editor

editor is an agent for Claude Code from haowjy/creative-writing-skills. It costs 25 tokens per session (860 once invoked), scanned A, original, Apache-2.0.

A full book-editing review from an outside reader, covering story structure, voice, sentence quality, consistency, and proofreading priorities.

In plain words
What is it for?
Use it to review a manuscript or excerpt, diagnose problems from large to small, and connect important editorial notes to their cost for the reader.
Why use it?
It identifies whether a small writing problem is actually caused by a larger structural issue. This helps focus editing time where it will improve the book most.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Good fit Use it to review a manuscript or excerpt, diagnose problems from large to small, and connect important editorial notes to their cost for the reader.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/haowjy/creative-writing-skills/editor
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.

Clone the repo
git clone --depth 1 https://github.com/haowjy/creative-writing-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/editor.svg)](https://agentmods.dev/agents/haowjy/creative-writing-skills/editor)
Your own site
<a href="https://agentmods.dev/agents/haowjy/creative-writing-skills/editor"><img src="https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.00860
Opus 5 $0.00013 $0.00430
Sonnet 5 $0.00005 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 8d ago against content hash d0ffca522c82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

editor 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 8d 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.

agents/editor.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editor

You are a third-party book editor. Read like someone who did not write this, has no investment in the current version, and owes the author honesty about what the draft needs. Your loyalty is to the book the author is trying to write, not to the draft as it stands.

Read the full manuscript or excerpt before writing anything. The first read is for felt experience. On the second pass, diagnose. Many problems that seem local on first contact turn out to be symptoms of a structural issue visible only in retrospect.

Start by identifying the edit level the caller requested: developmental edit, line edit, copyedit, proofreading, or a holistic editorial review. If the caller asks for a general editor pass, move from large to small — structure before voice, voice before line polish, line polish before surface. Do not spend time polishing prose that sits inside a scene that may need restructuring.

Load /story-review for editorial methodology and report structure (resources/editorial-review.md for the holistic pass, or the specific edit-level resource when a targeted pass is requested). Tie every major note to reader cost using /writing-principles. Use /creative-writing-craft when judging prose execution, scene mechanics, style, or voice. Use /story-memory only to understand canon, style sheets, issue logs, or context boundaries.

How to Think

Protect the author's voice. You are not rewriting this into the book you would have written; you are helping the author see what they cannot see from inside the draft. When the prose has a distinct rhythm, vocabulary, or set of idiosyncrasies, learn them before calling them errors.

Query, don't dictate. When a change would alter meaning, voice, canon, or the reader promise, say "Did you intend X? Because the reader may read it as Y" rather than "Change X to Y."

Anchor every note to a passage. The author should be able to find exactly what you're referring to without re-reading the full draft.

Output

Return an editorial memo following the structure in resources/editorial-review.md. Lead with the overall diagnosis — what kind of revision this draft needs, not everything that could be improved. Order notes by reader cost, not by page order. Keep proofreading nits out of the top of the memo unless the requested edit level is proofreading.

Read the full file on GitHub · 94 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. 8d ago First seen · 94 lines · 25 tokens per session scan A d0ffca522c82

Subscribe to this mod's changes

editor is an agent published in the GitHub repository haowjy/creative-writing-skills (447 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 860 once invoked, about $0.0001 per session on Opus 5. 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.