rossum-agents: Command for Claude Code

.claude/commands/ds-roast.md

ds-roast is a command for Claude Code from rossumai/rossum-agents. It costs 0 tokens per session (486 once invoked), scanned A, original, MIT.

A blunt code-review command that examines uncommitted changes or selected commits and lists flaws in the implementation.

In plain words
What is it for?
Use it for an intentionally direct review of code quality, maintainability, test coverage, and accuracy of project documentation.
Why use it?
It draws attention to dead code, repetition, confusing names, unnecessary complexity, missing tests, and documentation that does not match the code.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is rossumai/rossum-agents's own configuration. It tells Claude Code how to work on rossum-agents 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 rossum-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rossumai/rossum-agents. 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/rossumai/rossum-agents/master/.claude/commands/ds-roast.md
Clone the repo
git clone --depth 1 https://github.com/rossumai/rossum-agents

Made for: Claude Code.

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 ds-roast

README.md
[![agentmods](https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-roast/github.svg)](https://agentmods.dev/commands/rossumai/rossum-agents/ds-roast)
Your own site
<a href="https://agentmods.dev/commands/rossumai/rossum-agents/ds-roast"><img src="https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-roast/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 ds-roast

Your own site · 80×15
<a href="https://agentmods.dev/commands/rossumai/rossum-agents/ds-roast"><img src="https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-roast.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 486 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 $0.00000 $0.00486
Opus 5 $0.00000 $0.00243
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured 9d ago against content hash 870ec6a4f9da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ds-roast 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.

.claude/commands/ds-roast.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roast Code Changes

Goal: Brutally honest code review. No bullshit. Find every flaw and tear it apart.

Scope

Context What to Review
No argument Uncommitted changes; if none, roast last commit
Commit provided The specified commit(s)

Roast Checklist

Category What to Call Out
Dead code Imports going nowhere, variables collecting dust, zombie branches that will never execute
Copy-paste crap Same damn logic repeated because someone couldn't be arsed to make a function
AI slop Over-engineered try/catch, paranoid null checks, Any plastered everywhere, code that screams "I have no clue what I'm doing"
Naming disasters Variables named x, data, temp, or other lazy garbage requiring telepathy to understand
Complexity hell 50-line monstrosities, nested ifs deep enough to get lost in, "clever" one-liners that make everyone's life miserable
Missing tests New code with zero test coverage - because who needs confidence, right?
Documentation lies README is full of shit, says one thing while code does another

Approach

Step Action
Analyze Review diff with maximum skepticism - assume nothing works
Roast For each issue, explain why it sucks in plain terms
Severity Rate issues: "meh", "this is bad", or "what the hell is this"
Redemption After tearing it apart, explain how to unfuck it
Summary End with overall verdict and whether this belongs in the codebase

Tone Guidelines

  • Be brutally honest, swear where it adds emphasis
  • Assume the author has thick skin and wants real feedback
  • Humor is encouraged, cruelty is not
  • Every criticism must include how to fix the mess
  • If something is actually good, say so (don't be a complete asshole)

Output

End with a verdict:

## Verdict: <Shipit / Needs Work / Burn It>

<1-2 sentence summary of what's wrong or why it's acceptable>

Read the full file on GitHub · 57 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. 9d ago First seen · 57 lines · 0 tokens per session scan A 870ec6a4f9da

Subscribe to this mod's changes

ds-roast is a command published in the GitHub repository rossumai/rossum-agents (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 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 2026-08-30.