mr-review

mr-review is a skill for Claude Code, Codex from vmkteam/claude-plugins. It costs 50 tokens per session (1,673 once invoked), scanned A, original, MIT.

A workflow for reviewing someone else’s GitLab Merge Request, which is a proposed set of code changes, and publishing comments directly on the changed lines. It fetches the request, examines its code and existing discussions, then pauses for approval before publishing.

In plain words
What is it for?
Use it to review a GitLab Merge Request, with optional focus on security or performance, and publish inline review threads.
Why use it?
It gathers the relevant code and history and helps place review findings where developers can act on them.

Skill for Claude CodeCodex

Part of the vmkteam-developer plugin — 35 skills shipped together

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.

agentmods
npx agentmods add skills/vmkteam/claude-plugins/mr-review
Any agent
npx skills add vmkteam/claude-plugins --skill mr-review
Clone the repo
git clone --depth 1 https://github.com/vmkteam/claude-plugins

Made for: Claude Code, Codex.

Or install vmkteam-developer, the plugin that ships this one along with the rest of its 35 skills.

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 mr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/vmkteam/claude-plugins/mr-review.svg)](https://agentmods.dev/skills/vmkteam/claude-plugins/mr-review)
Your own site
<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/mr-review"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/mr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.01673
Opus 5 $0.00025 $0.00837
Sonnet 5 $0.00010 $0.00335
Haiku 4.5 $0.00005 $0.00167

Measured 5d ago against content hash 3996c192920f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mr-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 5d 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.

plugins/developer/skills/mr-review/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MR Review — ревью чужого Merge Request

Полный цикл code review для MR в GitLab: получить diff, проанализировать код, опубликовать замечания как inline threads.

Подключения из .claude/memory/project-index.md и ~/.claude/memory/infra-{group}.md.

Использование

/mr-review 42
/mr-review 42 --focus security
/mr-review 42 --focus performance

Flow

FETCH MR → READ CODE → REVIEW → SUMMARY → ⏸ HITL → PUBLISH

1. FETCH — получить MR

# Детали MR (title, description, author, source/target branch, diff_refs)
pcurl @{gl_profile} 'https://{gl_host}/api/v4/projects/{gl_project_id}/merge_requests/{mr_iid}' -s

# Diff (список изменённых файлов с содержимым)
pcurl @{gl_profile} 'https://{gl_host}/api/v4/projects/{gl_project_id}/merge_requests/{mr_iid}/changes' -s

# Коммиты MR
pcurl @{gl_profile} 'https://{gl_host}/api/v4/projects/{gl_project_id}/merge_requests/{mr_iid}/commits' -s

# Существующие discussions (чтобы не дублировать замечания)
pcurl @{gl_profile} 'https://{gl_host}/api/v4/projects/{gl_project_id}/merge_requests/{mr_iid}/discussions?per_page=100' -s

Извлечь:

  • diff_refs (base_sha, start_sha, head_sha) — нужны для inline comments
  • Список изменённых файлов и их diff
  • Описание MR и связанную задачу (из title или description)
  • Уже существующие замечания (не дублировать)

2. READ CODE — прочитать контекст

Для каждого изменённого файла:

  • Прочитать полный файл локально (не только diff) — для понимания контекста
  • Если ветка MR доступна локально — git fetch origin && git checkout {source_branch}
  • Если нет — читать через API или анализировать diff as-is

Дополнительно:

  • Прочитать связанную задачу из YouTrack (если ID в title/description)
  • Понять что должен делать MR — сравнить intent с реализацией

3. REVIEW — анализ кода

Запустить /go-review на изменения MR — 6 ревьюеров:

  1. Common — соответствие задаче, полнота
  2. Architecture (Dave Cheney) — структура, зависимости
  3. Code (Rob Pike) — простота, читаемость
  4. Security (Filippo Valsorda) — уязвимости, authz
  5. Tests (Mitchell Hashimoto) — покрытие, качество тестов
  6. Operability (Peter Bourgon) — логирование, метрики, graceful degradation

Read the full file on GitHub · 175 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. 5d ago First seen · 175 lines · 50 tokens per session scan A 3996c192920f

Subscribe to this mod's changes

mr-review is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,673 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens