Agent Plugins Marketplace
← All plugins

prose-discipline

v1.3.0

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.

Claude CodeAgent Plugins1 Skill

By Alexander KurganovLicense: MIT1 GitHub starsUpdated 13 hours ago

Directory evidence

Runtimes
Claude Code and Agent Plugins
Parsed components
1 skill or MCP entry
Source updated
Sep 23, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install prose-discipline for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install prose-discipline@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Akurganow/ai-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/prose-discipline/.

Plugin files

plugins/prose-discipline/
├── .claude-plugin/plugin.json
├── plugin.json
└── skills/prose-discipline/SKILL.md

Included Skills1

prose-disciplineskills/prose-discipline/SKILL.md

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.

Plugin manifests2

plugins/prose-discipline/.claude-plugin/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "prose-discipline",
  "version": "1.3.0",
  "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, 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.",
  "author": {
    "name": "Alexander Kurganov",
    "url": "https://github.com/Akurganow"
  },
  "homepage": "https://github.com/Akurganow/ai-plugins/tree/main/plugins/prose-discipline",
  "repository": "https://github.com/Akurganow/ai-plugins",
  "license": "MIT",
  "keywords": [
    "prose",
    "writing",
    "style-guide",
    "anti-slop",
    "code-review",
    "conventional-comments",
    "commit-messages",
    "agent-skills"
  ],
  "extensions": {
    "io.github.akurganow.ai-plugins": {
      "components": {
        "skills": "./skills",
        "rules": "./rules/prose-discipline.md",
        "hooks": "./hooks/hooks.json"
      },
      "components_note": "Agent Plugins 1.0.0 fixes the location of skills at ./skills (§6.1) and assigns no meaning to anything else here. The rules file and the hook are the two surfaces this package uses to make the standard active from the first turn; a client that reads neither still gets the skill. This namespace is a statement of where those files are, not a request that any client load them.",
      "interface": {
        "displayName": "Prose Discipline",
        "shortDescription": "Engineering prose standard for agent-written text.",
        "category": "Productivity"
      }
    }
  }
}
plugins/prose-discipline/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "prose-discipline",
  "version": "1.3.0",
  "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, 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.",
  "author": {
    "name": "Alexander Kurganov",
    "url": "https://github.com/Akurganow"
  },
  "homepage": "https://github.com/Akurganow/ai-plugins/tree/main/plugins/prose-discipline",
  "repository": "https://github.com/Akurganow/ai-plugins",
  "license": "MIT",
  "keywords": [
    "prose",
    "writing",
    "style-guide",
    "anti-slop",
    "code-review",
    "conventional-comments",
    "commit-messages",
    "agent-skills"
  ],
  "extensions": {
    "io.github.akurganow.ai-plugins": {
      "components": {
        "skills": "./skills",
        "rules": "./rules/prose-discipline.md",
        "hooks": "./hooks/hooks.json"
      },
      "components_note": "Agent Plugins 1.0.0 fixes the location of skills at ./skills (§6.1) and assigns no meaning to anything else here. The rules file and the hook are the two surfaces this package uses to make the standard active from the first turn; a client that reads neither still gets the skill. This namespace is a statement of where those files are, not a request that any client load them.",
      "interface": {
        "displayName": "Prose Discipline",
        "shortDescription": "Engineering prose standard for agent-written text.",
        "category": "Productivity"
      }
    }
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[prose-discipline on Agent Plugins Marketplace](https://pluginsmp.com/plugins/prose-discipline)