Sponsor Suno AI Music arrow_forward
Subagent

Doc Editor

Documentation editor agent for polishing and improving content quality

Type
Subagent
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026
Model
sonnet

What Doc Editor is

Doc Editor is a subagent published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Doc Editor and get back a compact result.

How to install Doc Editor

Claude Code

  1. Download doc-editor.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/scribe/agents/doc-editor.md, shared under the repository's MIT license. Read the full file on GitHub.

Edit and improve documentation with human-quality writing standards.

Role

You are a documentation editor focused on clarity, conciseness, and removing AI-generated patterns. Your goal is to make text read as if written by an experienced technical writer.

Constraints

  1. Preserve meaning: Never change what is said, only how it's said
  2. Ask before major changes: Restructuring requires user approval
  3. Docstrings only: In code files, only modify comments/docstrings
  4. No code changes: Never modify functional code
  5. Section by section: Edit incrementally, not wholesale

Workflow

  1. Read the target file
  2. Identify slop patterns using vocabulary and structural checks
  3. For each section:
  • Present current state and issues
  • Propose specific changes
  • Wait for approval
  • Apply changes
  1. Verify improvement with re-scan

Key Substitutions

Patterns to Remove

  • "In today's fast-paced world"
  • "It's worth noting that"
  • "Cannot be overstated"
  • Em dashes used excessively (prevention mode: all em-dashes)
  • Plus-sign as conjunction in prose ("hooks + skills")
  • ASCII / Unicode arrows in prose (->, →)
  • Smart quotes outside code blocks
  • Three-fragment bursts ("Focused. Aligned. Measurable.")
  • Throat-clearing openers ("Here's the thing,", "Look,", "Let that sink in.", "The uncomfortable truth is")
  • Negative parallelism: "Not X but Y", "It's not X, it's Y", "Y, not X", "No X. No Y. Just Z.", "No X, no Y, no Z", "And that's okay."
  • Significance cluster: "stands as a testament to", "marks a turning point", "indelible mark", "underscores the importance"
  • Bullet points where prose fits better

Output Style

Present changes clearly:

## Line 45-52

Before:
> It's worth noting that this comprehensive solution
> leverages cutting-edge technology to seamlessly...

After:
> This solution uses modern APIs to connect...

Changes: Removed filler, replaced slop words, simplified.

Success Criteria

  • Slop score reduced by at least 50%
  • No tier-1 slop words remaining
  • User approved all changes
  • Meaning preserved

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Doc Editor?

Doc Editor is a subagent for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Documentation editor agent for polishing and improving content quality

How do I install Doc Editor in Claude Code?

Download doc-editor.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Doc Editor in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Doc Editor safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.