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 matteobaccan/LinkedInCringe --skill linkedin-cringe-metergit clone --depth 1 https://github.com/matteobaccan/LinkedInCringeWrote 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/matteobaccan/linkedincringe/linkedin-cringe-meter)<a href="https://agentmods.dev/skills/matteobaccan/linkedincringe/linkedin-cringe-meter"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe-meter/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/matteobaccan/linkedincringe/linkedin-cringe-meter"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe-meter.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 | $0.00142 | $0.01692 |
| Opus 5 | $0.00071 | $0.00846 |
| Sonnet 5 | $0.00028 | $0.00338 |
| Haiku 4.5 | $0.00014 | $0.00169 |
Grade A, and why
linkedin-cringe-meter 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cringiometro: quanto è cringe questo post
Terza skill della famiglia: linkedin-cringe scrive il post, linkedin-cringe-analytics
misura i commenti, il Cringiometro misura il post di qualcun altro (o il proprio) con
lo stesso metro. L'ispirazione è il blastometro, spostato sul cringe: un voto, i
ganci presi, una frase secca, e un'immagine da lasciare nei commenti.
Si giudica il post, mai la persona. Nessun nome, azienda, headline o foto dell'autore compare nel report o nell'immagine. Questo non è negoziabile.
Flusso
1. Acquisizione del post
Serve solo il testo del post (espanso, con l'"…altro" cliccato), più un'indicazione se c'è un'immagine allegata e cosa mostra. Niente commenti: quelli sono della skill analytics.
A. URL + Claude in Chrome. Se i tool mcp__claude-in-chrome__* sono disponibili,
segui il Setup di ../linkedin-cringe-analytics/references/estrazione.md (caricamento
tool, list_connected_browsers, scelta browser, tabs_context_mcp, navigate). Gli
short link lnkd.in si risolvono da soli con la navigazione. Poi:
- clicca l'"…altro" del post se il testo è troncato;
- prendi il testo del post con
get_page_textoread_pagelimitato al contenitore del post (l'elemento concomponentkeyche inizia perurn:li:activity:o il primo[data-urn]), senza i commenti; - annota se c'è un'immagine, un video, un carosello o un sondaggio, e in una riga cosa si vede (senza persone riconoscibili).
Se la pagina chiede il login o il browser non è collegato, passa a B senza insistere.
B. Testo incollato. L'utente incolla il post in chat, o passa uno screenshot: la skill legge quello. Dallo screenshot ignora nome, foto e headline dell'autore anche se visibili. Il resto del flusso è identico.
I dati grezzi (URL, testo integrale, JSON di lavoro) stanno nella scratchpad di sessione. Nel repository entra solo il report anonimizzato, l'immagine e il JSON con i soli campi che compaiono nell'immagine.
2. Valutazione
Leggi references/valutazione.md e, attraverso i suoi rimandi, tassonomia.md e
moduli.md della skill gemella (../linkedin-cringe/references/). Se la skill
gemella non c'è, fermati e dillo: senza catalogo non c'è metro.
What ships with it
4 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.
- 9d ago First seen · 107 lines · 142 tokens per session scan A 4592c3208bd4
linkedin-cringe-meter is a skill published in the GitHub repository matteobaccan/LinkedInCringe (19 stars, last pushed 14d ago), licensed MIT. It adds 142 tokens to every session and 1,692 once invoked, about $0.0007 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
chrome-automation
A skill for automating an already open Google Chrome browser through its browser control connection.
atutun-xhs-cover
A prompt generator for creating Xiaohongshu cover designs, where Xiaohongshu is a Chinese social platform for lifestyle and product content.
video-creation-pro
A staged workflow for producing videos, from requirements and content creation through images, audio, subtitles, video assembly, quality checks, and iteration.
intelligent-content-system
A content workflow tool that gathers web content, creates supporting images and social posts, and publishes them across WeChat, Xiaohongshu, X, and Bilibili. Xiaohongshu is a Chinese social platform, while Bilibili is a Chinese video platform.
obsidian-bases
An Obsidian skill for creating database-view files. Obsidian is a note-taking app, and a database view shows notes as tables or cards using filters and formulas.
product-manager-toolkit
A product-management toolkit for prioritizing requests, analyzing user interviews, and writing PRDs. A PRD, or product requirements document, describes what a product or feature should do; RICE is a scoring method for comparing priorities.