gsd-domain-researcher

gsd-domain-researcher is an agent for Claude Code from swisstruthorg/swiss-truth-mcp. It costs 77 tokens per session (1,422 once invoked), scanned A, original, no licence file.

An agent that researches the real-world field and business context of an AI system before its evaluation criteria are written.

In plain words
What is it for?
It identifies domain experts’ criteria, field-specific risks, regulatory context, and definitions of good performance for later use in measurable evaluation rubrics.
Why use it?
It helps prevent AI evaluations from ignoring industry expectations, practical failure modes, or relevant regulations.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It identifies domain experts’ criteria, field-specific risks, regulatory context, and definitions of good performance for later use in measurable evaluation rubrics.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/swisstruthorg/swiss-truth-mcp

Made for: Claude Code.

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 gsd-domain-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher/github.svg)](https://agentmods.dev/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher)
Your own site
<a href="https://agentmods.dev/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher"><img src="https://agentmods.dev/badge/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher/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 gsd-domain-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher"><img src="https://agentmods.dev/badge/agents/swisstruthorg/swiss-truth-mcp/gsd-domain-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,422 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 unknown 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 $0.00077 $0.01422
Opus 5 $0.00039 $0.00711
Sonnet 5 $0.00015 $0.00284
Haiku 4.5 $0.00008 $0.00142

Measured 11d ago against content hash f240721e61ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gsd-domain-researcher 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 11d 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.

.claude/agents/gsd-domain-researcher.md · 154 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 11d ago First seen · 154 lines · 77 tokens per session scan A f240721e61ce

Subscribe to this mod's changes

gsd-domain-researcher is an agent published in the GitHub repository swisstruthorg/swiss-truth-mcp (0 stars, last pushed 4mo ago), with no licence file. It adds 77 tokens to every session and 1,422 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

kyc-screener

Parses an onboarding document packet, runs the firm's KYC/AML rules engine, screens against sanctions and PEP lists, and flags gaps for escalation. Use for new-client onboarding or periodic refresh — not for transaction monitoring.

anthropics/financial-services · 51 tokens

fiscal-legal-expert

Analyzes Swiss federal and cantonal tax implications including DBG/LIFD, StHG/LHID, MWSTG/LTVA, double taxation agreements, transfer pricing, and BEPS compliance.

fedec65/bettercallclaude · 46 tokens

customs-duty-drawback-specialist

Duty drawback specialist for co-export. Determines whether raw materials used in an export are eligible for duty refund under the Act on Special Cases Concerning the Refund of Customs Duties Levied on Raw Materials for Export (the Duty Drawback Act), selects the applicable refund method (individual refund vs.…

5throck/ai-workspace-standards · 129 tokens

hs-classification-specialist

HS code classification, customs valuation, and tariff rate determination specialist for co-export. Classifies goods under the Harmonized System per the home jurisdiction's customs legislation (see the active country profile under docs/countries/) and the WCO HS nomenclature, determines applicable tariff rates, and…

5throck/ai-workspace-standards · 109 tokens

risk-manager

Use this agent when you need comprehensive risk assessment, mitigation planning, or compliance guidance. Examples include:\n\n \nContext: User is implementing a new feature that handles sensitive financial data.\nuser: "I'm building a payment processing module that will handle credit card transactions. Can you help me…

SoundDocs/sounddocs · 0 tokens

ecd-escrituracao-contabil-digital

Especialista em ECD anual (SPED Contábil) — Diário, Razão, Balancetes — IN RFB 2.003/2021, transmissão até 31/05, validação no PVA, plano de contas com referencial 100%, autenticação automática Junta Comercial. Use proativamente quando o usuário (a) prepara ECD anual, (b) menciona PVA EFD-Contábil, plano referencial…

asv-digital/agents-contadores · 0 tokens