What is fix-with-mushi?

A guided command for investigating a Mushi bug report and requesting an automated fix attempt. Mushi is a service that collects user bug reports, and the resulting change is provided as a GitHub pull request.

Use it to triage a report, send a confirmed fix attempt, monitor its progress, retrieve the fix details, and close the report after the change is reviewed and merged.

It requires you to review the investigation and confirm the scope before a fix is dispatched. The generated pull request stays in draft form for human review by default.

fix-with-mushi — Command for Claude Code and Cursor by kensaurus

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.

Clone the repo

git clone --depth 1 https://github.com/kensaurus/mushi-mushi

Made for: Claude Code, Cursor.

Or install mushi-mushi, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/kensaurus/mushi-mushi/fix-with-mushi/github.svg)](https://agentmods.dev/commands/kensaurus/mushi-mushi/fix-with-mushi)

Your own site

<a href="https://agentmods.dev/commands/kensaurus/mushi-mushi/fix-with-mushi"><img src="https://agentmods.dev/badge/commands/kensaurus/mushi-mushi/fix-with-mushi/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/kensaurus/mushi-mushi/fix-with-mushi"><img src="https://agentmods.dev/badge/commands/kensaurus/mushi-mushi/fix-with-mushi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 344 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00344
Opus 5	$0.00000	$0.00172
Sonnet 5	$0.00000	$0.00069
Haiku 4.5	$0.00000	$0.00034

Measured 9d ago against content hash 34782e639f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fix-with-mushi 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 9d 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.

packages/cursor-plugin/commands/fix-with-mushi.md · 38 lines

What it actually says

Fix a Bug with Mushi

Investigate a Mushi bug report and dispatch an automated fix attempt, with human review at every stage.

Prerequisites

MUSHI_API_KEY must have mcp:write scope (or the project key must include mcp:write).
You must confirm the fix scope with the user before dispatching.

Steps

Triage first — run /triage-mushi-report for the target report. Do not skip this.
After presenting triage findings, ask: "Shall I dispatch a fix attempt? The PR will be a draft for your review."

On confirmation, call:

dispatch_fix { reportId: "<id>", autoReadyPr: false }

The response includes a prUrl (GitHub pull request). Share it with the user.

Monitor progress (optional):

get_recent_fixes { reportId: "<id>", limit: 1 }

Then:

get_fix_context { reportId: "<id>" }

Once the fix is reviewed and merged, the report moves to fixed. To close it manually:
```
close_report { reportId: "<id>" }
```
Only with explicit user confirmation.

Safety

autoReadyPr: false is mandatory unless the user explicitly requests auto-ready.
Never dispatch a fix for severity: critical reports without also sharing the blast radius.
If dispatch_fix returns an error, do not retry automatically — surface the error and ask the user what to do next.

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.

9d ago First seen · 38 lines · 0 tokens per session scan A 34782e639f7f

Subscribe to this mod's changes

fix-with-mushi is a command published in the GitHub repository kensaurus/mushi-mushi (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 344 tokens. 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.

Claude Code Debugging angular auto-fix bug-reporting feedback-widget llm-ops

upgrade-fix

Re-run the build-fix-verify cycle for the current upgrade step.

Acheron-AI/angular-upgrade-kit · 14 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

fix-with-mushi