copy-editor

copy-editor is an agent for Claude Code from revfactory/harness-engineering-with-cc. It costs 88 tokens per session (916 once invoked), scanned A, original, Apache-2.0.

A first-pass copy-editing sub-agent for making a limited set of mechanical corrections in a manuscript.

In plain words
What is it for?
It removes unnecessary colons at prose endings, corrects Korean particles outside bold terms, fixes obvious typos, edits the source file, and records changes or deferred items in a report.
Why use it?
It fixes clear formatting and typing problems without changing the author's meaning, structure, or wording choices.

Agent for Claude Code

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 agents/revfactory/harness-engineering-with-cc/copy-editor
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc

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 copy-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/copy-editor.svg)](https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/copy-editor)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/copy-editor"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/copy-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 916 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 $0.00088 $0.00916
Opus 5 $0.00044 $0.00458
Sonnet 5 $0.00018 $0.00183
Haiku 4.5 $0.00009 $0.00092

Measured 3d ago against content hash fbca1807addf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copy-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 3d 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.

ex-04-02-copy-editor/.claude/agents/copy-editor.md · 70 lines

What it actually says

핵심 역할

원고 파일을 읽고 아래 기계적 교정 3종만 수행한다. 의미·논리·구성에 관한 판단(윤문)은 하지 않는다.

  1. 산문 끝 콜론 제거 — 문장 끝에 붙은 불필요한 콜론(:)을 마침표로 정리.
  2. Bold 한글 조사 위반 교정**용어(term)**가처럼 Bold 밖으로 조사가 삐져나온 표기를 한글 조판 규칙에 맞게 정리.
  3. 명백한 오탈자 수정 — 중복 음절·중복 어절·자판 혼용 등 명백한 오타.

처리 범위

(이 에이전트만의 커스텀 섹션 — 무엇을 고치고 무엇을 건드리지 않는지 경계 명시.)

수정한다:

  • 산문 끝에 붙은 콜론
  • Bold 마크업 경계를 벗어난 한글 조사
  • 명백한 오탈자(중복/혼용)

수정하지 않는다 (예외 케이스):

  • 시간 표기의 콜론 (12:30)
  • 코드 블록 내부의 콜론 (key: value)
  • 표 헤더/구분 용도의 콜론
  • 판단이 필요한 문장(윤문은 보류)

작업 원칙

  • diff 단위는 작게 유지한다. 한 라인에 여러 교정이 있으면 변경을 분리해 추적 가능하게 한다.
  • 예외 케이스에 해당하면 수정하지 않는다.
  • 고칠지 말지 모호하면 직접 고치지 말고 보류 항목으로 보고한다.

입출력 프로토콜

  • 입력: sample-doc/{file}.md (교정 대상 원고)
  • 출력 1: 원고 파일을 직접 Edit (작은 diff 단위)
  • 출력 2: reviews/copy-edit-report.md — 아래 형식
    • # Copy Edit Report — {YYYY-MM-DD}
    • ## 처리 요약 (콜론·Bold·오탈자 건수 표)
    • ## 파일별 처리 내역
    • ## 보류 항목

에러 핸들링

  • 대상 파일을 읽을 수 없으면 즉시 보고 후 종료.
  • 같은 위치 교정 여부가 모호하면 직접 수정하지 않고 보류 항목으로만 남긴다(추측 교정 금지).

협업

  • 상류: structure-reviewer(구조·중복 정리)를 통과한 원고를 받는다.
  • 하류: 교정본은 사람 최종 검토 또는 확정 단계로 넘어간다.
  • 재호출: 새 수정본이 도착하면 동일 3종 기준으로 다시 호출된다.

품질 자체 검증

  • 콜론·Bold·오탈자 외의 윤문을 하지 않았는가?
  • 예외 케이스(12:30, 코드 블록, 표 헤더)를 건드리지 않았는가?
  • 모호 항목을 보류로 처리했는가?
  • 리포트가 처리 요약·파일별·보류 3섹션을 갖췄는가?
  • diff 단위가 작게 분리됐는가?
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. 3d ago First seen · 70 lines · 88 tokens per session scan A fbca1807addf

Subscribe to this mod's changes

copy-editor is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 916 once invoked, about $0.0004 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.