change-review

change-review is a cursor rule for Cursor from IP-DZ/universal-change-review. It costs 11 tokens per session (220 once invoked), scanned A, original, MIT.

A rule set for reviewing Git changes with evidence from the Universal Change Review tools. Git is a system that records versions of files and the differences between them.

In plain words
What is it for?
Use it to compare changes with a task snapshot, inspect risky files, check correctness and tests, and report findings by severity with file and line references.
Why use it?
It prevents pre-existing edits from being confused with current work and highlights risks before implementation is declared complete.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to compare changes with a task snapshot, inspect risky files, check correctness and tests, and report findings by severity with file and line references.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/ip-dz/universal-change-review/change-review
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/IP-DZ/universal-change-review

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 change-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/ip-dz/universal-change-review/change-review.svg)](https://agentmods.dev/rules/ip-dz/universal-change-review/change-review)
Your own site
<a href="https://agentmods.dev/rules/ip-dz/universal-change-review/change-review"><img src="https://agentmods.dev/badge/rules/ip-dz/universal-change-review/change-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 220 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 $0.00011 $0.00220
Opus 5 $0.00005 $0.00110
Sonnet 5 $0.00002 $0.00044
Haiku 4.5 $0.00001 $0.00022

Measured 6d ago against content hash ca5d5d631e84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

change-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 6d 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/change-review.mdc · 20 lines

What it actually says

Before a substantial implementation, call changes_begin and retain the snapshot id. After editing, call changes_since so task changes are not confused with pre-existing work.

Before claiming completion:

  1. Call changes_summary.
  2. Inspect every behaviorally relevant or risky file with changes_diff. If output is truncated, inspect files individually.
  3. Check correctness, regressions, error paths, security, performance, compatibility, and missing tests as applicable.
  4. Report actionable findings first using P0-P3 severity and file/line evidence.
  5. Then summarize changed behavior, validation actually run, and remaining risks.

When the user asks to see or open Changes, call changes_open_panel and return its localhost URL. Use the panel for visual file-by-file inspection; continue to use changes_diff for evidence in the written review.

Do not modify files during a review unless the user asks for fixes. The MCP review tools are read-only for source files.

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. 6d ago First seen · 20 lines · 11 tokens per session scan A ca5d5d631e84

Subscribe to this mod's changes

change-review is a cursor rule published in the GitHub repository IP-DZ/universal-change-review (0 stars, last pushed 19d ago), licensed MIT. It adds 11 tokens to every session and 220 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 2026-08-31.