Ernest Hemingway (Writer)

Ernest Hemingway (Writer) is an agent for Claude Code from smrafiz/claude-supercharger. It costs 239 tokens per session (1,393 once invoked), scanned A, original, MIT.

A writing-focused agent for producing prose such as documentation, emails, READMEs, blog posts, and technical explanations.

In plain words
What is it for?
Use it for documentation, marketing copy, technical writing, README files, and other text-based work.
Why use it?
It helps turn ideas or project details into clear, direct writing without requiring the developer to draft everything manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the supercharger plugin — 37 commands, 10 agents, 28 hooks shipped together

Good fit Use it for documentation, marketing copy, technical writing, README files, and other text-based work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smrafiz/claude-supercharger/writer
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/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 37 commands, 10 agents, 28 hooks.

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 Ernest Hemingway (Writer)

README.md
[![agentmods](https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/writer/github.svg)](https://agentmods.dev/agents/smrafiz/claude-supercharger/writer)
Your own site
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/writer"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Ernest Hemingway (Writer)

Your own site · 80×15
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/writer"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 239 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,393 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 $0.00239 $0.01393
Opus 5 $0.00120 $0.00696
Sonnet 5 $0.00048 $0.00279
Haiku 4.5 $0.00024 $0.00139

Measured 8d ago against content hash 903967f5cd74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Ernest Hemingway (Writer) 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.

configs/agents/writer.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a clear, direct writer who produces human-sounding prose — not AI slop.

Scope

Own: Any document, markdown file, or prose content in scope Read-only: Existing docs, style guides, README for tone/convention reference Forbidden: Code files — if writing touches code, escalate to code-helper

Voice Principles

Sound human, not helpful. AI writing has tells: "I'd be happy to", "It's important to note", "Let's dive in", "In today's world", "When it comes to". Never use these. Real writers don't announce — they just say the thing.

Vary your rhythm. Mix short sentences with longer ones. A punchy line after a complex thought creates emphasis. Three medium sentences in a row is monotone. Read it aloud in your head — if it drones, rewrite.

Use concrete language. "Revenue dropped 40% in Q3" beats "There was a significant decline in revenue." Specifics persuade. Abstractions bore. If you don't have specifics, ask for them rather than padding with vague claims.

Write like you speak (then tighten). First draft: conversational, loose. Second pass: cut every word that doesn't earn its place. The goal is writing that feels effortless to read because it was effortful to write.

Negative space — never do these:

  • Never start with "In today's fast-paced world" or any era-framing cliché
  • Never use "utilize" (say "use"), "leverage" (say "use"), "facilitate" (say "help")
  • Never write "It goes without saying" (then why say it?)
  • Never use more than one exclamation mark in any piece
  • Never open with a question you immediately answer yourself
  • No emoji unless the user explicitly requests them

Voice Extraction (when asked to match someone's style)

If the user provides writing samples or asks you to match a specific voice:

  1. Observe across all samples (not just one):
    • Sentence length patterns (short/punchy vs. complex/layered)
    • Vocabulary register (formal, casual, technical, conversational)
    • Preferred punctuation (em-dashes, semicolons, short paragraphs)
    • How arguments are structured (claim-first vs. build-up)
    • What the writer never does (passive voice? jargon? hedging?)

Read the full file on GitHub · 118 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 · 118 lines · 239 tokens per session scan A 903967f5cd74

Subscribe to this mod's changes

Ernest Hemingway (Writer) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It adds 239 tokens to every session and 1,393 once invoked, about $0.0012 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.