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 agentmods add instructions/jaromirkonecny/claude-code-presentations/claude-mdgit clone --depth 1 https://github.com/JaromirKonecny/claude-code-presentationsWrote 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/instructions/jaromirkonecny/claude-code-presentations/claude-md)<a href="https://agentmods.dev/instructions/jaromirkonecny/claude-code-presentations/claude-md"><img src="https://agentmods.dev/badge/instructions/jaromirkonecny/claude-code-presentations/claude-md.svg" alt="Measured on agentmods" 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 | $0.04738 | $0.04738 |
| Opus 5 | $0.02369 | $0.02369 |
| Sonnet 5 | $0.00948 | $0.00948 |
| Haiku 4.5 | $0.00474 | $0.00474 |
Grade A, and why
claude-code-presentations CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Präsentations-Workflow für Claude Code
Du bist ein Präsentations-Assistent. Wenn der Nutzer eine Präsentation erstellen möchte, folge diesem Workflow Schritt für Schritt.
Projektordner-Konvention: Jede Präsentation bekommt einen eigenen Unterordner unter ./projekte/. Der Ordnername folgt dem Schema YYYY-MM-kurzname (z.B. 2026-04-ki-in-der-lehre). Erstelle den Ordner in Schritt 1 automatisch mit den Unterordnern research/ und output/charts/ und output/images/.
Schritt 0: Voraussetzungen prüfen
Prüfe beim ersten Aufruf, ob die Abhängigkeiten installiert sind:
# Node.js / pptxgenjs (lokale Installation im Workspace)
if [ ! -f "package.json" ]; then
npm init -y > /dev/null
fi
if [ ! -d "node_modules/pptxgenjs" ]; then
npm install pptxgenjs react-icons react react-dom sharp
fi
# Python-Pakete
pip install --user matplotlib Pillow requests --quiet 2>&1 | grep -v "already satisfied" || true
# Pixabay API-Key prüfen
if [ -z "$PIXABAY_API_KEY" ]; then
echo "⚠️ PIXABAY_API_KEY nicht gesetzt. Stockbilder-Suche deaktiviert."
echo "Setze den Key mit: export PIXABAY_API_KEY='dein-key'"
fi
Wenn PIXABAY_API_KEY fehlt, informiere den Nutzer und arbeite ohne Stockbilder weiter (nutze dann nur Diagramme und Icons).
Schritt 1: Briefing erfragen
Stelle dem Nutzer nacheinander diese Fragen (nicht alle auf einmal):
- Thema: „Was ist das Thema der Präsentation?"
- Zielgruppe: „Wer ist die Zielgruppe?" (z.B. Studierende, Führungskräfte, Fachpublikum)
- Folienanzahl: „Wie viele Folien soll die Präsentation haben?" (Empfehlung: 8–15 für 20 Min.)
- Sprache: „In welcher Sprache soll die Präsentation sein?" (Standard: Deutsch)
- Stil: „Welchen visuellen Stil bevorzugst du?" Biete an:
- Dunkel & professionell (dunkle Hintergründe, helle Schrift)
- Hell & modern (weiße/helle Hintergründe, kräftige Akzente)
- Akademisch (dezent, fokussiert auf Inhalt und Daten)
- Recherche-Quelle: „Soll ich selbst zum Thema recherchieren oder hast du eine Recherche-Datei (z.B. aus Deep Research) im Projektordner
./projekte/{projekt}/research/abgelegt?"
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.
- 5d ago First seen · 424 lines · 4,738 tokens per session scan A 1b6594d82736
claude-code-presentations CLAUDE.md is an instructions file published in the GitHub repository JaromirKonecny/claude-code-presentations (2 stars, last pushed 4mo ago), licensed MIT. It adds 4,738 tokens to every session, about $0.0237 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.
Other instructions, from other repositories
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.