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-analyticsgit 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-analytics)<a href="https://agentmods.dev/skills/matteobaccan/linkedincringe/linkedin-cringe-analytics"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe-analytics/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-analytics"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe-analytics.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 | $0.00102 | $0.01320 |
| Opus 5.5 | $0.00041 | $0.00528 |
| Sonnet 5.5 | $0.00020 | $0.00264 |
| Haiku 4.5 | $0.00010 | $0.00132 |
Grade A, and why
linkedin-cringe-analytics 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 2mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Cringe Analytics: analisi dei commenti
Data l'URL di un post LinkedIn, scarica tutti i commenti e produce un report
markdown con le statistiche. È la skill gemella di linkedin-cringe: quella
genera il post, questa misura cosa è successo dopo.
Flusso
1. Acquisizione dei commenti
Due strade, in ordine di preferenza:
A. Browser automation (Claude in Chrome). Se i tool mcp__claude-in-chrome__*
sono disponibili e un browser è collegato, estrai tutto da solo. La procedura
completa e collaudata è in references/estrazione.md: leggila prima di iniziare,
la UI di LinkedIn ha classi CSS offuscate, liste virtualizzate e lazy-load che si
innesca solo con eventi rotella, e il playbook risolve tutti e tre i problemi.
Se il browser non risulta collegato, chiedi all'utente di collegarlo e offri
subito la strada B come alternativa.
B. Fallback manuale. L'utente apre il post, espande tutti i commenti ("Carica altri commenti" / "Vedi risposte precedenti" / "…altro"), seleziona tutto, copia e incolla in chat, oppure salva la pagina e passa il percorso del file. Il parsing a valle è identico.
I dati grezzi (con i nomi veri) vanno solo nella scratchpad di sessione, mai nel repository.
2. Parsing
Trasforma il raccolto in una lista di commenti strutturati. Il formato dei
blocchi e le regole (risposte dell'autore, duplicazioni da annidamento, righe
di conteggio) sono in references/estrazione.md, sezione Parsing.
Escludi dalla classificazione le risposte dell'autore del post (blocco "Autore"): si contano a parte come "botta e risposta" e non inquinano le percentuali.
3. Analisi
Per ogni commento assegna, con i criteri di references/classificazione.md:
- Esito: 😇 ci ha creduto · 🎭 ha colto lo scherzo · 🤨 dubbioso · ⬜ non classificabile
- Tono: ironico di rimando, serio-motivazionale, correttivo-normativo, logico-forense, indignato, aneddotico, altro
- Categoria autore: dedotta dalla headline (tech, sales/BD, HR/recruiting, motivazionale, altro)
- Cringe-metro 1-10: solo per i commenti scritti in buona fede, usando
../linkedin-cringe/references/tassonomia.mdemoduli.md(riferimento incrociato: se la skill gemella non è installata accanto, salta questa parte segnalandolo)
What ships with it
3 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.
- 2mo ago First seen · 97 lines · 102 tokens per session scan A fdb4e0806496
linkedin-cringe-analytics is a skill published in the GitHub repository matteobaccan/LinkedInCringe (23 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,320 once invoked, about $0.0004 per session on Opus 5.5. 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.
linkedin-cringe-analytics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| linkedin-cringe-analyticsmatteobaccan/LinkedInCringe | Skill | 23 | 1mo ago | MIT | A | 102 | Claude Code |
| diagram-designanbeime/skill | Skill | 9.2k | yesterday | none | A | 211 | Claude Code |
| img2threejsanbeime/skill | Skill | 9.2k | yesterday | none | A | 63 | Claude Code, Codex |
| chrome-automationanbeime/skill | Skill | 9.2k | yesterday | none | A | 73 | Claude Code |
| atutun-xhs-coveranbeime/skill | Skill | 9.2k | yesterday | none | A | 156 | Codex |
| video-creation-proanbeime/skill | Skill | 9.2k | yesterday | none | A | 101 | Claude Code, Codex |
| intelligent-content-systemanbeime/skill | Skill | 9.2k | yesterday | none | A | 231 | Claude Code, Codex |