gbb-humanizer

gbb-humanizer is a skill for Claude Code, Codex from aiappsgbb/awesome-gbb. It costs 212 tokens per session (7,957 once invoked), scanned A, original, MIT.

A prose editing guide that removes writing patterns often associated with AI-generated text, such as repetitive structure, inflated claims, filler, and overly familiar openings. It is meant to polish text produced by another tool.

In plain words
What is it for?
Use it to edit catalog copy, technical writing, sales material, and other prose-heavy documents after they have been generated.
Why use it?
It helps make drafted copy sound more natural while preserving the original information and purpose.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

Good fit Use it to edit catalog copy, technical writing, sales material, and other prose-heavy documents after they have been generated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiappsgbb/awesome-gbb/gbb-humanizer
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 aiappsgbb/awesome-gbb --skill gbb-humanizer
Clone the repo
git clone --depth 1 https://github.com/aiappsgbb/awesome-gbb

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 gbb-humanizer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/gbb-humanizer"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/gbb-humanizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,957 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00212 $0.07957
Opus 5 $0.00106 $0.03979
Sonnet 5 $0.00042 $0.01591
Haiku 4.5 $0.00021 $0.00796

Measured 8d ago against content hash 225ae894e445, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gbb-humanizer 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.

skills/gbb-humanizer/SKILL.md · 704 lines

How it starts

The opening of the file, as written. The whole thing — 704 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GBB Humanizer — remove AI tells from prose

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

Provenance. Adapted from blader/humanizer v2.5.1 (MIT). The 29-pattern catalog, the personality/soul guidance, the process loop, and the full example below are upstream canon — do not modify them when editing this skill. Awesome-gbb additions are confined to the four sections below this Provenance block (When to use, Voice calibration, Section-aware mode, Density-preserving guardrail) and the GBB changelog at the bottom.


GBB · When to use in this catalog

gbb-humanizer is a polish pass that runs after another skill has generated prose. It does not generate prose itself. The table below maps the catalog's prose-heavy artifacts to whether and how to humanize them.

Source artifact Generated by Humanize? Notes
specs/overview.html body paragraphs threadlight-design ✅ yes Highest ROI. Pass gbb-seller-pitch.md as the voice sample. Skip the hero kicker (already disciplined), tables, KPI cards, code blocks, SME verbatim quotes.
specs/prep-guide.md / specs/demo-script.md threadlight-design (post-deploy phase) ✅ yes Read aloud or paraphrased to customers. Use gbb-seller-pitch.md.
Speaker notes in generated PPTX gbb-pptx ✅ yes Speaker notes get spoken verbatim. Use gbb-seller-pitch.md. Do not humanize slide bullets — those need to stay punchy and parallel.
Generated README "Demo" section threadlight-deploy ✅ yes (light pass) Use gbb-technical-blog.md.
specs/SPEC.md body sections threadlight-design ⚠️ selective Humanize the narrative sections (overview, in-scope/out-of-scope rationale). Do not touch BR-XXX rule definitions, eval scenario tables, or the canonical sections sellers use to navigate.
specs/AGENTS.md threadlight-design ❌ no Runtime contract for sub-agents. Directive style is intentional.
Skill SKILL.md files in this catalog humans + sub-agents ❌ no Runtime contracts. Bullet density and parallel structure are load-bearing.
Bicep / Python / TypeScript / shell various ❌ no Code, not prose.
Agent system prompts (config.yaml, agent.yaml) threadlight-deploy ❌ no Directive imperative voice is intentional ("You MUST do X"). Humanizing softens commands and degrades agent reliability.
Synthetic mock data / Cosmos seeds threadlight-demo-data-factory ❌ no Sometimes the AI flavor is the point (mock LLM responses).

Read the full file on GitHub · 704 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 704 lines · 212 tokens per session scan A 225ae894e445

Subscribe to this mod's changes

gbb-humanizer is a skill published in the GitHub repository aiappsgbb/awesome-gbb (5 stars, last pushed yesterday), licensed MIT. It adds 212 tokens to every session and 7,957 once invoked, about $0.0011 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

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