avoid-cleavage-in-prose

A wording rule for technical prose. It prohibits one specific word and recommends clearer alternatives such as “split,” “boundary,” “distinction,” or “divide.”

In plain words
What is it for?
Use it when writing or reviewing docs, ADRs, specifications, plans, READMEs, pull-request descriptions, commit messages, and comments.
Why use it?
It avoids wording that may distract readers or carry an unintended meaning in documentation and code comments.

Cursor rule for Codex

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/prisma/prisma-next/avoid-cleavage-in-prose
Clone the repo
git clone --depth 1 https://github.com/prisma/prisma-next

Made for: Codex.

Per session 273 This file is loaded in full into every session.
When invoked 273 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00273 $0.00273
Opus 5 $0.00137 $0.00137
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00027 $0.00027

Measured 3d ago against content hash 8500c45a3972, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

avoid-cleavage-in-prose 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.

Origin

This is a copy

100% identical to avoid-cleavage-in-prose — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/rules/avoid-cleavage-in-prose.mdc · 20 lines

What it actually says

Avoid the word "cleavage" in prose

Don't use "cleavage" as a metaphor for a split, boundary, or division in any prose: docs, ADRs, specs, plans, READMEs, PR descriptions, commit messages, or code comments. The word is technically correct in the geological / structural sense but reads weirdly in technical writing because of its other common meaning, and the alternatives are clearer anyway.

Prefer the natural English alternative for the context:

Instead of Prefer
"the natural cleavage between X and Y" "the natural split between X and Y" / "the natural distinction between X and Y"
"the cleavage is precise:" "the split is precise:" / "the boundary is precise:"
"the cleavage between Project 1 and Project 2" "the boundary between Project 1 and Project 2"
"predicate / non-predicate cleavage" "predicate / non-predicate split"

Use whichever of "split", "boundary", "distinction", or "divide" reads most naturally in the surrounding sentence.

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 · 20 lines · 273 tokens per session scan A 8500c45a3972

Subscribe to this mod's changes

avoid-cleavage-in-prose is a cursor rule published in the GitHub repository prisma/prisma-next (420 stars, last pushed 8d ago), licensed Apache-2.0. It adds 273 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to avoid-cleavage-in-prose, differing in 0 lines, and is treated as a copy.