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-cringegit 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)<a href="https://agentmods.dev/skills/matteobaccan/linkedincringe/linkedin-cringe"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe.svg" alt="Measured on agentmods" 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 | $0.00157 | $0.05393 |
| Opus 5 | $0.00078 | $0.02697 |
| Sonnet 5 | $0.00031 | $0.01079 |
| Haiku 4.5 | $0.00016 | $0.00539 |
Grade A, and why
linkedin-cringe 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Cringe: generatore di post
Genera post LinkedIn in italiano che riproducono il cringe autentico di LinkedIn Italia.
Principio guida
Il cringe non è "scritto male". Il cringe è imbarazzo vicario: nasce quando chi scrive ci crede davvero, rivendica una profondità che il testo non ha, e sta vendendo qualcosa fingendo di non vendere nulla.
Regola non negoziabile: la voce non strizza mai l'occhio. Nessuna ironia, nessuna autoconsapevolezza, nessun ammicco al lettore. Appena il testo ammicca, smette di essere cringe e diventa barzelletta.
Leggi references/tassonomia.md prima di scrivere: contiene la definizione operativa,
la legge dello scarto e la scala 1-10.
Flusso
1. Raccogli i parametri
Se l'utente ha già indicato tema, livello o moduli nella richiesta, non fare domande: usa quello che ha detto e riempi i buchi con i default (livello 7, credibile).
Altrimenti mostra prima il menu dei moduli: elenco compatto, codice + nome, preso da
references/moduli.md, e poi chiedi i parametri con AskUserQuestion, quattro domande:
D1. Livello di cringe (header: "Livello")
4Lieve: passa inosservato, lascia solo un leggero fastidio7Imbarazzante (consigliato): il punto dolce, chi legge fa una faccia9Insostenibile: screenshottabile, il tipo di post che gira nelle chat10Leggendario: tutti i tic insieme, oltre il limite del sopportabile
D2. Registro (header: "Registro")
Credibile (consigliato): deve poter passare per un post vero, pescato dal feed. Nessuna esagerazione che tradisca la finzione.Parodico: esagerazione dichiarata, si capisce che è una presa in giroSurreale deadpan: il mondo raccontato è impossibile e la voce non se ne accorge. Né credibile né parodico, nessuna battuta. Vive dal livello 7 in su, il punto dolce è il 9AI-SLOP: il post non ha un autore, è stato generato e incollato senza rileggerlo. Ribalta la regola anti-AI di questa skill. Non viene mai scelto dalla skill: solo dall'utente, qui o per nome. Vive dal livello 5 in su, il punto dolce è l'8
What ships with it
8 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 · 348 lines · 157 tokens per session scan A 47521db252b5
linkedin-cringe is a skill published in the GitHub repository matteobaccan/LinkedInCringe (19 stars, last pushed 14d ago), licensed MIT. It adds 157 tokens to every session and 5,393 once invoked, about $0.0008 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
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.
product-marketing-copywriter
A marketing-copy tool that analyzes audience problems and product benefits, then creates promotional headlines and body text. Marketing copy is writing intended to explain and promote a product.