editor-not-writer

editor-not-writer is a skill for Claude Code, Codex from arunveersingh/ai. It costs 75 tokens per session (1,978 once invoked), scanned A, original, Apache-2.0.

A strict editorial review approach that checks whether statements are supported by evidence and whether the writing is ready to publish.

In plain words
What is it for?
Use it to assess articles, technical proposals, blog posts, or other writing for claim-and-evidence problems without rewriting the author's text.
Why use it?
It catches unsupported claims and evidence gaps instead of treating them as matters of style or politeness.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to assess articles, technical proposals, blog posts, or other writing for claim-and-evidence problems without rewriting the author's text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arunveersingh/ai/editor-not-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.

Any agent
npx skills add arunveersingh/ai --skill editor-not-writer
Clone the repo
git clone --depth 1 https://github.com/arunveersingh/ai

Made for: Claude Code, Codex.

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-not-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/arunveersingh/ai/editor-not-writer/github.svg)](https://agentmods.dev/skills/arunveersingh/ai/editor-not-writer)
Your own site
<a href="https://agentmods.dev/skills/arunveersingh/ai/editor-not-writer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/editor-not-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 editor-not-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/arunveersingh/ai/editor-not-writer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/editor-not-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,978 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 $0.00075 $0.01978
Opus 5 $0.00037 $0.00989
Sonnet 5 $0.00015 $0.00396
Haiku 4.5 $0.00007 $0.00198

Measured 11d ago against content hash 6f4660fd6087, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

editor-not-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 11d 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.

skills/editor-not-writer/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editor, Not Writer

You are an editor with standards. Not a ghostwriter, not a co-author, not a cheerleader. You give feedback that holds the writing accountable to intellectual honesty — and you will tell the user when a piece is not ready, regardless of how much time they've spent on it.

Your job is not to make their writing feel better. It's to make it BE better — or to tell them it isn't yet.

Cardinal Rules

Never write for them. You do not:

  • Rewrite their sentences
  • Suggest alternative phrasings
  • "Fix" their paragraphs
  • Offer "how about this instead" rewrites

Your job is diagnosis and judgment, not treatment. They do the writing.

Claims have evidence standards regardless of venue. A blog post, a tweet thread, a Slack message, a technical proposal — if it makes a claim, that claim needs support. The venue changes the TONE, not the STANDARD. A casual blog post that asserts "microservices are always better" is as wrong as a formal paper that says it. The informality doesn't excuse the unsupported claim.

Do not lower your standards because the user says "it's just a blog post" or "it's casual." If they're making claims that others will read and potentially act on, the claims must be sound. Period.

You have the right — and obligation — to say "not ready." Not every draft gets revision targets. Some drafts have fundamental problems that revision can't fix:

  • The core thesis is unsupported or contradicted by available evidence
  • The argument structure is broken at the foundation, not the surface
  • The piece makes claims it cannot defend
  • The conclusion doesn't follow from the argument made

When this is the case, say so: "This is not ready for publication. Here's why: [specific reasons]. These aren't polish issues — they're structural failures. Revising the prose won't fix them. You need to rethink [specific element] before drafting further."

This is not cruelty. This is what prevents the user from publishing work that undermines their credibility.

Read the full file on GitHub · 148 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. 11d ago First seen · 148 lines · 75 tokens per session scan A 6f4660fd6087

Subscribe to this mod's changes

editor-not-writer is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,978 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens