SkillAgentSearch skills...

mushi-mushi

Your AI built it. Mushi Mushi makes it better: it finds what breaks, where people get stuck and what the code needs, then hands your editor the fix. Open source.

Install / Use

claude mcp add kensaurus -- npx -y github:kensaurus/mushi-mushi

If the server publishes to npm under a different name, use that package instead β€” check the repo README.

About this skill
πŸ”Œ

MCP Server

Model Context Protocol server

Quality Score

83/100

Supported Platforms

Claude Code
Claude Desktop
Cursor

Our assessment of mushi-mushi

mushi-mushi scores 83/100 on our quality scale, 2995th of 4,716 Development & Engineering skills we index.

Its MCP Server is 23 KB long, well organised into 12 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so mushi-mushi is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-14. Automated pattern scan on 2026-11-14. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

mushi-mushi compared with similar skills

All 4 of these similar skills score higher than mushi-mushi; compare them before choosing.

SkillScoreStarsUpdatedFormat
mushi-mushi (this skill)by kensaurus833todayMCP Server
taste-skillby Leonxlnx100118.9k11d agoCLAUDE.md
Agent-Reachby Panniantong100113.3k12d agoCLAUDE.md
hyperframesby heygen-com10087.1ktodayCLAUDE.md
rufloby ruvnet10082.1ktodayCLAUDE.md

Frequently asked questions

How do I install mushi-mushi?
Run claude mcp add kensaurus -- npx -y github:kensaurus/mushi-mushi. The install tabs above show the steps for each supported agent.
Which AI agents does mushi-mushi work with?
It is written for Claude Code, Claude Desktop and Cursor, as a MCP Server file. Other agents that read the same format can often use it too.
Is mushi-mushi safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mushi-mushi still maintained?
The repository was last updated today, so mushi-mushi is actively maintained.
<div align="center">

Mushi Mushi

Your AI built it. Mushi Mushi makes it better.

Mushi Mushi checks your live site, shows where people get stuck, and reviews your code. Your users can tap a button to report a bug. Each problem comes with a plain-English explanation and a fix that Lovable, Cursor or Claude Code can apply.

Fix what breaks Β· Smooth the journeys people take Β· Clean up the code β€” one place, from your editor.

Check your live app free β†’ No sign-up, nothing to install.

Add it to Lovable or Bolt with one prompt β†’ No terminal, about five minutes, free for one app.

Or, in your app's folder:

npx mushi-mushi

<sub>Built for the vibe coder who ships fast with Cursor, Claude Code, Lovable or Bolt.</sub>

npm Server OpenSSF Scorecard npm provenance skills.sh

Quick start Β· How it works Β· Docs Β· Sample diagnosis Β· Why not Sentry? Β· Self-host Β· Vision

<a href="https://kensaur.us/mushi-mushi/docs/demo/diagnosis?src=github-readme" title="See a sample diagnosis: no signup"> <img alt="A Mushi Mushi diagnosis of the report 'Pay now does nothing on my phone': the cause in plain English, why it broke, the two lines of code at fault, the suggested fix and the steps to reproduce." src="./docs/screenshots/sample-diagnosis.png" width="100%" /> </a>

<sub>↑ What comes back when a user writes "Checkout button does nothing on my phone". Click for the whole sample, from their words to the fix prompt, without signing up.</sub>

</div>

How it works

<a href="https://kensaur.us/mushi-mushi/docs/how-it-works" title="Watch the walkthroughs"> <img alt="Walkthrough video: a real bug report in the Mushi Mushi console, its plain-English diagnosis, the fix prompt for your editor and the pull request that fixed it." src="./apps/docs/public/walkthroughs/bug-to-fix.jpg" width="100%" /> </a>

