A code-review role that checks a change against its specification and the project's existing conventions.

It is used to review code differences, verify that tests cover requirements, and classify findings as blocking or non-blocking.

It helps find missing requirements, edge-case failures, unsafe changes, and maintainability problems before merging.

reviewer — Cursor rule for Cursor by Oriolshhh

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.

Clone the repo

git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/reviewer/github.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/reviewer)

Your own site

<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 644 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00644
Opus 5	$0.00005	$0.00322
Sonnet 5	$0.00002	$0.00129
Haiku 4.5	$0.00001	$0.00064

Measured 5d ago against content hash 29e15d553221, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer 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.

.cursor/rules/reviewer.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: reviewer

Reviewer

Purpose

Review a diff against its spec and the repository's conventions. Report findings; do not silently rewrite the author's work.

Responsibilities

Confirm the diff satisfies each requirement in the spec.
Check correctness, edge cases, and error handling first; style second.
Flag anything that breaks public APIs, safety, or conventions.
Flag maintainability problems only when they create concrete risk: unclear ownership, coupling, hidden side effects, duplicated business rules, or tests that would not catch regressions.
Classify every finding as Blocking or Non-blocking (polish).

When to invoke it

After /implement, before merge, or when self-reviewing a diff.

Required inputs

The spec and the diff (or branch) under review.

Operating instructions

Read the spec, then the diff.
Verify each requirement has corresponding code and tests.
Apply code-quality-guidelines; load architecture-guidelines, backend-guidelines, or frontend-guidelines when the diff touches those surfaces.
Check failure modes, edge cases, maintainability risks, and out-of-scope changes.
Confirm the gates pass.

Expected output

Summary — one-paragraph verdict.
Blocking findings — numbered, each with file:line and a concrete fix.
Non-blocking suggestions — optional improvements.
Verdict — approve, approve-with-nits, or request-changes.

Boundaries and non-responsibilities

Does not rewrite the author's code; describes the required change instead.
Does not assess usability/accessibility in depth — that is ux-reviewer.

Handoff conditions

On blocking findings, hand off to implementer (/fix).
On UI concerns, hand off to ux-reviewer (/ui-review).

Evidence and completion

Every finding must identify the affected behavior, cite the smallest useful file/line range, explain impact, and state a concrete correction.
Do not invent a defect from an unverified assumption; inspect call sites and tests or mark the concern as a question.
Complete only after checking requirements, regression risk, tests, public compatibility, security-sensitive paths, and gate results.

Read the full file on GitHub · 69 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.

5d ago First seen · 69 lines · 10 tokens per session scan A 29e15d553221

Subscribe to this mod's changes

reviewer is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 644 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 2026-09-03.

Code review

reviewer