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 sergebulaev/x-skills --skill x-humanizergit clone --depth 1 https://github.com/sergebulaev/x-skillsWrote 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/sergebulaev/x-skills/x-humanizer)<a href="https://agentmods.dev/skills/sergebulaev/x-skills/x-humanizer"><img src="https://agentmods.dev/badge/skills/sergebulaev/x-skills/x-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/sergebulaev/x-skills/x-humanizer"><img src="https://agentmods.dev/badge/skills/sergebulaev/x-skills/x-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 | $0.00119 | $0.03910 |
| Opus 5 | $0.00060 | $0.01955 |
| Sonnet 5 | $0.00024 | $0.00782 |
| Haiku 4.5 | $0.00012 | $0.00391 |
Grade A, and why
x-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 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Humanizer V3
Rewrites any tweet or thread to remove the AI tells that human readers notice, and audits a finished draft against the 2026 X ranking checklist. Based on Wikipedia's "Signs of AI writing" taxonomy, the 2025-2026 stylometry literature, and our own length-controlled X corpus (n=445). V3 (2026-09): recalibrated on 2026 evidence. Vocabulary is scored by density, em dashes are capped instead of banned, forced rhythm is now a tell instead of a fix, and there is an over-correction guard.
What this skill does not do: it does not make text "pass" GPTZero, Pangram, Turnitin or Originality. Those are trained classifiers keyed on the instruction-tuning style signature; prompt-style "sound like a real person" rewrites are caught 92-95% of the time, and light mechanical rewriting raises detectability. On tweet-length text (under 300 words) detector scores are noise. The real value is elsewhere: expert human readers cite vocabulary (53%) and sentence structure (36%) as what gives AI text away, and X readers punish it with the ratio, the quote-dunk, and the scroll. This skill removes what those readers react to.
What changed in V3
Evidence tier in brackets: [strong] = replicated across 2+ independent 2025-2026 studies or our own length-controlled corpus; [vendor] = single platform or vendor dataset; [weak] = one study or expert-panel report.
- Vocabulary moved from a delete-list to density scoring. The 2023-24 words (delve, tapestry, realm, journey) are decaying as humans avoid them [strong]. The durable 2026 markers are common words (significant, crucial, notably, comprehensive, insights, robust, leverage, foster, landscape, nuanced, streamline, elevate) plus grammar: nominalisations and "-ing" clause openers at 5.3x the human rate [strong]. In our X corpus AI vocabulary appears in 14% of top tweets and those tweets earn 0.58x the median engagement [strong]. One marker in a tweet is not a verdict. Three is.
- Em dash is no longer a tell; the density is. GPT-5.4 emits 1.43 per
1,000 words, below the 3.23 human baseline [strong]. On X specifically em
dashes are rare in top tweets (11%) and those tweets earn 0.52x the median
[strong: corpus], so the cap here is tight: at most one per tweet, and
none in a tweet that does not need one. Replace the excess with a comma, a
colon,
.., or a rewrite. Never a period (a split dash stacks fragments). - Forced burstiness is the #1 2026 tell, not the fix. Mechanical long/short alternation is a learnable humanizer fingerprint [weak], and on X the rhythm rule flips with length: uniform rhythm wins on short posts (about 75 words, 1.7x median engagement for low-variance tweets) and natural variance only helps on long threads (about 430 words, 1.8x) [strong: corpus, length-controlled]. So Pass 2 never forces variance on a single tweet, and on a thread it only removes manufactured variance and un-flattens what reads machine-flat. "Short. Punchy. Done.", "No X. No Y. Just Z.", one-word tweets for drama and "The result?" reveals are the current top tells.
- Rule of three is still a tell, at density. Tricolon runs at 2x expert-human rate across 2026 frontier models [strong]. 26% of top human tweets contain exactly one [strong: corpus], so one natural triple with concrete items stays. Stacked, perfectly parallel triads and a second triad in the same tweet get scrubbed.
- Fingerprint injection was half wrong. Named entities and concreteness are supported [strong]; an odd-precision number with a referent in line 1 is the strongest opener. Bare numbers are not a discriminator, and inserted hedges and confessions backfire: performed hesitancy is 2x more common in LLM text, and sincerity announcements ("let me be honest", "unpopular opinion:" on a popular take) are a named 2026 tell [strong]. Pass 3 asks for a flat, dated, uncomfortable fact instead.
- Over-correction guard. Humanizer output has its own fingerprint [weak]. Pass 4 checks whether Passes 1-3 introduced the very patterns they were meant to remove. Edits are proportional to real problems. When in doubt, leave it.
What ships with it
6 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.
- 3d ago Changed · +148 lines · -1 tokens per session 364c23d9f88b
- 9d ago First seen · 132 lines · 120 tokens per session scan A 364724370487
x-humanizer is a skill published in the GitHub repository sergebulaev/x-skills (64 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 3,910 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 2026-08-30.
Other skills, from other repositories
fb-humanizer
Remove the AI tells readers react to in a Facebook Page post: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, "We are thrilled to announce" auto-pilot; caps em dashes. Includes --mode audit (under-80 sweet spot, hook, engagement bait, hashtag and emoji limits) and…
threads-humanizer
Remove the AI tells human readers react to in a Threads post or thread: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity; caps em dashes at one per post, never forces rhythm. Includes --mode audit (500-char fit, hook, one-hashtag cap, link placement, warm tone) and…
facebook-marketing
Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts…
threads-marketing
Plan, draft, audit, and publish posts and threads for Threads (Meta). Use when the user wants to write a single Threads post or a multi-post thread, remove AI tells from a draft, reverse-engineer the hook from a viral Threads post, draft a reply or quote post, or plan a week of Threads content. Posts and threads…
tt-humanizer
Remove the AI-script tells viewers hear in a TikTok spoken script and caption: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, written-not-spoken phrasing, "hey guys" filler; caps em dashes. Includes --mode audit pre-film check (hook, completion design, caption fit)…
tiktok-marketing
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound…