human-writing

human-writing is a skill for Claude Code, Codex from pr-pm/prpm. It costs 28 tokens per session (2,983 once invoked), scanned A, original, MIT.

A writing guide for producing natural, conversational text that avoids common AI and corporate phrasing.

In plain words
What is it for?
Use it for articles, documentation, marketing copy, and other text that should sound specific, opinionated, and human.
Why use it?
It helps when generated writing sounds generic, overly enthusiastic, or unlike something a real person would say.

Skill for Claude CodeCodex

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 skills/pr-pm/prpm/human-writing
Any agent
npx skills add pr-pm/prpm --skill human-writing
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

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 human-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/pr-pm/prpm/human-writing.svg)](https://agentmods.dev/skills/pr-pm/prpm/human-writing)
Your own site
<a href="https://agentmods.dev/skills/pr-pm/prpm/human-writing"><img src="https://agentmods.dev/badge/skills/pr-pm/prpm/human-writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,983 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 $0.00028 $0.02983
Opus 5 $0.00014 $0.01491
Sonnet 5 $0.00006 $0.00597
Haiku 4.5 $0.00003 $0.00298

Measured 4d ago against content hash 4665b527ba9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

human-writing 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 4d 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.

.claude/skills/human-writing/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human-Style Writing

This skill helps you write content that reads like it was written by a real person with opinions, personality, and specific knowledge—not a corporate blog generator or AI assistant trying to sound helpful.

Core Principle

Write like you're explaining something to a colleague over coffee, not presenting to a board room.

Good writing is specific, opinionated, and conversational. Bad writing is generic, safe, and sounds like every other tech blog.

What Makes Writing Sound AI-Generated

❌ Patterns to Avoid

1. Over-Enthusiastic Openings
❌ "We're thrilled to announce..."
❌ "Today, we're excited to share..."
❌ "I'm delighted to introduce..."
❌ "Join us on this exciting journey..."

✅ "We built X because Y kept breaking."
✅ "Here's what we learned shipping X to production."
✅ "Most migration tools get you 70% of the way. Here's how we get to 95%."
2. Vague Claims Without Evidence
❌ "This revolutionary approach transforms how developers work."
❌ "Leveraging cutting-edge AI technology..."
❌ "A game-changing solution for modern development."
❌ "Unlock the full potential of your workflow."

✅ "Nango used this to migrate 47 repos in 3 days."
✅ "We tested this on Next.js App Router migration—reduced manual fixes from 800 to 40."
✅ "Stripe's migration guide is 12,000 words. This gets it down to 200 lines of code."
3. Corporate Buzzword Soup
❌ "Empowering developers to leverage synergies..."
❌ "Best-in-class solutions for enterprise-grade..."
❌ "Seamlessly integrate with your existing ecosystem..."
❌ "Drive innovation through collaborative paradigms..."

✅ "Works with whatever you're already using."
✅ "Detects edge cases your regex won't catch."
✅ "One command. No config file. No surprises."
4. Unnecessary Hedging
❌ "This might help you potentially improve..."
❌ "You could possibly consider..."
❌ "This may or may not be useful..."
❌ "Some users have reported that..."

✅ "This cuts migration time in half."
✅ "Use this when codemods aren't enough."
✅ "Three users reported this edge case. We fixed it."

Read the full file on GitHub · 380 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. 4d ago First seen · 380 lines · 28 tokens per session scan A 4665b527ba9e

Subscribe to this mod's changes

human-writing is a skill published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 2,983 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.