By fedec65
Swiss legal intelligence for precedent research, case strategy, legal drafting, and citation verification across all 26 cantons with attorney-client privilege protection.
Check MCP server connectivity
Run three-agent adversarial analysis -- advocate builds the case, adversary challenges it, judicial analyst synthesizes
Structured pre-execution briefing session -- collects case context through specialist panel, builds execution plan, supports resume and depth control
Analyze cantonal law for all 26 Swiss cantons -- cantonal court decisions, cantonal legislation, procedural specifics, and interaction with federal law
Validate, format, and look up Swiss legal citations including BGE/ATF/DTF decisions and statutory references
Challenges a legal position by finding weaknesses, counter-precedents, and opposing arguments under Swiss law
Builds the strongest possible case in favor of a legal position using Swiss law precedents, statutory provisions, and doctrine
Pre-execution briefing session that collects case context through multi-agent panel consultation, builds a structured execution plan, and persists state for cross-session recovery
Analyzes law across all 26 Swiss cantons including cantonal constitutions, court systems, intercantonal concordats, procedural variations, and multi-canton comparisons
Verifies, formats, and converts Swiss legal citations across BGE/ATF/DTF, cantonal decisions, and statutory references in DE/FR/IT
Swiss adversarial legal analysis — stress-tests any legal position by running three independent agents: Advocate (strongest case FOR), Adversary (strongest case AGAINST), and Judicial synthesizer (Erwägung-style balanced conclusion with probability). Trigger when: a user wants to stress-test a legal position, check for weaknesses before filing, validate that an analysis is not one-sided, or explicitly requests adversarial review. Also triggered as option '4' in the /legal post-execution framework menu. Invoked via /bettercallclaude:adversarial. Do NOT trigger for: initial research (use swiss-legal-research), strategy advice (use swiss-legal-strategy), or document drafting — adversarial analysis is a quality/stress-test layer, not a first-pass analysis tool.
Swiss financial regulatory compliance analysis — assesses and maps compliance obligations under FINMA supervision, GwG/LBA (AML/KYC), FIDLEG/LSFin (financial services), FINIG/LEFin (financial institution licensing), BankG (banking secrecy), crypto/DLT regulation (DLT-Gesetz / Mantelerlass amending OR/FinfraG/BankG/GwG, FINMA ICO/staking guidance), nDSG data processing in fintech, and cross-border obligations (AEOI/CRS, FATCA/QI, EU market access). Trigger when: a user asks 'do we need a FINMA license', 'are we compliant with GwG/AML', 'what are the KYC requirements', 'can we offer financial services cross-border', 'what does FINMA require for crypto/DLT/tokens', 'is our data processing compliant for fintech'; or when the compliance-officer agent is invoked. Also use for FINIG licensing gap analysis and remediation planning. Do NOT trigger for: general corporate law questions (use corporate-law-agent); data protection not specific to financial services (use data-protection-specialist); tax/transfer-pricing (use fiscal-legal-expert); cantonal commercial registry or zoning (use cantonal skill).
Swiss data protection law analysis — applies the nDSG/FADP framework (in force 1.9.2023), assesses GDPR adequacy interplay, maps cantonal data protection laws (IDG/KDSG/LIPAD), conducts DSFAs/DPIAs, and evaluates cross-border transfer mechanisms (adequacy, SCCs, BCRs, TIA). Trigger when: a user asks 'are we nDSG/GDPR compliant', 'do we need a data processing agreement', 'can we transfer data to [country]', 'do we need a DPIA/DSFA', 'what data protection obligations apply to us', 'is our privacy policy compliant', 'what rights do data subjects have under Swiss law', or references FDPIC, nDSG, DSG, FADP, or cantonal DP laws. Also triggered when the data-protection agent is invoked. Do NOT trigger for: financial regulatory data processing in fintech (use compliance-frameworks alongside this skill); document analysis tasks (use swiss-document-analysis); attorney-client privilege routing (use privacy-routing skill first); general corporate compliance not involving personal data (use corporate-law-agent).
BetterCallClaude 5-step Swiss legal framework — an end-to-end pipeline that chains five agents sequentially: (1) doc-analyze for intake and fact extraction, (2) swiss-legal-research for precedent and statute lookup via BGE/ATF/DTF, fedlex-sparql, entscheidsuche, and onlinekommentar MCP servers, (3) swiss-legal-strategy for claim strength, risk matrix, and settlement evaluation, (4) adversarial-analysis for three-agent Erwägung-style stress test, (5) swiss-legal-drafting for verified document production. Trigger when: a user invokes /bettercallclaude:legal-5step, asks to run the full framework on a case, wants a complete legal analysis from intake to draft, or says 'run all steps', 'full pipeline', 'end-to-end analysis', or 'complete legal workflow'. Do NOT trigger for: single-step tasks (use the individual command: research, strategy, adversarial, draft, or doc-analyze), citation-only work (use swiss-citation-formats), quick legal questions (use swiss-legal-research directly), or translation only (use swiss-legal-translation). Boundary with /bettercallclaude:workflow: the workflow command executes predefined pipelines (litigation-prep, due-diligence, etc.); legal-5step is a fixed five-step framework that always runs the same sequence and is optimized for repeatable client intake.
