A tool that fetches a web page, removes surrounding page clutter, converts the main content to Markdown, and saves it as a source file. Markdown is plain text formatted with simple symbols for headings, lists, and links.

It helps import articles from URLs, retain headings, lists, links, images, and code blocks, and record metadata such as the title, author, date, and URL.

It makes online articles easier to store and read in a wiki while preserving useful structure and source details.

wiki-scrape — Skill for Claude Code and Codex by PLATZDORSCH

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 PLATZDORSCH/wiki-hermes --skill wiki-scrape

Clone the repo

git clone --depth 1 https://github.com/PLATZDORSCH/wiki-hermes

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-scrape/github.svg)](https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-scrape)

Your own site

<a href="https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-scrape"><img src="https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-scrape/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-scrape"><img src="https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-scrape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 792 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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00792
Opus 5.5	$0.00011	$0.00317
Sonnet 5.5	$0.00005	$0.00158
Haiku 4.5	$0.00003	$0.00079

Measured 2mo ago against content hash 2b2ac19d3423, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wiki-scrape 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.

skills/wiki-scrape/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-scrape

Scrape eine URL, konvertiere den Inhalt zu Markdown und speichere ihn als Quelle in raw/articles/.

When to Use

User gibt eine URL und will den Inhalt ins Wiki aufnehmen
User sagt "lies diesen Artikel", "scrape das", "nimm das auf" o.ä.
User teilt einen Link per Telegram, Discord oder Chat

Procedure

URL entgegennehmen — URL vom User übernehmen. Falls mehrere URLs: einzeln nacheinander verarbeiten.
Inhalt abrufen — URL fetchen und Inhalt zu sauberem Markdown konvertieren:
- HTML-Boilerplate entfernen (Navigation, Footer, Ads, Cookie-Banner)
- Hauptinhalt extrahieren (Artikel-Body)
- Überschriften, Listen, Links, Bilder und Code-Blöcke beibehalten
- Bilder-URLs als Markdown-Links belassen (nicht herunterladen)
Metadaten extrahieren — Aus der Seite extrahieren:
- Titel
- Autor (falls vorhanden)
- Veröffentlichungsdatum (falls vorhanden)
- URL als Quellenangabe
Als Markdown speichern — Datei in raw/articles/ ablegen:
- Dateiname: YYYY-MM-DD-kurztitel.md (lowercase, Bindestriche, keine Umlaute)
- Frontmatter am Anfang der Datei:
```
---
title: "Originaltitel des Artikels"
url: "https://example.com/artikel"
author: "Name"
published: YYYY-MM-DD
scraped: YYYY-MM-DD
---
```
- Danach der konvertierte Markdown-Inhalt
User kurz informieren — Titel, Dateiname und geschätzte Länge (Wörter) bestätigen.
⛔ Ingest ausführen — Direkt den vollständigen wiki-ingest Workflow ausführen (Schritte 1–10 aus wiki-ingest). Der Ingest ist der DEFAULT — nur überspringen wenn der User explizit sagt, dass er nicht ingestieren will. Scrape ohne Ingest ist ein halber Job.

Pitfalls

Paywalled oder Login-geschützte Seiten können nicht gescrapt werden — User darauf hinweisen
Sehr lange Artikel vollständig speichern, nicht kürzen — das Kürzen passiert beim Ingest
PDFs nicht über diesen Skill verarbeiten — dafür direkt in raw/pdfs/ ablegen
Cookie-Consent-Banner, Werbung und Navigation sauber entfernen
Bei Scraping-Fehlern den User informieren und alternative Vorgehensweisen vorschlagen (z.B. manuell kopieren nach raw/notes/)
⛔ NIEMALS den Ingest-Schritt vergessen — Scrape ohne Ingest lässt die Quelle unverarbeitet in raw/ liegen

Read the full file on GitHub · 74 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.

2mo ago First seen · 74 lines · 27 tokens per session scan A 2b2ac19d3423

Subscribe to this mod's changes

wiki-scrape is a skill published in the GitHub repository PLATZDORSCH/wiki-hermes (10 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 792 once invoked, about $0.0001 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 2026-08-31.

Research

wiki-scrape next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wiki-scrapePLATZDORSCH/wiki-hermes	Skill	10	7mo ago	MIT	A	27	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

wiki-scrape

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

wiki-scrape

When to Use

Procedure

Pitfalls

What this file has done since we first saw it

wiki-scrape compared with skills from other repositories