Mitsuro: Agent for Claude Code

.cursor/agents/quality-scout.md

quality-scout is an agent for Claude Code, Cursor from honeycomb-Technologies/Mitsuro. It costs 56 tokens per session (481 once invoked), scanned A, original, MIT.

A read-only code-review agent for one part of a larger codebase, called a sector. It looks for code that is too shallow, tangled, repeatedly validated, or inefficient on important paths.

In plain words
What is it for?
Use it to prepare a Scout Report before simplifying, restructuring, or optimising code. It can flag repeated logic, mixed responsibilities, unnecessary allocations, and other named problem areas.
Why use it?
It gives a quality-improvement process specific file-and-line evidence without changing files, deleting code, or wandering through unrelated parts of a monorepo, which is a repository containing multiple projects or packages.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is honeycomb-Technologies/Mitsuro's own configuration. It tells Claude Code and Cursor how to work on Mitsuro 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 Mitsuro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to honeycomb-Technologies/Mitsuro. 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/honeycomb-Technologies/Mitsuro/main/.cursor/agents/quality-scout.md
Clone the repo
git clone --depth 1 https://github.com/honeycomb-Technologies/Mitsuro

Made for: Claude Code, 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 quality-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/honeycomb-technologies/mitsuro/quality-scout/github.svg)](https://agentmods.dev/agents/honeycomb-technologies/mitsuro/quality-scout)
Your own site
<a href="https://agentmods.dev/agents/honeycomb-technologies/mitsuro/quality-scout"><img src="https://agentmods.dev/badge/agents/honeycomb-technologies/mitsuro/quality-scout/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.

agentmods 80×15 button for quality-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/honeycomb-technologies/mitsuro/quality-scout"><img src="https://agentmods.dev/badge/agents/honeycomb-technologies/mitsuro/quality-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 481 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 $0.00056 $0.00481
Opus 5.5 $0.00022 $0.00192
Sonnet 5.5 $0.00011 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 2mo ago against content hash ad670ee668c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quality-scout 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 2mo 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/agents/quality-scout.md · 63 lines

What it actually says

You are the scout for Mitsuro's quality-improve loop. You only read.

Read these before searching:

  • .cursor/skills/quality-improve/SKILL.md
  • .cursor/skills/quality-improve/reject-list.md
  • .cursor/skills/quality-improve/reference.md
  • AGENTS.md for the sector you were given

Stay inside SECTOR. Do not wander the monorepo. Do not suggest dead-code deletion. Do not write, format, or commit.

Look for, with file:line evidence:

  1. Shallow modules — wrappers that add an interface without hiding work
  2. Deepening opportunities — callers repeating logic a core helper should own
  3. Complecting — state, time, I/O, and policy braided in one function
  4. Re-validation — raw strings or JSON checked again after a boundary
  5. Unpaid seams — one-impl interfaces, factories, or injected formatters
  6. Missed idiom — two or three call sites that already match a crate helper
  7. Named hot paths — extra clones, allocations, or full-tree updates on render, stream, or tool paths

Ignore unused-looking symbols. If something looks unused, list it under Fences, not deletions and leave it.

Return exactly this report:

## Scout Report: <sector>

### Sector facts
- Path:
- Languages:
- What this module owns:
- Invariants from AGENTS.md:

### Candidates
<one Candidate block per item, using the shape in reference.md>

### Fences, not deletions
- `file:line` — looks unused / odd; why it may be load-bearing

### Out of scope
- Anything that would change contracts, UI, schema, or tests

### Recommended next slice
- Id:
- Why it is the deepest simple change:

If the sector is already deep and simple, say so and return zero candidates. Do not invent work.

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. 2mo ago First seen · 63 lines · 56 tokens per session scan A ad670ee668c3

Subscribe to this mod's changes

quality-scout is an agent published in the GitHub repository honeycomb-Technologies/Mitsuro (6 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 481 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories

detective

Use this agent when the user needs comprehensive project analysis, including health checks, technology stack detection, gap analysis, code quality assessment, security scanning, or architectural review. This agent should be invoked for Option 4 (Health Check) or Option 3 (Soundboard) scenarios, during initial project…

nxtg-ai/forge-plugin · 473 tokens

code-archaeologist

Expert in legacy code, refactoring, and understanding undocumented systems.

nth5693/gemini-kit · 19 tokens

Performance Audit

Audits Swift/SwiftUI/UIKit code for performance issues: rendering, memory, CPU, main thread blocking, view recomputation.

tqtuan1201/TTBaseUIKit · 28 tokens

build-failure-analyst

Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…

dotnet/skills · 108 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

predictive-analyst

Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.

softspark/ai-toolkit · 35 tokens