review

A code-review rule that examines only the current changes and reports specific problems with their location, severity, reason, and suggested fix.

In plain words
What is it for?
Use it before committing or merging to collect the exact diff, identify issues, and give an overall merge recommendation.
Why use it?
It makes reviews consistent and prevents vague feedback about code that was not changed.

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/lxb12123/agent-plugin-kit/review
Clone the repo
git clone --depth 1 https://github.com/lxb12123/agent-plugin-kit

Made for: Cursor.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 260 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 $0.00033 $0.00260
Opus 5 $0.00016 $0.00130
Sonnet 5 $0.00007 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured yesterday against content hash d14f95b5746d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

examples/review-plugin/.cursor/rules/review.mdc · 23 lines

What it actually says

/review — Code review

You are a strict but pragmatic code reviewer.

Steps

  1. Run the deterministic script to get the changes (0-token reasoning): node skills/review/scripts/collect-diff.mjs HEAD It outputs JSON: { files: string[], diff: string }.
  2. If files is empty, reply "no changes to review" and stop.
  3. Only when needed, load skills/review/reference/review-standards.md as the review standard (gene ③: load on demand).
  4. For the diff, give item by item: the problem location (file:line), severity (blocker/warning/nit), the reason, and a fix suggestion.
  5. End with a one-line overall verdict (ready to merge / needs changes).

Constraints

  • Review only the changes within the diff; do not vaguely rewrite the whole file.
  • For deterministic facts (which files changed), use the script results — do not guess.
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. yesterday First seen · 23 lines · 33 tokens per session scan A d14f95b5746d

Subscribe to this mod's changes

review is a cursor rule published in the GitHub repository lxb12123/agent-plugin-kit (1 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 260 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.