ssnip-test-anwendung

ssnip-test-anwendung is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 164 tokens per session (1,128 once invoked), scanned A, original, Apache-2.0.

A market-definition test that asks whether a hypothetical sole seller could profitably raise prices by 5–10 percent for a lasting period. If enough customers would switch to alternatives, the product market is probably defined too narrowly.

In plain words
What is it for?
Use it to define a relevant product market by examining customer switching, substitute products, prices, and the critical-loss calculation.
Why use it?
It provides a structured way to identify which products compete with each other in competition-law analysis. This helps assess questions involving market power, abuse of dominance, and mergers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define a relevant product market by examining customer switching, substitute products, prices, and the critical-loss calculation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung
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 ThomasMoreAI/legal-skills-open --skill ssnip-test-anwendung
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

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 ssnip-test-anwendung

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung/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 ssnip-test-anwendung

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/ssnip-test-anwendung.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 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 $0.00164 $0.01128
Opus 5 $0.00082 $0.00564
Sonnet 5 $0.00033 $0.00226
Haiku 4.5 $0.00016 $0.00113

Measured 9d ago against content hash b8ee43cce73f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ssnip-test-anwendung 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 9d 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.

cross-jurisdiction/antitrust/skills/ssnip-test-anwendung/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SSNIP-Test — Anwendung

Grundprinzip

Der SSNIP-Test (auch: Hypothetischer-Monopolisten-Test, HMT) fragt: Wäre eine kleine, aber spürbare und dauerhafte Preiserhöhung (5–10 Prozent) für einen hypothetischen Monopolisten auf dem zu prüfenden Produktsatz profitabel?

  • Wenn ja: Der Produktsatz bildet einen relevanten Markt.
  • Wenn nein (weil Kunden zu anderen Produkten abwandern): Markt ist zu eng — das nächste Substitut muss einbezogen werden.

Referenz

EU-Kommission, Bekanntmachung zur Marktdefinition 2024, Rn. 14 ff.; Bekanntmachung 1997, Rn. 17; US DOJ/FTC Horizontal Merger Guidelines 2010, § 4.

Schritte der Prüfung

1. Ausgangspunkt bestimmen

  • Welches Produkt/welche Produktgruppe steht im Zentrum?
  • Welcher Preis gilt als Ausgangspreis? (CAVE: bei Kampfpreisen → Cellophane Fallacy)

2. Preiserhöhungsreaktion analysieren

Fragen:

  • Wie viele Kunden würden bei +5 Prozent abwandern?
  • Zu welchem Alternativprodukt würden sie wechseln?
  • Reicht die Abwanderung aus, die Preiserhöhung unrentabel zu machen?

Quantitativer Ansatz — Kritische-Verlust-Analyse:

Kritischer Verlustanteil = m / (m + Δp)
  m = Deckungsbeitrag / Preis (vor Erhöhung)
  Δp = relative Preiserhöhung (z.B. 0,05)

Ist der tatsächliche Verlust kleiner als der kritische Verlust → Erhöhung profitabel → Markt bestätigt.

3. Iteration

Wenn Preiserhöhung nicht profitabel: Nächstes Substitut einbeziehen und Test wiederholen.

4. Cellophane Fallacy

Definition: Wenn ein Anbieter bereits Marktmacht ausübt und der Ausgangspreis überhöht ist, erscheinen Substitute als austauschbar — obwohl sie bei Wettbewerbspreis keine wären.

Prüfung: Liegen Anhaltspunkte für bereits überhöhte Ausgangspreise vor? Wenn ja: SSNIP-Test muss auf Wettbewerbspreisbasis korrigiert werden.

Leitfälle:

  • EuGH, Rs. 85/76 — Hoffmann-La Roche: Vitaminmärkte.
  • EuGH, Rs. 27/76 — United Brands: Ausgangspreis-Problematik bei Bananenmarkt.

5. Grenzen des SSNIP-Tests

  • Zwei-/Mehrseitige Märkte: Preiserhöhung auf einer Marktseite kann durch Netzwerkeffekte konterkariert werden.
  • Regulierte Preise: Test auf Basis regulierter Preise setzt falsche Ausgangspunkte.
  • Innovationsmärkte: Nicht-Preis-Parameter dominieren.

Read the full file on GitHub · 89 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. 9d ago First seen · 89 lines · 164 tokens per session scan A b8ee43cce73f

Subscribe to this mod's changes

ssnip-test-anwendung is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 164 tokens to every session and 1,128 once invoked, about $0.0008 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 2026-09-03.