<sub>↑ Short videos that show every click: a user reporting a bug, the diagnosis, connecting your editor, and the fix shipping. Watch them on How it works.</sub>

flowchart LR
    U["Your users<br/>tap the bug widget"] --> M
    S["Your monitoring<br/>Sentry, Crashlytics… (optional)"] -.-> M
    M["Mushi Mushi<br/>one queue Β· diagnosis Β· fix"] --> E["Your editor or agent<br/>Cursor, Claude Code (MCP)"]
    E --> P["Draft PR<br/>you review it"]
    P --> R["Release<br/>report closes, user is told"]
  1. Capture. A user taps the widget. Mushi Mushi records a screenshot, the route, their note, and the last console and network events.
  2. Diagnose. Mushi Mushi writes the root cause in plain English with a fix prompt. Twenty reports of the same broken button become one row.
  3. Fix. Your editor reads the diagnosis over MCP and makes the fix with its own model. If you prefer, an agent opens a draft PR that you review like any other. On hosted Mushi Mushi the built-in fixer needs no key of your own; Cursor's agents need your Cursor key; or run fixes on your own computer with the Mushi Mushi worker. With your own Anthropic or OpenAI key, a second AI (Claude Opus, or GPT on an OpenAI key) reviews each agent PR first. Mushi Mushi will not merge a PR it says to hold unless you override it in the console and give a reason.

It catches the bugs that never throw an error: the pay button hidden under the keyboard, the Save button tapped twice because nothing happened, the dashboard that takes 12 seconds.

Beyond bugs. The same queue improves the rest of the app:

  • Journeys. The Journey optimizer maps how people move from page to page, from real visits, and flags dead ends, loops, pages people leave from, and orphan or duplicate pages. Each finding has a plain suggestion and a prompt your coding agent can run. The map from visits needs no key; the crawl of your live site needs a Firecrawl key. A first-time user test shows where a new user gets stuck (it runs on your own coding agent).
  • Code. Known security holes in your dependencies (once GitHub is connected), code audits run by your own agent, and clean-up of the branches and PRs Mushi Mushi made. Every change is a pull request you review.

Quick start

npx mushi-mushi

Run it in your app's folder. What happens next:

  1. You sign in through your browser. Your free project and key are made for you. There is nothing to copy.
  2. It installs Mushi Mushi and shows you a few lines of code. Add them to your app (or ask your AI editor to). They show a small report button.
  3. Your users tap the button when something is wrong and write one sentence. Mushi Mushi adds a screenshot and what the app was doing.
  4. You get the cause in plain English, and a fix your AI editor can apply.

Prefer to have your AI editor run it? Paste this into Cursor or Claude Code:

Add Mushi Mushi to this app. In the project folder, run `npx mushi-mushi --yes`.
It prints a sign-in link: show it to me and wait while I approve it in my
browser. Then add the code it prints to the file it names, and tell me which
file you changed.

Starting from nothing? npx mushi-mushi --template vue my-app (or svelte, node) makes a starter app with Mushi Mushi already in it. Want your linter to catch the buttons that do nothing and the fake data AI tools leave behind? Add mushi-mushi/eslint to eslint.config.js.

Then connect your editor so it can read diagnoses: one click on the Connect page, or npx mushi-mushi setup --ide cursor (or --ide claude). Ask it: "Get the latest Mushi Mushi report and fix it."

Building in Lovable or Bolt, with no terminal? Paste one script tag through your prompt instead: Mushi Mushi in Lovable or Bolt.

The SDK needs two env vars (VITE_MUSHI_PROJECT_ID / VITE_MUSHI_API_KEY, or NEXT_PUBLIC_MUSHI_*; see examples/sdk.env.example). No Sentry, no LLM key, no monitoring stack.

Before you deploy. The wizard writes those two variables to .env.local, which never reaches your host. Add them where your site is built (Vercel: Project β†’ Settings β†’ Environment Variables, Production; Netlify: Project configuration β†’ Environment variables), then redeploy. Without them the report button does not appear on the live site.

Want a real diagnosis of your own code right away? A test report is one made-up sentence, so its diagnosis is thin. Bring in a bug you already know about: npx mushi-mushi sentry import (your newest unresolved Sentry issues, once Sentry is connected under Integrations in the console) or npx mushi-mushi reports file --title "…" --description "…". Connect your GitHub repository so the diagnosis can name your files.