Proactively suggests or activates a structured briefing session before executing complex Swiss legal queries. Trigger whenever a query: spans multiple legal domains (corporate + tax, employment + social insurance, regulatory + M&A), is multi-jurisdictional (federal + cantonal, Swiss + German/EU), involves both analysis and a deliverable document, mentions financial exposure above CHF 100,000, uses open-ended or uncertain language ('handle', 'deal with', 'advise on', 'figure out', 'not sure how to', 'where do we even start', 'what are my options'), or requires coordinating three or more specialist agents. Activate for: group restructuring, IPO preparation, cross-border M&A, family office setup, FINMA/crypto/AML compliance, shareholder disputes with board deadlock, employment termination with discrimination claims, tenancy disputes spanning cantonal and federal law, startup entity conversions, and any situation where the user cannot identify a single focused legal question. Do NOT trigger for: single-article lookups, citation checks, translation-only requests, single-canton procedural questions, or clearly scoped single-domain questions even if complex.
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
api_tokenOptional bearer token for accessing a protected BetterCallClaude MCP deployment. Leave blank for the public service.
${user_config.api_token}ollama_hostURL of the Ollama host used by the bundled ollama MCP server for local-only translation and summarisation.
${user_config.ollama_host}privacy_modePrivacy routing mode: strict (same pattern matching as balanced but blocks instead of prompting — non-privileged content passes through, only Ollama exempt from all checks), balanced (prompt on privilege markers), or cloud (prompt on strong markers only, weak signals pass through).
${user_config.privacy_mode}output_languagePreferred output language for agents and drafter output. One of: DE, FR, IT, EN.
${user_config.output_language}default_jurisdictionDefault Swiss canton code for cantonal research (e.g. ZH, BE, GE, TI, VD). Leave blank for federal-only queries.
${user_config.default_jurisdiction}Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Swiss Legal Intelligence Plugin for Cowork Desktop
BetterCallClaude transforms legal research, case strategy, and document drafting for Swiss lawyers. It provides deep integration with Swiss legal databases, multi-lingual analysis (DE/FR/IT/EN), and built-in Anwaltsgeheimnis (attorney-client privilege) protection -- 20 agents, 21 commands, 15 skills, and 9 MCP servers covering BGE/ATF/DTF precedent research, litigation strategy, adversarial analysis, legal drafting, citation verification, document intelligence, and CAS/TAS sports arbitration across all 26 Swiss cantons.
Claude Code CLI users: this repository is Cowork Desktop only. The CLI version is at fedec65/bettercallclaude-cli.
BetterCallClaude provides a structured methodology for handling legal work with AI assistance. The framework consists of five interconnected phases.

v4.7.0 — Plugin scope enforcement. All 17 legal commands now include an explicit instruction that legal work (research, strategy, drafting, translation, citation, adversarial analysis) must use exclusively BetterCallClaude agents, skills, and MCP servers. This prevents Claude from delegating legal tasks to generic or external skills outside the plugin. Infrastructure operations (file generation via pandoc, file reading, computation) remain exempt.
legal, legal-5step, draft, research, strategy, adversarial, translate, cite, validate, doc-analyze, summarize, workflow, refine, briefing, cantonal, federal, precedent.Content counts: 20 agents, 21 commands, 15 skills, 9 MCP servers in .mcp.json (7 remote HTTP on mcp.bettercallclaude.ch + swiss-caselaw SSE on mcp.opencaselaw.ch + ollama local STDIO).
Cowork Desktop dedicated release -- This repository is exclusively for Claude Cowork Desktop. The Claude Code CLI version is at fedec65/bettercallclaude-cli.
mcp.bettercallclaude.ch / mcp.opencaselaw.ch -- no local Node.js build required for thoseollama): bundled and only touches http://localhost:11434 for privacy-routed translation/summarisation/setup checks connectivity only -- no transport switching needed in CoworkFull installation guide with screenshots: BetterCallClaude Tutorial →
fedec65/bettercallclaude and click SyncMCP servers connect automatically via HTTP. No Node.js, no local setup, no API keys required.
npx claudepluginhub fedec65/bettercallclaude --plugin bettercallclaudeIntelligenza Legale Italiana -- Ricerca sui precedenti della Cassazione, strategia di causa, redazione legale e verifica delle citazioni in tutte le 20 regioni italiane con assistenza al rilevamento del segreto professionale (Art. 622 CP).
Spain Legal Intelligence -- TS/AP/STS/STC precedent research, case strategy, legal drafting, and citation verification across all 17 Autonomous Communities with secreto profesional privacy protection.
Intelligenza Legale Italiana — Ricerca sui precedenti della Cassazione, strategia di causa, redazione legale e verifica delle citazioni in tutte le 20 regioni italiane con protezione privacy GDPR e segreto professionale.
Civil legal aid and court self-help — eligibility screening, structured intake, jurisdiction-aware drafting, managing-attorney review, and rolling case transfers — built within ABA Formal Op. 512 and LSC program rules.
Finds, evaluates, and installs community legal skills — with a security review gate before anything lands in your environment.
Intelligenza Legale Italiana -- Ricerca sui precedenti della Cassazione, strategia di causa, redazione legale e verifica delle citazioni in tutte le 20 regioni italiane con assistenza al rilevamento del segreto professionale (Art. 622 CP).
Drills Socratically, briefs cases, builds outlines, runs bar prep sessions tuned to your jurisdiction, grades IRAC practice, and plans the study schedule — without ever writing it for you.
Legal Operations and Compliance: 1 agent, 6 skills (1 router + 5 products), 6 jurisdiction overlays (UK, EU, US, Pakistan, UAE, GCC). Extends Anthropic's built-in Legal Plugin with multi-jurisdiction awareness and domain-specific workflows.
Polish Commercial Legal — Claude skill for drafting and reviewing contracts under Polish civil law. Focused on B2B, IP and IT contracts (body leasing, NDAs, IT implementation, SaaS, IP assignment, settlements). Built from the practice of Zurawska Piotrowski Law Firm (ktzr.pl). Use when the user asks to analyze a Polish contract, audit contract risks, generate a new agreement, edit a clause, or check contract consistency.