rafter-code-review

rafter-code-review is a cursor rule for Cursor from Raftersecurity/rafter-cli. It costs 83 tokens per session (246 once invoked), scanned A, original, MIT.

A required security review rule for changes involving areas such as user input, SQL, shell commands, authentication, credentials, file paths, serialization, or dependencies. It uses security questions from OWASP, ASVS, and MITRE, which are established security guidance and threat frameworks.

In plain words
What is it for?
Use it before marking security-sensitive work done, alongside the required rafter scan, to review web, API, AI, command-line, library, and infrastructure changes.
Why use it?
Compilers and ordinary tests may miss unsafe design choices or attack paths. The review is paired with a security scanner so both reasoning-based checks and known-pattern checks are performed before completion.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: reads .claude/ paths.

Good fit Use it before marking security-sensitive work done, alongside the required rafter scan…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/raftersecurity/rafter-cli/rafter-code-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/Raftersecurity/rafter-cli

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 rafter-code-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/raftersecurity/rafter-cli/rafter-code-review.svg)](https://agentmods.dev/rules/raftersecurity/rafter-cli/rafter-code-review)
Your own site
<a href="https://agentmods.dev/rules/raftersecurity/rafter-cli/rafter-code-review"><img src="https://agentmods.dev/badge/rules/raftersecurity/rafter-cli/rafter-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 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 $0.00083 $0.00246
Opus 5 $0.00042 $0.00123
Sonnet 5 $0.00017 $0.00049
Haiku 4.5 $0.00008 $0.00025

Measured yesterday against content hash c9bb381c63cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

rafter-code-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.

node/resources/cursor-rules/rafter-code-review.mdc · 15 lines

What it actually says

rafter-code-review — structured pre-merge review

Pointer rule. Use the rafter-code-review skill at .claude/skills/rafter-code-review/SKILL.md BEFORE declaring done on any diff touching the surface listed above.

  • Read the matching sub-doc (web-app / api / llm / cli-library-iac).
  • Walk the OWASP / ASVS / MITRE questions the scanner can't ask.
  • Pair with rafter run on the same diff — the scanner finds known-bad patterns, this skill asks the questions patterns miss.

A security-relevant task marked complete without BOTH the skill walkthrough and a rafter run pass has been under-delivered. Do not claim done until both are recorded.

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 · 15 lines · 83 tokens per session scan A c9bb381c63cf

Subscribe to this mod's changes

rafter-code-review is a cursor rule published in the GitHub repository Raftersecurity/rafter-cli (27 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 246 once invoked, about $0.0004 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 2026-09-04.