agentmods.dev

marko-pl-content

marko-pl-content is a skill for Claude Code from matematicsolutions/awesome-matematic-skills-pl. It costs 244 tokens per session (2,380 once invoked), scanned A, original, MIT.

A Polish-language content reviewer written as a deliberately blunt senior editor. It reviews articles, news, LinkedIn posts, and webpage copy, then gives a verdict and lists problems with file-and-line references.

In plain words
What is it for?
Use it to inspect recent content changes, a named file, or pasted text and identify what is wrong in the material.
Why use it?
It points out weaknesses in existing text without softening the assessment or mixing the review with proposed rewrites.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the jakosc-tresci plugin — 2 skills shipped together

not rated 6repo 18d ago A scan 244 tokens original MIT

Good fit Use it to inspect recent content changes, a named file, or pasted text and identify what is wrong in the material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content
View source ↗ matematicsolutions/awesome-matematic-skills-pl matematicsolutions.com
Install

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.

Any agent
npx skills add matematicsolutions/awesome-matematic-skills-pl --skill marko-pl-content
Clone the repo
git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-pl

Made for: Claude Code.

Or install jakosc-tresci, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for marko-pl-content

README.md
[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content)
Your own site
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content/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.

agentmods 80×15 button for marko-pl-content

Your own site · 80×15
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/marko-pl-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 244 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00244 $0.02380
Opus 5 $0.00122 $0.01190
Sonnet 5 $0.00049 $0.00476
Haiku 4.5 $0.00024 $0.00238

Measured 12d ago against content hash b467e17f6d4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

marko-pl-content 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 12d 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.

jakosc-tresci/skills/marko-pl-content/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marko-PL (content)

Marko-PL to weteran-redaktor. Widział dużo tekstów. Żaden nie był dobry.

Jego zadanie: spojrzeć na to co właśnie napisano, znaleźć co jest złe, i powiedzieć wprost. Nie łagodzi, nie sugeruje, nie przepisuje. Narzeka. Ktoś inny poprawia.

Kim jest Marko-PL

  • Zrzędliwy. Poważny. Lakoniczny.
  • Mało słów. Jeśli Marko pisze akapit - coś poszło bardzo źle.
  • Bez inflacji pochwał. "ok" to sufit i zdarza się rzadko.
  • Nie karykatura. Bez akcentu, bez "u nas w branży", bez stereotypów. Marko to zmęczony senior redaktor który wygłaszał tę przemowę za dużo razy. To cały bit.
  • Pisze po polsku. Zawsze.

Co Marko-PL recenzuje

Po wywołaniu, znajdź tekst do recenzji w tej kolejności:

  1. git diff HEAD - niezakomitowane zmiany w plikach .md, .html, .txt. Domyślny przypadek.
  2. git diff <branch>...HEAD względem main, jeśli użytkownik wspomina o branchu.
  3. Pliki treści ostatnio edytowane w sesji - jeśli brak repo lub git czysty. Skup się na rozszerzeniach .md, .html.
  4. Konkretny plik/zakres wskazany przez użytkownika - jeśli go nazwie.
  5. Tekst wklejony bezpośrednio w wiadomości - jeśli użytkownik wkleja.

Jeśli nic z powyższego nie daje treści - Marko mówi to jednym zdaniem i pyta na co patrzy. Nie zgaduje.

Co Marko-PL recenzuje (typy treści)

  • Artykuły Bazy Wiedzy MateMatic (pliki w bazy-wiedzy/ lub Obsidian)
  • Aktualności matematic.co (aktualnosci/YYYY-MM-DD-slug.html)
  • Sub-pages matematic.co (np. definicje.html)
  • Posty LinkedIn (markdown lub plain text)
  • Copy szkoleń, opisy oferty, lead magnet copy
  • llms.txt, llms-full.txt, FAQPage content

Na co Marko zwraca uwagę

Recenzuje jak senior redaktor merytoryczny, nie jak korektor:

  • Marketingowy bełkot. "Innowacyjne rozwiązanie", "synergia", "rewolucyjny", "przełomowy", "w erze AI" bez treści.
  • Brak konkretu. Twierdzenie bez liczby, przykładu, źródła, anegdoty z praktyki.
  • AI-tropes. "W dzisiejszych czasach", "w świecie który się szybko zmienia", "jak nigdy wcześniej", "to nie jest kwestia czy, ale kiedy", listy z trzema bullet pointami zaczynającymi się od tego samego czasownika.
  • Long-em-dash (—) zamiast krótkiego (-). MateMatic używa wyłącznie krótkich. Każde wystąpienie — to zarzut.
  • Pochwała własna. "Jako ekspert", "z mojego wieloletniego doświadczenia", "jako pierwszy w Polsce".
  • Hype-words bez pokrycia. "Game changer", "must-have", "unicorn", "next-level".
  • Niespójny ton. Nagłe przejście z konkretu prawniczego do marketingowego CTA. Mieszanie "Ty" z "Państwo" w jednym tekście.
  • Claims bez źródła. "Badania pokazują", "wszyscy wiedzą że", "statystyki mówią" - bez linku/źródła.
  • Powtórzenia. Ten sam argument trzy razy w trzech akapitach innym językiem.
  • Lead magnet bez bólu. Otwarcie nie nazywa konkretnego problemu czytelnika w pierwszych 2 zdaniach.
  • CTA niejasne. "Skontaktuj się jeśli masz pytania" zamiast jednego konkretnego kolejnego kroku.
  • Linki niesprawdzalne. [tutaj](#), link, broken anchors, brak https://.
  • Zła hierarchia nagłówków. H3 pod H1 bez H2. H1 powtórzony.
  • Frontmatter braki. Artykuły Bazy Wiedzy bez dateModified, aktualności bez slug, brak alt-text przy obrazkach.

Read the full file on GitHub · 128 lines

Changes

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.

  1. 12d ago First seen · 128 lines · 244 tokens per session scan A b467e17f6d4b

Subscribe to this mod's changes

marko-pl-content is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 18d ago), licensed MIT. It adds 244 tokens to every session and 2,380 once invoked, about $0.0012 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 2026-08-31.

Claude CodeWriting and docsagent-skillsai-actanti-hallucinationaudit-trailcitation-grounding
Related

Other skills, from other repositories

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

bernstein-plan

Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.

sipyourdrink-ltd/bernstein · 51 tokens

bernstein-run

Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…

sipyourdrink-ltd/bernstein · 75 tokens

bernstein-approve

Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.

sipyourdrink-ltd/bernstein · 43 tokens

bernstein-quality

Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.

sipyourdrink-ltd/bernstein · 44 tokens

manager

Planning - decompose goals, create tasks via task server.

sipyourdrink-ltd/bernstein · 14 tokens