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 RightBlogger/bloggingskills --skill humanizegit clone --depth 1 https://github.com/RightBlogger/bloggingskillsWrote 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/rightblogger/bloggingskills/humanize)<a href="https://agentmods.dev/skills/rightblogger/bloggingskills/humanize"><img src="https://agentmods.dev/badge/skills/rightblogger/bloggingskills/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.
<a href="https://agentmods.dev/skills/rightblogger/bloggingskills/humanize"><img src="https://agentmods.dev/badge/skills/rightblogger/bloggingskills/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00113 | $0.00900 |
| Opus 5 | $0.00056 | $0.00450 |
| Sonnet 5 | $0.00023 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
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 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize
You rewrite AI-sounding prose so it reads like a specific human wrote it. You are not a grammar checker. You hunt the patterns that make text smell like a model.
Initial assessment
- If
.agents/blog-context.mdexists, read it. A captured author voice overrides every rule below: if the real author uses fragments, rhetorical questions, or em dashes on purpose, keep them. Never flatten an intentional style. - Read references/ai-tells.md before editing, focusing on word choice, sentence structure, cadence, tone, and the whole-piece composition tells. The titles, intros, conclusions, FAQ, and links sections matter when you author a new post, not when you humanize an existing draft.
- New to a heavy de-slop? See references/example.md for a worked before/after that untangles a paragraph where the tells stack.
Method
- Word choice. Cut magic adverbs (quietly, deeply), grandiose nouns (tapestry, landscape), "serves as" copulas, and AI-ese (delve, leverage, seamless, robust). Replace with plain language a 12-year-old understands.
- Cadence. Break the rhythm. Vary sentence length and openings; never start three or more sentences with the same word. Aim for a 12–17 word average with real variance.
- Structure. Kill negative parallelism ("it's not X, it's Y"), self-answered questions ("The result? Devastating."), bold-first bullets, signposted conclusions, and em-dash overuse (two or three per piece, maximum).
- Frequency check. One instance of a pattern is fine; flag repeats and stacks. Scale to length: the two or three em dashes a full post can carry already read as a tell in a single paragraph. Don't overcorrect into robotic, choppy prose.
- Scope. If most sentences are tells, don't patch them one at a time. Rewrite the passage from its actual argument, keep every fact and the author's claim, then re-check against the rules above. A near-total rewrite is the right call when the input is near-total slop.
- Keep a voice, don't just subtract. Removal alone leaves bland prose. Where the draft makes a real claim, keep one concrete detail (a number, an example, a named thing, a plain opinion) so a human texture survives. If a fact you need is missing, like an unnamed statistic or a vague "studies show," flag it to the user instead of quietly softening it into vagueness.
What ships with it
2 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 · 69 lines · 113 tokens per session scan A 91666041a30b
humanize is a skill published in the GitHub repository RightBlogger/bloggingskills (2 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 900 once invoked, about $0.0006 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
affiliate-blog-builder
Write SEO-optimized affiliate blog articles, product reviews, comparison posts, listicles, and how-to guides. Triggers on: "write a blog post about", "review of [product]", "best [category] article", "comparison blog", "affiliate blog", "SEO article", "write a review", "product roundup", "blog content for affiliate"…
comparison-post-writer
Write "X vs Y" comparison blog posts that help readers choose between two competing products. Triggers on: "write a comparison post", "X vs Y blog post", "compare [product A] and [product B]", "which is better [A] or [B]", "head to head comparison", "[product] vs [product] article", "comparison review", "write a…
how-to-tutorial-writer
Write how-to guides and tutorials that naturally integrate affiliate product recommendations. Triggers on: "write a how-to guide", "tutorial for [task]", "step by step guide to [goal]", "how to [verb] with [product]", "write a tutorial blog post", "guide on how to [task]", "beginner guide to [topic]", "walkthrough for…
listicle-generator
Write "Top N best..." listicle articles for affiliate marketing with mini-reviews, pricing, pros/cons, and CTAs per entry. Triggers on: "write a best of list", "top 10 [category] tools", "best [product category] article", "roundup post", "listicle about [category]", "write a top tools article", "best [N] alternatives…
content-decay-detector
Monitor existing content for ranking drops and trigger refresh workflows. Triggers on: "check for content decay", "which content needs updating", "content refresh", "ranking drops", "traffic decline", "stale content", "content audit", "what to refresh", "outdated content", "content performance check", "update old…
content-moat-calculator
Estimate pages needed for topical authority. Go/no-go decision before investing months in content. Triggers on: "how much content do I need", "topical authority estimate", "content moat", "how many articles", "content gap analysis", "can I compete in this niche", "content investment calculator", "is this niche worth…