agentmods.dev

ucits-etf-chooser

ucits-etf-chooser is a skill for Claude Code from ferinator/bullrun-mcp. It costs 100 tokens per session (1,684 once invoked), scanned A, original, MIT.

A research skill for comparing European UCITS exchange-traded funds that follow the same index. UCITS is a European fund framework, and an ETF is a fund traded on an exchange.

In plain words
What is it for?
It is for comparing funds tracking indexes such as MSCI World, S&P 500, FTSE All-World, Nasdaq-100, and MSCI Emerging Markets.
Why use it?
It helps investors compare fees, fund identity, share classes, listings, overlap, and missing data without mistaking multiple listings for separate funds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the bullrun plugin — 2 skills, 1 MCP server shipped together

not rated 0repo 8d ago A scan 100 tokens original MIT

Good fit It is for comparing funds tracking indexes such as MSCI World, S&P 500, FTSE All-World, Nasdaq-100, and MSCI Emerging Markets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ferinator/bullrun-mcp/ucits-etf-chooser
View source ↗ ferinator/bullrun-mcp bull-run.org
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 ferinator/bullrun-mcp --skill ucits-etf-chooser
Clone the repo
git clone --depth 1 https://github.com/ferinator/bullrun-mcp

Made for: Claude Code.

Or install bullrun, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 ucits-etf-chooser

README.md
[![agentmods](https://agentmods.dev/badge/skills/ferinator/bullrun-mcp/ucits-etf-chooser/github.svg)](https://agentmods.dev/skills/ferinator/bullrun-mcp/ucits-etf-chooser)
Your own site
<a href="https://agentmods.dev/skills/ferinator/bullrun-mcp/ucits-etf-chooser"><img src="https://agentmods.dev/badge/skills/ferinator/bullrun-mcp/ucits-etf-chooser/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 ucits-etf-chooser

Your own site · 80×15
<a href="https://agentmods.dev/skills/ferinator/bullrun-mcp/ucits-etf-chooser"><img src="https://agentmods.dev/badge/skills/ferinator/bullrun-mcp/ucits-etf-chooser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,684 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 $0.00100 $0.01684
Opus 5.5 $0.00040 $0.00674
Sonnet 5.5 $0.00020 $0.00337
Haiku 4.5 $0.00010 $0.00168

Measured 15d ago against content hash 7b96c7225029, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ucits-etf-chooser 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 15d 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.

plugin/skills/ucits-etf-chooser/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Choosing between UCITS ETFs on one index

This skill uses the Bullrun connector's ETF tools to compare funds that track the same index. The aim is a dated, sourced comparison the user can check with their broker. It does not pick a fund for them.

Ground rules

  • Count funds, not tickers. One UCITS fund (one ISIN) trades on several exchanges under different tickers. Treat those as one choice. Two listings of the same ISIN are never diversification.
  • Watch for share classes. Share classes of one fund, such as "EUR Capitalisation" and "USD Capitalisation", or hedged and unhedged, have different ISINs but hold the same portfolio. When the cheapest rows are classes of one fund, say so. Count them as one choice, and use the other slot in a shortlist for a different issuer.
  • Fees and yields are percentage points. 0.07 means 0.07% a year, in tool inputs and outputs.
  • Missing means unknown. A fund with no published fee, AUM, holdings or price is reported as missing. It is not "zero" and not "fine". Don't fill gaps from memory.
  • Show disagreements. If two tools report different values for the same fund, for example AUM from get_etf_index_group and from compare_etfs, show both. Don't pick one. AUM currency is often not stored, so don't compare AUM across funds as if it were in one currency.
  • Never guess a filter value. Index keys, categories, exchanges and domiciles match exactly. A wrong string returns zero rows, which looks like "no such fund". Resolve every value first.
  • Prices are stored daily closes, not live quotes. Give the date with every price or return.

Steps

1. Pin down the index and the user's constraints

Work out which index the user means and what they have already said: payout (accumulating or distributing), exchange or trading currency (for example XETRA in EUR, SIX in CHF, LSE in GBP or USD), any AUM floor or issuer preference, and any amount and horizon for a cost estimate. Ask only about things that change the answer, in one short question. Sensible defaults are any payout, any venue, and no cost simulation.

Read the full file on GitHub · 68 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. 15d ago First seen · 68 lines · 100 tokens per session scan A 7b96c7225029

Subscribe to this mod's changes

ucits-etf-chooser is a skill published in the GitHub repository ferinator/bullrun-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 1,684 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-22.

Finance and fintechResearchai-agentsclaudeetfeuropean-stocksfinancial-data
Related

ucits-etf-chooser compared with skills from other repositories

ucits-etf-chooser next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ucits-etf-chooserferinator/bullrun-mcpSkill08d agoMITA100Claude Code
defeatbeta-earnings-analysisdefeat-beta/defeatbeta-apiSkill7957d agoApache-2.0A112Claude Code
tickdb-market-dataTickDB/tickdb-unified-realtime-marketdata-apiSkill91523d agoMITA165Claude Code, Codex
defeatbeta-earnings-previewdefeat-beta/defeatbeta-apiSkill7957d agoApache-2.0A60Claude Code, Codex
sprrwilsonfreitas/awesome-quantSkill30kyesterdaynoneA60Claude Code, Codex
defeatbeta-earnings-key-datadefeat-beta/defeatbeta-apiSkill7957d agoApache-2.0A138Claude Code, Codex
create-entrywilsonfreitas/awesome-quantSkill30kyesterdaynoneA43Claude Code, Codex