research

A command for structured legal research using verified German and European laws and court decisions, with footnote citations.

In plain words
What is it for?
It is for researching questions about areas such as the GDPR, German civil law, online contracts, and cross-border data transfers.
Why use it?
It helps separate quoted legal text from the explanation applied to a question, while keeping the research tied to selected jurisdictions.

Command

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.

agentmods
npx agentmods add commands/planit-tech/primamcp/research
Clone the repo
git clone --depth 1 https://github.com/PLANIT-TECH/primamcp
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00674
Opus 5 $0.00009 $0.00337
Sonnet 5 $0.00004 $0.00135
Haiku 4.5 $0.00002 $0.00067

Measured 2d ago against content hash 52e6ac897cc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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 2d 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.

plugins/claude/primamcp/commands/research.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/primamcp:research

Führt eine strukturierte Rechtsrecherche durch — mit Pflicht zur Tool-Nutzung, Fußnoten-Zitaten und sauberer Trennung von wörtlichem Zitat (Block-Quote) und eigener Subsumtion.

Nutzung

/primamcp:research <Frage> [jurisdiction=DE+EU] [depth=thorough]
  • Frage: natürlichsprachlich. Z. B. „Welche Pflichten hat ein Verantwortlicher bei einem Datenleck nach DSGVO?"
  • jurisdiction: DE (nur deutsches Bundesrecht), EU (nur EU-Recht), DE+EU (beides — Default).
  • depth: thorough (Default — volle Kommentierung) oder quick (3–5 Sätze Kernaussagen).

Beispiele

/primamcp:research Voraussetzungen für eine Schmerzensgeldforderung nach § 253 BGB
/primamcp:research Drittlandübermittlung personenbezogener Daten jurisdiction=EU
/primamcp:research Widerrufsrecht bei Fernabsatzverträgen jurisdiction=DE+EU depth=thorough

Workflow (was PRIMAMCP im Hintergrund macht)

  1. Frage zerlegt — relevante Rechtsdomäne identifiziert; bei Unsicherheit legal://rechtsrahmen konsultiert (Domain → Gesetze).
  2. Suchelegal_search mit natürlichsprachlicher Query; source_type passt zur jurisdiction (gii = DE-Bundesrecht, eurlex = EU, eurlex_caselaw = EuGH).
  3. Verifikation — jede Norm, die zitiert werden soll, mit legal_lookup (oder legal_lookup_batch für 2+) auf den Volltext geprüft.
  4. Kontext — bei zentralen Normen legal_get_context für umliegende Paragrafen (Auslegungs-Kontext).
  5. Auslegungspraxislegal_find_citing_decisions für DE-Bundesgerichte; für EuGH stattdessen legal_search source_type=eurlex_caselaw.
  6. Antwort — strukturiert in Zusammenfassung / Rechtliche Würdigung / Quellen, Fußnoten [1], [2] mit Norm-Kürzel + Stand + URL.

Hard rules

  • Keine fiktiven Quellen. Wenn legal_lookup found=false liefert, mit legal_search als Fallback suchen — sonst „Fundstelle nicht auffindbar" sagen.
  • Keine ungesicherten Aussagen. Was nicht im Tool-Output steht, kommt nicht in die Antwort.
  • Keine Rechtsberatung. PRIMAMCP liefert verifizierte Rechtsinformation, nicht Rechtsberatung im Sinne des RDG. Bei konkreter Beratung Hinweis auf Anwalt/Anwältin.

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 18 tokens per session scan A 52e6ac897cc9

Subscribe to this mod's changes

research is a command published in the GitHub repository PLANIT-TECH/primamcp (10 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 674 once invoked, about $0.0001 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.