velith-editing

A five-stage editing process covering structure, content, sentence clarity, correctness, and final proofreading, with checks for artificial-sounding writing.

In plain words
What is it for?
Use it to revise books, articles, technical documents, or other text from an initial structural review through final proofreading.
Why use it?
It gives long-form writing a defined review sequence and helps identify repetitive or generic language.

Cursor rule for 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/epicsagas/velith/velith-editing
Clone the repo
git clone --depth 1 https://github.com/epicsagas/Velith

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 651 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 $0.00000 $0.00651
Opus 5 $0.00000 $0.00326
Sonnet 5 $0.00000 $0.00130
Haiku 4.5 $0.00000 $0.00065

Measured 2d ago against content hash 9e593e35475f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

velith-editing 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 2d 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/velith-editing.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Velith — Editing Pipeline and Style Conventions

5-Stage Editing Pipeline

Stage Focus What to check
1. Editorial Assessment Macro structure Chapter order, pacing, gap analysis, argument flow
2. Developmental Edit Flow and content Transitions, evidence quality, redundant sections, missing content
3. Line Edit Sentence-level clarity Word choice, sentence rhythm, paragraph flow, voice consistency
4. Copy Edit Grammar and consistency Grammar, punctuation, terminology consistency, formatting
5. Proofread Final polish Typos, spacing, formatting artifacts, cross-reference accuracy

AI-Slop Detection Patterns

These patterns indicate AI-generated text that reads as inauthentic. Flag and fix:

Excessive modifiers: revolutionary, game-changer, groundbreaking, cutting-edge, transformative, innovative, seamless, robust, comprehensive

Repetitive transitions: overuse of "however", "moreover", "furthermore", "additionally", "notably"

Generic conclusions: "in conclusion", "in summary", "ultimately", "at the end of the day", "it's important to note"

Weak hedging: "can be", "seems like", "it could be argued", "one might say", "arguably"

English AI markers: "delve", "tapestry", "landscape" (metaphorical), "nuanced", "multifaceted", "plethora", "myriad"

List overuse: 5+ consecutive bullet points without prose context

Style Drift Indicators

Quantitative signals that a chapter's style has drifted from the rest:

  • Sentence length variance — compare per-chapter average against book mean
  • Paragraph length distribution — flag chapters with significantly different patterns
  • Type-token ratio — vocabulary diversity should remain consistent
  • POV mixing — detect shifts between 1st/3rd person within chapters

Severity Classification

Level Criteria Action
Critical Breaks reader comprehension, factual error, POV violation Must fix before proceeding
Major Style drift, inconsistent tone, structural gap Should fix, flag for review
Minor Word choice, transition quality, formatting Nice to fix, batch at proofread stage

Read the full file on GitHub · 69 lines

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. 2d ago First seen · 69 lines · 0 tokens per session scan A 9e593e35475f

Subscribe to this mod's changes

velith-editing is a cursor rule published in the GitHub repository epicsagas/Velith (33 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 651 tokens. 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 2026-08-30.