rossum-agents: Command for Claude Code

.claude/commands/ds-review.md

ds-review is a command for Claude Code from rossumai/rossum-agents. It costs 0 tokens per session (916 once invoked), scanned A, original, MIT.

A command that reviews uncommitted or selected committed code changes for quality, tests, documentation, compatibility, and tool-related issues.

In plain words
What is it for?
Use it to inspect a diff, check whether tests cover changes, verify public interfaces remain compatible, and produce a merge-ready summary.
Why use it?
It helps catch dead code, duplicated logic, missing tests, outdated documentation, and breaking API changes before a merge request is opened.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

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-review.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-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/rossumai/rossum-agents/ds-review"><img src="https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-review.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 916 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 $0.00916
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured 10d ago against content hash 8bcf09badba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ds-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 10d 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-review.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Code Changes

Goal: Review uncommitted changes for quality issues, ensure tests pass, and produce MR-ready summary.

Scope

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

Review Checklist

Category Check For
Unused code Dead imports, variables, unreachable branches
Duplication Repeated logic that should use shared components
AI slop Excessive try/catch, defensive checks in trusted paths, Any casts, style drift
Documentation Changes reflected in README.md and CLAUDE.md
Tests New features/bug fixes have tests; existing tests not deleted without cause
Breaking changes Public API or tool signatures changed without backward compatibility
Tools consolidation If tools were added, removed, or merged — see Tools Consolidation below
Opus prompts If rossum_agent/prompts/ or rossum_agent/skills/ changed — see Opus Prompt Guidelines below

Tools Consolidation

Apply when tools are added, removed, or merged in rossum_agent/tools/ or rossum_mcp/tools/:

Principle What to check
Efficiency Does the consolidation reduce token overhead, tool-call round trips, or redundant functionality?
SOTA alignment Is the tool design aligned with current state-of-the-art agentic patterns (e.g., fewer specialized tools vs. many narrow ones, proper use of structured outputs)?
Capability preservation No previously available functionality silently dropped without justification
Naming clarity Tool names and descriptions remain clear and discoverable by the agent

Opus Prompt Guidelines

Apply when reviewing changes to rossum_agent/prompts/ or rossum_agent/skills/:

Principle Violation to flag
Goals over procedures Step-by-step instructions where a single goal statement suffices
Constraints over explanations Prose explaining why a constraint exists instead of stating it directly
Tables for structure Prose lists that would be clearer as markdown tables
No redundancy Repeating information Opus can infer from context or earlier in the same prompt
Facts not warnings "IMPORTANT:", "Note:", "WARNING:" preambles — state the rule directly instead

Read the full file on GitHub · 109 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. 10d ago First seen · 109 lines · 0 tokens per session scan A 8bcf09badba1

Subscribe to this mod's changes

ds-review is a command published in the GitHub repository rossumai/rossum-agents (11 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 916 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.