agentmods.dev

wiki-ingest

wiki-ingest is a skill for Claude Code, Codex from PLATZDORSCH/wiki-hermes. It costs 18 tokens per session (1,061 once invoked), scanned A, original, MIT.

A workflow for reading a new source, such as a file, web page, note, or PDF, and adding its useful knowledge to a wiki. The German instructions mean “process a new source and integrate the knowledge into the wiki.”

In plain words
What is it for?
Use it to ingest sources, write summaries, update related wiki pages, add links, and record contradictions.
Why use it?
It keeps new research organized, connected to existing pages, and marked when it conflicts with earlier information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

not rated 10repo 7mo ago A scan 18 tokens original MIT

Good fit Use it to ingest sources, write summaries, update related wiki pages, add links, and record contradictions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/platzdorsch/wiki-hermes/wiki-ingest
View source ↗ PLATZDORSCH/wiki-hermes platzdorsch.de
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-ingest
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.

agentmods badge for wiki-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-ingest/github.svg)](https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-ingest)
Your own site
<a href="https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-ingest"><img src="https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-ingest/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 wiki-ingest

Your own site · 80×15
<a href="https://agentmods.dev/skills/platzdorsch/wiki-hermes/wiki-ingest"><img src="https://agentmods.dev/badge/skills/platzdorsch/wiki-hermes/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 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 $0.00018 $0.01061
Opus 5.5 $0.00007 $0.00424
Sonnet 5.5 $0.00004 $0.00212
Haiku 4.5 $0.00002 $0.00106

Measured 2mo ago against content hash 33034b49ca6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wiki-ingest 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-ingest/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-ingest

Verarbeite eine neue Quelle und integriere das Wissen ins Wiki.

When to Use

  • Neue Datei wurde in raw/ abgelegt
  • User gibt eine URL oder Text zum Verarbeiten
  • User sagt "ingest", "verarbeite", "lies das" o.ä.

Procedure

  1. Quelle lesen — Datei lesen, URL scrapen oder Text übernehmen. Bei PDFs: Text extrahieren.

  2. Aktuellen Wissensstand erfassen — wiki/index.md lesen, um zu verstehen was bereits im Wiki existiert.

  3. Summary erstellen — Neue Seite in wiki/sources/ anlegen:

    ---
title: "Titel der Quelle"
category: sources
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: [relevante, tags]
source_type: article|pdf|note|web
source_path: raw/articles/dateiname.md
ingested: YYYY-MM-DD
status: active
---

    Danach: Zusammenfassung der Kernaussagen, wichtigste Fakten, Zitate.

  4. Kernaussagen mit User besprechen — Kurz die 3–5 wichtigsten Takeaways auflisten. Fragen ob der User Schwerpunkte setzen will.

  5. Bestehende Wiki-Seiten aktualisieren — Für jede relevante bestehende Seite:

    • Neue Informationen einarbeiten
    • Widersprüche mit > ⚠️ Widerspruch: ... markieren
    • Neue Querverweise setzen (relative Markdown-Links)

  6. Neue Seiten anlegen — Falls die Quelle Themen, Trends, Player oder Konzepte enthält die noch keine eigene Seite haben, neue Seiten erstellen in den passenden Unterordnern. Frontmatter-Konventionen aus AGENTS.md beachten.

  7. Verwandte Seiten verlinken — Jede neue/aktualisierte Seite braucht einen "Verwandte Seiten"-Abschnitt am Ende. Links MÜSSEN kategorieübergreifend sein (siehe Pflicht-Verlinkungstabelle in AGENTS.md): Sources verlinken auf Topics/Trends/Players, Topics verlinken zurück auf Sources und auf verwandte Trends/Players, usw. Verlinkungen sind bidirektional — wenn A auf B verlinkt, MUSS B auch auf A verlinken. In bestehenden Seiten Rückverweise ergänzen.

  8. ⛔ Index aktualisieren — wiki/index.md LESEN und PRÜFEN. Alle neuen Seiten eintragen. Format: - [Titel](pfad) — Kurzbeschreibung (X Quellen)

Read the full file on GitHub · 86 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. 2mo ago First seen · 86 lines · 18 tokens per session scan A 33034b49ca6d

Subscribe to this mod's changes

wiki-ingest is a skill published in the GitHub repository PLATZDORSCH/wiki-hermes (10 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 1,061 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.

ResearchWriting and docs
Related

wiki-ingest compared with skills from other repositories

wiki-ingest next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wiki-ingestPLATZDORSCH/wiki-hermesSkill107mo agoMITA18Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code