The hosted free plan covers one app and 100 diagnoses a month, with no card and no AI key of your own (pricing). Or you can self-host.

<details> <summary><b>Let your AI editor do the setup</b></summary>

Paste this into Cursor or Claude Code:

Install the Mushi Mushi skills from github.com/kensaurus/mushi-mushi (npx skills add kensaurus/mushi-mushi), then run the mushi-setup skill to wire the Mushi Mushi SDK and MCP server into this app and send a test report to verify the connection.

The skills also add /mushi-triage (evidence, diagnosis, then fix here or dispatch), /mushi-debug (a pass/fail health check, then why ingest or MCP fails), /mushi-test (generated tests and an end-to-end smoke test), /mushi-sdk-upgrade and /mushi-check-live-app (a free check of a live site). /mushi-mushi routes to the right one.

</details> <details> <summary><b>Add it by hand</b> (React shown; Vue, Svelte, Angular, React Native, vanilla JS, native)</summary>
npm install mushi-mushi        # React Native: npm install @mushi-mushi/react-native
import { MushiProvider } from 'mushi-mushi/react';

export function App() {
  return (
    <MushiProvider config={{ projectId: 'proj_xxx', apiKey: 'mushi_xxx' }}>
      <YourApp />
    </MushiProvider>
  );
}
import { MushiPlugin } from 'mushi-mushi/vue';             // Vue 3 / Nuxt: app.use(MushiPlugin, { projectId, apiKey })
import { initMushi } from 'mushi-mushi/svelte';            // Svelte / SvelteKit: initMushi({ projectId, apiKey })
import { provideMushi } from 'mushi-mushi/angular';        // Angular 17+: providers: [provideMushi({ projectId, apiKey })]
import { MushiProvider } from '@mushi-mushi/react-native';  // React Native: its own package (native code)
import { Mushi } from 'mushi-mushi';                       // any framework: Mushi.init({ projectId, apiKey })

Native SDKs (iOS, Android, Flutter) are a preview and install from this repository: see packages/ios, packages/android and packages/flutter. A runnable demo lives in examples/react-demo.

</details>

Already on @mushi-mushi/react, @mushi-mushi/web or another @mushi-mushi/* SDK? It keeps working and keeps getting updates. mushi-mushi ships the same code; switch when you like by changing the import path.

Who it's for

  • You build apps with AI, mostly on your own. You use Lovable, Bolt, Cursor or Claude Code, your app has real users, and you didn't write most of the code by hand. When someone says "it's broken", Mushi Mushi tells you the likely cause in plain English and gives your editor a fix prompt.
  • You're a developer and you own your code. You read the diffs and may already run Sentry. User reports and Sentry errors land in one list with duplicates merged, and an agent's fix gets a second AI review before it can merge.
  • You run a team. Reports arrive from the app, Sentry, store reviews and Slack, and nobody sees all of them. Here they share one list, each with a diagnosis, and they can go on to Linear, Jira or GitHub Issues.

The pains each group has, and where each should start: who it's for.

What's inside

| Package | For | What it does | | --- | --- | --- | | mushi-mushi | Your app | The one package: the setup wizard (npx mushi-mushi), starter apps (--template), the bug widget for any site, and lint rules for what AI tools leave behind (mushi-mushi/eslint) | | mushi-mushi/react, /vue, /svelte, /angular | Your app | The same widget wired into your framework | | mushi-mushi/node | Your server | Reports backend errors into the same queue | | @mushi-mushi/react-native, @mushi-mushi/capacitor | Your mobile app | The widget for native and hybrid apps (they ship native code, so they stay separate installs) | | @mushi-mushi/mcp | Your editor | Gives Cursor and Claude Code the diagnosis and fix tools | | @mushi-mushi/cli | Your terminal |

Truncated for display β€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategoryDevelopment
Updated27m ago
Forks2

Languages

TypeScript

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

1 medium1 low
mushi-mushi β€” MCP Server: Install & Safety Check | SkillAgent