code-review-agents

code-review-agents is a cursor rule for Cursor from Axcient/public-gateway-mcp. It costs 232 tokens per session, scanned A, original, Apache-2.0.

Rules for code reviews requiring reviewers to read and enforce AGENTS.md, the repository’s coding instructions.

In plain words
What is it for?
Reviewing changed code for compliance with MCP, OpenAPI, testing, naming, cleanup, and command-use requirements.
Why use it?
They make repository-specific violations visible during review, even when automated checks pass.

Cursor rule for Cursor

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 rules/axcient/public-gateway-mcp/code-review-agents
Clone the repo
git clone --depth 1 https://github.com/Axcient/public-gateway-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.

agentmods badge for code-review-agents

README.md
[![agentmods](https://agentmods.dev/badge/rules/axcient/public-gateway-mcp/code-review-agents.svg)](https://agentmods.dev/rules/axcient/public-gateway-mcp/code-review-agents)
Your own site
<a href="https://agentmods.dev/rules/axcient/public-gateway-mcp/code-review-agents"><img src="https://agentmods.dev/badge/rules/axcient/public-gateway-mcp/code-review-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 232 This file is loaded in full into every session.
When invoked 232 The same file — it is already loaded in full.
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 $0.00232 $0.00232
Opus 5 $0.00116 $0.00116
Sonnet 5 $0.00046 $0.00046
Haiku 4.5 $0.00023 $0.00023

Measured 3d ago against content hash 5d807e1478dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-agents 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 3d 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/code-review-agents.mdc · 22 lines

What it actually says

Code reviews enforce AGENTS.md

Whenever you run or delegate a code review (including the code-reviewer subagent / Task tool, /code-reviewer, or the stop-hook review loop):

  1. Read the full current AGENTS.md from disk before judging the diff. Do not rely on memory or a partial summary.
  2. Enforce every applicable AGENTS.md rule on the change-set (MCP server globals, OpenAPI docs passed unchanged, one httpx client per mount, no BaseException, no mocking, full-object asserts, naming, just tooling, etc.).
  3. Treat AGENTS.md violations as High / blocking unless clearly stylistic.
  4. Tell the reviewer (in the Task prompt) to read AGENTS.md first and to confirm AGENTS.md reviewed: yes in its report.
  5. just check-all does not replace this — tooling does not enforce AGENTS.md conventions.
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. 3d ago First seen · 22 lines · 232 tokens per session scan A 5d807e1478dc

Subscribe to this mod's changes

code-review-agents is a cursor rule published in the GitHub repository Axcient/public-gateway-mcp (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 232 tokens to every session, about $0.0012 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 2026-09-01.