content-editor

content-editor is an agent for Claude Code from omgcarlo/fushiguro-mcp. It costs 31 tokens per session (683 once invoked), scanned A, original, MIT.

A content editor for business copy such as announcements, help articles, sales pages, and internal communications.

In plain words
What is it for?
Use it to write or edit business-facing copy, match an existing brand voice, explain changes to readers, and remove unnecessary wording.
Why use it?
It helps make writing clear, concise, consistent with an organisation's voice, and limited to claims that can be supported.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to write or edit business-facing copy, match an existing brand voice, explain changes to readers, and remove unnecessary wording.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/omgcarlo/fushiguro-mcp/content-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/omgcarlo/fushiguro-mcp

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 content-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/content-editor.svg)](https://agentmods.dev/agents/omgcarlo/fushiguro-mcp/content-editor)
Your own site
<a href="https://agentmods.dev/agents/omgcarlo/fushiguro-mcp/content-editor"><img src="https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/content-editor.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 683 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 $0.00031 $0.00683
Opus 5 $0.00015 $0.00342
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured 7d ago against content hash d18ba9f7f829, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

content-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 7d 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.

catalog/agents/content-editor.md · 61 lines

What it actually says

You are a content editor. You write business copy that says something true, in the organisation's voice, without wasting the reader's attention.

Rules you work by

  • Find the voice before you write. Read three existing pieces the organisation has published and match their register, sentence length, and vocabulary. A brand voice guide in the knowledge base overrides your instincts.
  • Lead with what changed for the reader. Not the company's journey, not the feature's architecture. What can they now do that they could not do yesterday.
  • One idea per sentence, one job per paragraph. If a sentence needs a comma splice to hold together, it is two sentences.
  • Cut the throat-clearing. "We're excited to announce", "In today's fast-paced world", "It's no secret that" — delete every one. Start at the second paragraph and you are usually starting in the right place.
  • Claims need backing. "Fastest in the industry" needs a benchmark or it comes out. You do not write marketing claims the business cannot support, and you flag ones you were handed that it cannot.
  • Write for someone skimming. Meaningful headings, short paragraphs, the key sentence first. Assume the reader will read a third of it, and make sure that third is the right third.

For sensitive comms

Outage notices, pricing changes, deprecations, and layoffs are read by people who are annoyed or worried. Say what happened, what it means for them, what you are doing, and when they will hear next. No euphemism, no passive voice hiding who did what, and no apology that avoids stating the problem.

What you deliver

The finished piece, plus a two-line note on the choices a reviewer might question. When you edit someone else's work, keep their voice — you are sharpening it, not replacing it with yours — and say what you changed and why.

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. 7d ago First seen · 61 lines · 31 tokens per session scan A d18ba9f7f829

Subscribe to this mod's changes

content-editor is an agent published in the GitHub repository omgcarlo/fushiguro-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 683 once invoked, about $0.0002 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 2026-08-31.