepo heuristic → hosted.

Command matrix

Command Use when
npx mushi-mushi / mushi init First SDK install — framework detect, packages, .env.local
mushi connect --project-id <uuid> --endpoint <url> --write-env --wire-ide --wait Have ID + key; want env + Cursor MCP + heartbeat proof
mushi login Save credentials before other commands
mushi setup MCP-only wiring from saved config (not SDK install)

Do not mint SDK keys under Settings → BYOK. Use Setup → Verify → Generate API key (report:write).

Quick Start (5 steps)

1. Get your project credentials

Open the Mushi admin console (local: http://localhost:6464).

  1. Setup → Steps or Projects → New project — create a project.
  2. Copy Project ID (UUID) from the success panel immediately after Create.
  3. Setup → VerifyGenerate API key (report:write). Shown once.

Or run npx mushi-mushi — the wizard opens /onboarding?tab=steps&setup=cli, verifies via whoami, then installs.

You need:

  • MUSHI_PROJECT_ID — UUID from success panel or Projects chip
  • MUSHI_API_KEYmushi_… from Verify tab

2. Install the SDK

# Recommended — wizard handles framework + env
npx mushi-mushi

# Or manual
npm install @mushi-mushi/web

3. Initialize in your app

import { Mushi } from '@mushi-mushi/web'

Mushi.init({
  projectId: process.env.MUSHI_PROJECT_ID!,
  apiKey: process.env.MUSHI_API_KEY!,
  capture: {
    discoverInventory: {
      enabled: true,
      routeTemplates: ['/items/[id]', '/users/[userId]/profile'],
    },
  },
})

Read the full file on GitHub · 173 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.

  1. 7d ago First seen · 173 lines · 94 tokens per session scan A 6927ee58decc

Subscribe to this mod's changes

mushi-setup is a skill published in the GitHub repository kensaurus/mushi-mushi (3 stars, last pushed 10d ago), licensed MIT. It adds 94 tokens to every session and 1,379 once invoked, about $0.0005 per session on Opus 5. 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.

Related

Other skills, from other repositories

test-component

Runs, analyzes, and fixes Playwright and accessibility tests for a specific DB UX component.

db-ux-design-system/core-web · 21 tokens

fullstack-testing-and-quality-gates

Define and enforce layered test strategy and quality gates for fullstack systems, including UI behavior, API contracts, integration paths, and release readiness criteria.

vaquarkhan/Fullstack-development-agent-skills · 37 tokens

e2e-testing-playwright-cypress

Implement end-to-end testing for critical user journeys using Playwright or Cypress with CI integration.

vaquarkhan/Fullstack-development-agent-skills · 27 tokens

cometchat-native-testing

Testing patterns for CometChat React Native — Jest + React Native Testing Library setup, mocking the UI Kit + SDK, testing custom bubbles / headers / composer actions, snapshot pitfalls, E2E with Detox vs Maestro, and CI integration. Covers what to test vs what to skip.

cometchat/cometchat-skills · 63 tokens

cometchat-flutter-v5-testing

Testing patterns for CometChat Flutter UIKit v5 (GetX-based). Covers fluttertest (built-in), mocktail for SDK mocking, widget tests around CometChat widgets, integrationtest for real-device flows, golden tests for theming, and CI on GitHub Actions / Codemagic. Sister skill of cometchat-flutter-v6-testing — the cohorts…

cometchat/cometchat-skills · 99 tokens

cometchat-ios-testing

Testing patterns for CometChat iOS UI Kit v5 in Swift / SwiftUI / UIKit projects. Covers XCTest setup, mocking CometChatSDK + CometChatUIKitSwift via protocols, snapshot testing with iOSSnapshotTestCase, async/await test helpers, UI testing for full chat flows on simulators, and CI on Xcode Cloud / GitHub Actions.

cometchat/cometchat-skills · 81 tokens