review-change

review-change is a cursor rule for Cursor from kunalsuri/ai-fication-kit. It costs 29 tokens per session (405 once invoked), scanned A, original, Apache-2.0.

A written checklist for reviewing a completed code change against the document that requested it. It is intended for a reviewer who did not implement the change, so the review is based on fresh evidence.

In plain words
What is it for?
Checking the exact files changed, matching the implementation to its specification, rerunning named tests, checking project conventions and documentation, and recording findings by severity with a merge recommendation.
Why use it?
It reduces the chance that the original developer overlooks problems or confirms their own assumptions. It gives the human deciding whether to merge the change a record of what was checked and found.

Cursor rule for Cursor

Written for Cursor: installed under .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/kunalsuri/ai-fication-kit/review-change
Clone the repo
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kit

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-change

README.md
[![agentmods](https://agentmods.dev/badge/rules/kunalsuri/ai-fication-kit/review-change.svg)](https://agentmods.dev/rules/kunalsuri/ai-fication-kit/review-change)
Your own site
<a href="https://agentmods.dev/rules/kunalsuri/ai-fication-kit/review-change"><img src="https://agentmods.dev/badge/rules/kunalsuri/ai-fication-kit/review-change.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 405 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 5.1 $0.00029 $0.00405
Opus 5 $0.00015 $0.00202
Sonnet 5 $0.00006 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured 6d ago against content hash e80a2a73ac93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-change 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/review-change.mdc · 29 lines

What it actually says

Review a completed change against its spec. Run this in a session that did NOT implement the change — a reviewer sharing the implementer's context inherits the implementer's blind spots.

  1. Pin the scope. Identify the exact diff (commits / branch / files) and the spec or bugfix doc in ai/lab/specs/ that authorized it. No spec ⇒ that is finding #1, severity blocker: unspecced work.
  2. Copy the template. ai/lab/reviews/REVIEW_TEMPLATE.mdai/lab/reviews/REVIEW_<work-id>.md.
  3. Check with evidence, not assertions. For each check in the template — spec conformance, surgical diff, Stability respected, tests, conventions, knowledge updated, provenance clean — record where you looked and what you saw. Re-run the suites the spec names; do not trust the implementer's report.
  4. File findings by severity. Any blocker or major ⇒ verdict request-changes and hand the list back to the implementer. Minor/nit findings can ship with notes.
  5. Verdict and hand-off. Fill "what the human should double-check" — the judgement calls a mechanical check cannot make. The review itself is [inferred]; the human's merge decision is the real approval, and this document is its evidence.
  6. Record. Link the review from the work's row in ai/lab/WORKLOG.md (Review column) and set that row's Status to in-review.
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 · 29 lines · 29 tokens per session scan A e80a2a73ac93

Subscribe to this mod's changes

review-change is a cursor rule published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 405 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.