review-gate-v2

review-gate-v2 is a cursor rule for Cursor from zlcggb/Review-Gate-win11-chinese. It costs 1,519 tokens per session, scanned A, original, MIT.

A set of review rules requiring a review checkpoint before an agent finishes a response. The checkpoint opens an interactive review chat for user feedback.

In plain words
What is it for?
Use it in workflows that require every response to include the specified checkpoint and call the review-gate chat tool.
Why use it?
It adds a required human review step to the response process and prevents the task from being treated as complete before that step is performed.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it in workflows that require every response to include the specified checkpoint and call the review-gate chat tool.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/zlcggb/review-gate-win11-chinese/review-gate-v2
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/zlcggb/Review-Gate-win11-chinese

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.

agentmods badge for review-gate-v2

README.md
[![agentmods](https://agentmods.dev/badge/rules/zlcggb/review-gate-win11-chinese/review-gate-v2/github.svg)](https://agentmods.dev/rules/zlcggb/review-gate-win11-chinese/review-gate-v2)
Your own site
<a href="https://agentmods.dev/rules/zlcggb/review-gate-win11-chinese/review-gate-v2"><img src="https://agentmods.dev/badge/rules/zlcggb/review-gate-win11-chinese/review-gate-v2/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-gate-v2

Your own site · 80×15
<a href="https://agentmods.dev/rules/zlcggb/review-gate-win11-chinese/review-gate-v2"><img src="https://agentmods.dev/badge/rules/zlcggb/review-gate-win11-chinese/review-gate-v2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,519 This file is loaded in full into every session.
When invoked 1,519 The same file — it is already loaded in full.
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 $0.01519 $0.01519
Opus 5 $0.00759 $0.00759
Sonnet 5 $0.00304 $0.00304
Haiku 4.5 $0.00152 $0.00152

Measured 12d ago against content hash 001779bfefa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-gate-v2 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 12d 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.

review-gate-v2.mdc · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY CHECKPOINT (Must be included in every response):

Before ending any response, I MUST:

  1. State: "CHECKPOINT: Transitioning to Review Gate V2"
  2. Immediately call review_gate_chat tool
  3. Never provide a response without this checkpoint

ENFORCEMENT MECHANISM:

If I provide any response without calling review_gate_chat, treat it as an incomplete response that violates the protocol.

AI Agent Protocol: Review Gate V2 - MCP Integration (Version 2)

0. User Advisory & Safety:

This is an advanced rule that leverages the Review Gate V2 MCP (Model Context Protocol) server to facilitate interactive review sessions. The system uses a popup interface in Cursor that supports text input, image uploads, and speech-to-text functionality. By using this rule, you acknowledge that the AI will call MCP tools to open interactive dialogs for user feedback.

1. Core Principle & Context:

Your primary task processing includes a mandatory final interactive review stage driven by user input through the Review Gate V2 MCP tool (review_gate_chat). You are NOT to consider your overall task complete until this review stage explicitly signals completion. This protocol leverages the MCP server's ability to open popup dialogs in Cursor and capture user responses.

Phase 1: Primary Task Execution

  1. Address the user's main request as you normally would: perform analysis, make code changes, call tools, and run applications/tests in sub-terminals if the main task requires it.
    • Application Execution Confirmation: Before attempting to run an entire application (e.g., a web server, a full front-end build, a long-running background process), you MUST ask the user for explicit confirmation. For example: "I am about to run the [application name/command]. Is it okay to proceed, or is it possibly already running?"
    • This confirmation is NOT required for running individual test scripts, linters, build tools for specific components, or other non-application-level commands necessary for task completion.
    • If the user indicates an application is already running or denies permission, adapt your strategy accordingly (e.g., focus on tests or specific file executions).
  2. Leverage your ability to read outputs/errors from these sub-terminals to make iterative fixes during this primary phase.

Read the full file on GitHub · 78 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. 12d ago First seen · 78 lines · 1,519 tokens per session scan A 001779bfefa4

Subscribe to this mod's changes

review-gate-v2 is a cursor rule published in the GitHub repository zlcggb/Review-Gate-win11-chinese (6 stars, last pushed 1y ago), licensed MIT. It adds 1,519 tokens to every session, about $0.0076 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.