slope-review-loop

slope-review-loop is a cursor rule for coding agents from srbryers/slope. It costs 9 tokens per session (234 once invoked), scanned A, original, MIT.

A review process for checking sprint plans in several levels of detail before implementation begins.

In plain words
What is it for?
Use the light, standard, or deep review level based on the number of tickets and the size of architectural, package, schema, or API changes.
Why use it?
It helps catch duplicated infrastructure, incorrect dependencies, missing scope, and plans that do not fit the project’s existing patterns.

Cursor rule

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/srbryers/slope/slope-review-loop
Clone the repo
git clone --depth 1 https://github.com/srbryers/slope

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 slope-review-loop

README.md
[![agentmods](https://agentmods.dev/badge/rules/srbryers/slope/slope-review-loop.svg)](https://agentmods.dev/rules/srbryers/slope/slope-review-loop)
Your own site
<a href="https://agentmods.dev/rules/srbryers/slope/slope-review-loop"><img src="https://agentmods.dev/badge/rules/srbryers/slope/slope-review-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 234 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 $0.00009 $0.00234
Opus 5 $0.00005 $0.00117
Sonnet 5 $0.00002 $0.00047
Haiku 4.5 $0.00001 $0.00023

Measured 3d ago against content hash 0850d14e807d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slope-review-loop 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.

templates/cursor/rules/slope-review-loop.mdc · 34 lines

What it actually says

Sprint Plan Review Loop

After creating a sprint plan, run a structured review.

Review Tier Selection

Tier Rounds When to use
Skip 0 Research, infra, or docs-only sprints
Light 1 1-2 tickets, familiar patterns, single-package
Standard 2 3-4 tickets, multi-package, or schema/API changes
Deep 3 5+ tickets, new infrastructure, architectural changes

Round 1 — Deep Review

  • Does the plan duplicate existing infrastructure?
  • Are dependencies correct and ordering optimal?
  • Does the approach match codebase patterns?
  • Are there scope gaps or underscoped complexity?

Round 2 — Delta Review (Standard+)

Review only what changed since Round 1.

Round 3 — Final Sign-off (Deep only)

Delta review of Round 2 changes. Expected outcome: approval with minor notes.

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 · 34 lines · 9 tokens per session scan A 0850d14e807d

Subscribe to this mod's changes

slope-review-loop is a cursor rule published in the GitHub repository srbryers/slope (6 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 234 once invoked, about $0.0000 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.