---
title: "prose-discipline"
description: "Engineering prose standard for everything an agent writes: user replies, prose, code comments, review comments, commit messages, change descriptions, error messages and agent instructions. Five layers, sentence structure"
canonical: https://agentpluginsdirectory.com/plugins/prose-discipline
last-updated: 2026-09-09
---

# prose-discipline
Engineering prose standard for everything an agent writes: user replies, prose, code comments, review comments, commit messages, change descriptions, error messages and agent instructions. Five layers, sentence structure, plain vocabulary, comment hygiene, artifact formats, slop pruning, each stated as a rule a reader can check rather than a preference. The core rules are one file, rules/prose-discipline.md, injected at session start by the hook in hooks/ on hosts that run plugin hooks, and loaded as an always-apply rule by hosts that read plugin rule files; the skill carries the protocol and the depth behind every rule, including the substitution table, the Conventional Comments labels and a calibration corpus. Code blocks, identifiers, commands, URLs and quoted text are never flagged, and established domain terms are kept. No credentials, no MCP servers, no settings files, and no checker script: enforcement is model judgement over rule texts a person can read and argue with.
- Slug: prose-discipline
- Publisher: Alexander Kurganov
- Repository: https://github.com/Akurganow/ai-plugins
- Manifest: plugins/prose-discipline/plugin.json
- Version: 1.3.0
- License: MIT
- Category (editorial): other
- Skills: 1 (prose-discipline)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-08-22
- Repository last pushed: 2026-09-08
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/prose-discipline
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What prose-discipline does, in the publisher's words

An engineering prose standard for everything an agent writes: user replies, prose, code comments, review comments, commit messages, change descriptions, error messages, and agent instructions.

Part of the ai-plugins marketplace.

Five layers, each a rule a reader can check rather than a preference:

- Structure: a 25-word sentence ceiling, one action per sentence or step, active voice, no noun stacks, semicolons split into sentences.
- Vocabulary: plain verbs, a substitution table, no significance inflation, and a domain-term contract that keeps accessible, accept, validate, rotate and robust where they name a technical property.
- Comment hygiene: no narrator comments, no step markers, no ASCII dividers, no committed uncertainty. Comments explain why; names explain what.
- Artifact formats: Conventional Comments labels on review feedback; change descriptions as what / why / verification; three-part error messages; single-intent instruction steps. A repository's own template outranks these formats.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/Akurganow/ai-plugins/HEAD/plugins/prose-discipline/README.md

## Skills

- prose-discipline: The prose standard for all agent-written output: user replies, prose, code comments, review comments, commit messages, change descriptions, error messages, and instructions. Use when writing or reviewing any of these, or when asked to apply or check the standard.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.