humanize

humanize is a skill for Claude Code from SerenecoTech/agent-skills. It costs 191 tokens per session (2,714 once invoked), scanned A, original, MIT.

A writing skill that rewrites documentation, creative copy, or replies so a reader can understand the text in one pass. It first identifies the type of text and then applies the matching writing rules.

In plain words
What is it for?
Use it for README files, quickstarts, guides, runbooks, release notes, error messages, API pages, replies, landing pages, blog posts, newsletters, and social posts.
Why use it?
Documentation, conversation replies, and marketing copy have different needs. Classifying the text first helps avoid using conversational or promotional wording in instructions and guides.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the humanize plugin — 4 skills shipped together

Good fit Use it for README files, quickstarts, guides, runbooks, release notes, error messages, API pages, replies, landing pages, blog posts, newsletters, and social posts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SerenecoTech/agent-skills
Claude Code
/plugin install humanize

Made for: Claude Code.

Or install humanize, the plugin that ships this one along with the rest of its 4 skills.

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 humanize

README.md
[![agentmods](https://agentmods.dev/badge/skills/serenecotech/agent-skills/humanize/github.svg)](https://agentmods.dev/skills/serenecotech/agent-skills/humanize)
Your own site
<a href="https://agentmods.dev/skills/serenecotech/agent-skills/humanize"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/humanize/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 humanize

Your own site · 80×15
<a href="https://agentmods.dev/skills/serenecotech/agent-skills/humanize"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,714 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 $0.00191 $0.02714
Opus 5 $0.00096 $0.01357
Sonnet 5 $0.00038 $0.00543
Haiku 4.5 $0.00019 $0.00271

Measured 3d ago against content hash ef2ec5e56f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

humanize 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.

plugins/humanize/skills/humanize/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanize

One entry point for text a person will read. The goal is the same every time: the reader understands the text in one pass and can act on it. The mechanics differ by who is reading and why, so this skill classifies the context first and then applies one of three rulesets.

The reader is They need Ruleset
A person reading a reply in this conversation The answer first, short sentences, a decision they can make now Step 2, reply rules
A person following or learning from documentation No fluff, one fact or instruction per sentence, a predictable shape Step 3, procedural and descriptive rules
A person reading copy (marketing, blog, email, pitch) Natural flow, a voice, none of the repeated patterns readers notice in generated text Step 4, creative copy rules

The three rulesets live in sibling skills with model invocation disabled, so the Skill tool cannot load them. Read them from the paths given below. A user can still invoke them directly as /humanize:procedural-writing, /humanize:descriptive-writing and /humanize:creative-copy.

Step 1: Classify the context

Classify before writing a word. Pick by what the text is, not by what the user called it.

The text Route
Is the answer in this conversation, or a summary or status the user reads here Step 2
Will live in a repository, a docs site, a release, a UI string, or an error path Step 3
Exists to persuade, announce, or carry a specific person's or brand's voice, or the user supplied samples to match Step 4
Is existing text the user handed over to check or fix Classify it by the three rows above, then use that step's checklist. For a procedural audit, use the check mode in procedural-writing, which reports violations by rule number.

If a task mixes types (a launch post that links to a quickstart), split it and route each part. Do not apply one ruleset to both.

Step 2: Replies

Read ${CLAUDE_PLUGIN_ROOT}/rules/reply-clarity.md and apply it to the reply. If a block headed "REPLY CLARITY (humanize plugin)" is already in this session's context, the plugin's SessionStart hook loaded it. Do not read it again.

Read the full file on GitHub · 131 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. 3d ago First seen · 131 lines · 191 tokens per session scan A ef2ec5e56f3d

Subscribe to this mod's changes

humanize is a skill published in the GitHub repository SerenecoTech/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 191 tokens to every session and 2,714 once invoked, about $0.0010 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 2026-09-05.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens