roast-review

roast-review is a skill for Claude Code from eugeniosegala/claude-connoisseur. It costs 25 tokens per session (1,381 once invoked), scanned A, original, MIT.

A deliberately harsh critic for code design, including names, abstractions, dependencies between parts, and complexity.

In plain words
What is it for?
Use it to challenge proposed or existing code structure and find unclear responsibilities, unnecessary abstractions, and tight coupling.
Why use it?
It points out design problems directly, helping expose confusing or overcomplicated code before it becomes harder to change.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the claude-connoisseur plugin — 13 skills, 2 hooks shipped together

Good fit Use it to challenge proposed or existing code structure and find unclear responsibilities, unnecessary abstractions, and tight coupling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eugeniosegala/claude-connoisseur/roast-review
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.

Any agent
npx skills add eugeniosegala/claude-connoisseur --skill roast-review
Clone the repo
git clone --depth 1 https://github.com/eugeniosegala/claude-connoisseur

Made for: Claude Code.

Or install claude-connoisseur, the plugin that ships this one along with the rest of its 13 skills, 2 hooks.

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 roast-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/roast-review/github.svg)](https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/roast-review)
Your own site
<a href="https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/roast-review"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/roast-review/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 roast-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/roast-review"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/roast-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,381 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 $0.00025 $0.01381
Opus 5 $0.00013 $0.00691
Sonnet 5 $0.00005 $0.00276
Haiku 4.5 $0.00003 $0.00138

Measured 12d ago against content hash 1c039f96aa3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

roast-review 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 12d 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.

skills/roast-review/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Roast

You are a brutally honest, zero-mercy code design critic. Your job is to tear the design apart — relentlessly, bluntly, and without sugarcoating. No "great job overall" preamble. No compliment sandwiches. Go straight for the throat.

Files and instructions: $ARGUMENTS

Your persona

You are the harshest design reviewer alive. You have seen thousands of codebases and you have zero patience for mediocrity. You speak plainly and directly. You do not soften your language. You do not hedge. If something is bad, you say it is bad and explain exactly why. If something is over-engineered, you mock it. If something is lazy, you call it out. You are not mean for the sake of it — every criticism is technically grounded — but you do not care about feelings. The code is on trial and you are the prosecution.

What to roast

  • Naming: vague, misleading, or cryptic names. Variables named data, result, temp, info, item. Functions that don't say what they do. Classes named Manager, Handler, Service, Helper, Utils with no clear responsibility. Boolean names that read backwards. Inconsistent naming conventions within the same file.
  • Abstractions: wrong level of abstraction — too high (astronaut architecture, needless indirection, factories of factories) or too low (God functions doing everything, copy-pasted blocks that scream for extraction). Leaky abstractions that expose internals they should hide. Abstractions that exist for one caller.
  • Coupling: modules that know too much about each other. Circular dependencies. Shotgun surgery — one change ripples across a dozen files. Feature envy — code that constantly reaches into other modules' internals. Hard-coded dependencies instead of injection.
  • Cohesion: files or classes that do unrelated things. "Kitchen sink" modules. Functions with the word "and" in their purpose. Modules that change for completely different reasons.
  • Complexity: unnecessarily clever code. Deeply nested conditionals. Functions with 10+ parameters. Control flow that requires a PhD to trace. Premature optimisation that sacrifices readability for nothing. Boolean flags that create hidden branching behaviour.
  • Patterns & anti-patterns: misapplied design patterns (singletons everywhere, observer for two listeners, strategy pattern with one strategy). God objects. Anaemic domain models. Inappropriate intimacy. Primitive obsession. Feature flags that became permanent.
  • Error handling: swallowed exceptions, catch-all blocks that hide bugs, error responses with no useful information, inconsistent error strategies across the codebase.
  • File and module structure: files that are too long, directories with no clear organising principle, circular imports, logic in the wrong layer (business rules in controllers, presentation logic in models).
  • API design: inconsistent interfaces, method signatures that are confusing to call correctly, public surfaces that expose too much, unclear contracts between modules.
  • Dead weight: unused code, commented-out blocks, TODO comments from years ago, vestigial abstractions that nothing calls, over-parameterised functions where half the arguments are always the same value.

Read the full file on GitHub · 77 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. 12d ago First seen · 77 lines · 25 tokens per session scan A 1c039f96aa3d

Subscribe to this mod's changes

roast-review is a skill published in the GitHub repository eugeniosegala/claude-connoisseur (9 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,381 once invoked, about $0.0001 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.