review-mr

review-mr is a skill for Claude Code from sleeyax/promptfiles. It costs 43 tokens per session (2,748 once invoked), scanned A, original, MIT.

A GitLab-only workflow for reviewing a merge request, a proposed set of changes, and leaving findings as unpublished draft notes.

In plain words
What is it for?
Use it when given a GitLab merge-request URL and asked to perform a senior-level review; GitHub requests are not supported.
Why use it?
It organizes the review process and keeps comments from being published or repository changes being made without confirmation.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

Part of the sleeyax-skills plugin — 17 skills, 2 agents shipped together

Good fit Use it when given a GitLab merge-request URL and asked to perform a senior-level review; GitHub requests are not supported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sleeyax/promptfiles/review-mr
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 sleeyax/promptfiles --skill review-mr
Clone the repo
git clone --depth 1 https://github.com/sleeyax/promptfiles

Made for: Claude Code.

Or install sleeyax-skills, the plugin that ships this one along with the rest of its 17 skills, 2 agents.

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 review-mr

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sleeyax/promptfiles/review-mr"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/review-mr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,748 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 $0.00043 $0.02748
Opus 5 $0.00022 $0.01374
Sonnet 5 $0.00009 $0.00550
Haiku 4.5 $0.00004 $0.00275

Measured 10d ago against content hash 029fa4e8a23a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-mr 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.

The scan reads SKILL.md. This mod also ships 1 executable file (post-draft-note.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/review/review-mr/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a Merge Request

MR: $ARGUMENTS

Review a GitLab MR like a senior engineer on the team and post findings as draft notes so the user publishes/discards manually.

This skill fetches the MR's context and places the comments. The reviewing itself is delegated to the review-changes skill in report-only mode, which picks the reviewers (two agents by default), runs them, and returns one merged, deduplicated set of findings.

Hard rules

  • Never publish draft notes — leave them for the user.
  • Every gate — dirty-tree, no-checkout, diff-size, pre-submission — is a real stop: ask, then wait for the answer. Use the AskUserQuestion tool when it's available in the session; where it isn't (e.g. Codex), ask in plain text with the same numbered options and stop until the user replies. Never assume an answer.
  • Never push, commit, or modify the cwd repo's working tree without an explicit confirm.
  • Every finding cites a real + (added) line in the actual diff. Removed-line comments are out of scope.
  • Posting is gated by exactly one explicit confirm covering the whole batch.
  • Don't review the diff here. Delegate to review-changes and work from the findings it returns; the only exception is diff-only mode, where that skill can't run — and the user has to pick it at the step 5 gate.
  • One defect is one draft note. review-changes merges and deduplicates before returning — never re-split a merged finding, and never post the same defect twice because both agents found it.
  • The agent writes exactly one findings.json per run (matching findings.schema.json) and invokes post-draft-note.sh exactly once. No per-finding shell calls. Rollback on partial failure is the helper's job.
  • GitLab MCP server first if available; fall back to glab. If neither, stop.
  • Never dump the full diff to a file or to chat, or hand it to a subagent as one blob. When the cwd repo matches the MR, read the diff incrementally from git (per-file, on demand) — not from glab api .../diffs. The API diffs endpoint is only used when there is no local checkout, and even then read it page-by-page, one file at a time, never as one bulk write. To measure size up front, use /merge_requests/<iid>/changes (metadata + per-file stats), not /diffs. This rule still holds when the user picks Review whole diff anyway — that answer authorizes the scope, not bulk-dumping.

Read the full file on GitHub · 171 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 171 lines · 43 tokens per session scan A 029fa4e8a23a

Subscribe to this mod's changes

review-mr is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 11d ago), licensed MIT. It adds 43 tokens to every session and 2,748 once invoked, about $0.0002 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.