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.
npx skills add aiappsgbb/awesome-gbb --skill gbb-humanizergit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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.
[](https://agentmods.dev/skills/aiappsgbb/awesome-gbb/gbb-humanizer)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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). |
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.
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.
- 8d ago First seen · 704 lines · 212 tokens per session scan A 225ae894e445
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…