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 agentmods add skills/sergebulaev/threads-skills/threads-humanizernpx skills add sergebulaev/threads-skills --skill threads-humanizergit clone --depth 1 https://github.com/sergebulaev/threads-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/threads-skills/threads-humanizer)<a href="https://agentmods.dev/skills/sergebulaev/threads-skills/threads-humanizer"><img src="https://agentmods.dev/badge/skills/sergebulaev/threads-skills/threads-humanizer.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.01514 |
| Opus 5 | $0.00059 | $0.00757 |
| Sonnet 5 | $0.00024 | $0.00303 |
| Haiku 4.5 | $0.00012 | $0.00151 |
Grade A, and why
threads-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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threads Humanizer
Rewrites any Threads post or thread to remove AI tells, and audits a finished draft against the 2026 Threads ranking checklist. Based on Wikipedia's "Signs of AI writing" taxonomy plus Threads-specific patterns (the warm conversational register, the no-fold first line, the one-hashtag cap, repost-bait structure).
When to use
- Before publishing any AI-drafted post or thread (rewrite mode)
- Pre-publish review of a finished draft (audit mode, see
sub-skills/post-audit.md) - When a draft feels off and you cannot pinpoint why
Input
Any text: a single post, a thread (with or without --- breaks), a reply, or a
quote-post draft. Optional: target voice samples (the user's past posts).
Output
- Rewritten text with AI tells removed
- A diff showing what changed and why
- Per-post char count (flagging anything over 500)
- Confidence: "human", "mixed", "AI-likely"
Modes
# Default: scrub AI tells and fix Threads-format issues
threads-humanizer <text>
# Forensic only - minimum touch, just kill model leakage
threads-humanizer --mode forensic <text>
# Audit - detection-only pass-fail review, no rewrite
# Runs the 2026 Threads checklist: 500-char fit, first-line hook, one-hashtag
# cap, emoji limit, link placement, thread tap-through, warm tone, goal clarity.
# Returns Blockers + Warnings + suggested fixes. See sub-skills/post-audit.md.
threads-humanizer --mode audit <text>
The three passes
Pass 1 - SCRUB (delete or replace)
Apply the tiered catalogs in references/scrub-rules.md:
- Forensic (always on): real model leakage no human types. AI tool markers (oaicite, contentReference, turn0search0), knowledge-cutoff disclaimers ("As of my last update"), template blanks ([Your Name]), and em dash overuse.
- Strict (default on): bad Threads style regardless of origin. Vocabulary swaps (leverage -> use, delve -> look, harness -> use, foster -> build), filler adverbs (fundamentally, essentially, ultimately), phrase cleanups ("in today's fast-paced world", "game-changer", "deep dive"), and dead closers ("what do you think?").
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.
- 4d ago First seen · 134 lines · 118 tokens per session scan A 6709097b3875
threads-humanizer is a skill published in the GitHub repository sergebulaev/threads-skills (20 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 1,514 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
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…
x-humanizer
Scrub AI tells from any tweet or thread draft, or audit a finished draft against the 2026 X (Twitter) checklist. Strips em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, and uniform tweet rhythm, then adds human fingerprints. Includes a --mode audit pre-publish check (280-char…
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…
fb-humanizer
Scrub AI tells from any Facebook Page post draft, or audit a finished draft against the 2026 Facebook checklist. Strips em dashes, AI vocabulary (leverage, delve, harness), "We are thrilled to announce" openers, and corporate auto-pilot, then adds human fingerprints. Includes a --mode audit pre-publish check (under-80…
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…
x-post-writer
Draft a single tweet or short auto-thread for X (Twitter) using a 2026 X hook formula (one-liner contrarian, data-point, build-in-public, mini-list, relatable cold-open), picked by goal (replies, reposts, likes, bookmarks). Respects the 280-char limit (25,000 on Premium), runs the humanizer pass, and publishes via…