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.
npx skills add daringanitch/claude-stock-analyst --skill etf-comparegit clone --depth 1 https://github.com/daringanitch/claude-stock-analystWrote 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.
[](https://agentmods.dev/skills/daringanitch/claude-stock-analyst/etf-compare)<a href="https://agentmods.dev/skills/daringanitch/claude-stock-analyst/etf-compare"><img src="https://agentmods.dev/badge/skills/daringanitch/claude-stock-analyst/etf-compare/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.
<a href="https://agentmods.dev/skills/daringanitch/claude-stock-analyst/etf-compare"><img src="https://agentmods.dev/badge/skills/daringanitch/claude-stock-analyst/etf-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00401 |
| Opus 5 | $0.00019 | $0.00200 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
etf-compare 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 10d 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.
What it actually says
Run a side-by-side comparison of the ETFs provided. Structure:
1. WHAT EACH ONE IS One sentence per ETF: strategy, index tracked, issuer.
2. SIDE-BY-SIDE SCORECARD
| Metric | [ETF 1] | [ETF 2] |
|---|---|---|
| AUM | ||
| Expense ratio | ||
| # of holdings | ||
| Top holding (% weight) | ||
| Top 10 as % of portfolio | ||
| 1yr return | ||
| 3yr annualized | ||
| Beta vs S&P 500 | ||
| Avg daily volume |
3. OVERLAP ANALYSIS
- What % of holdings do they share?
- If overlap >70%: flag — owning both is redundant
- Where they diverge: what does one own that the other doesn't?
4. WHAT YOU'RE ACTUALLY CHOOSING BETWEEN
- Is this a cost decision? (same exposure, different fee)
- Is this a conviction decision? (different index methodology = different bet)
- Is this a liquidity decision? (one trades much more thinly)
- Is this a tax decision? (different distribution behavior)
5. FACTOR DIFFERENCES Which ETF loads more heavily on: growth / value / momentum / quality / size? Under what market conditions does each outperform the other?
6. VERDICT: WHICH ONE AND WHY Give a clear recommendation. If the answer is genuinely "it depends," explain on what — don't hedge without a reason.
If the user provides more than 2 ETFs, run the comparison as a ranked table and eliminate the weakest option first with a clear explanation.
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.
- 10d ago First seen · 44 lines · 39 tokens per session scan A 36f2cae4cefa
etf-compare is a skill published in the GitHub repository daringanitch/claude-stock-analyst (9 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 401 once invoked, about $0.0002 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.
Other skills, from other repositories
equity-research
A Chinese-language guide for researching and valuing a publicly traded company's stock. It describes how to produce an institutional-style equity research report covering evidence, valuation, risks, expectations, and possible investment actions.
serenity-chokepoint-investing
Analyze public equities and sectors using the Serenity-style AI supply-chain chokepoint investing framework. Best for AI infrastructure, semiconductors, optical communications, data center power, storage, cooling, robotics, and industrial supply-chain bottleneck research.
grayscale-crypto-sectors
Use when evaluating crypto through a Grayscale-style Crypto Sectors lens: sector taxonomy, FTSE/Grayscale index eligibility, fee/usage fundamentals, sector-share valuation, ETP/trust wrappers, and Zcash-style privacy-as-money theses.
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
buffett
Use when evaluating a business through Buffett-style ownership, owner earnings, durable moat, management quality, capital allocation, and margin-of-safety judgment.
darvas-box
Use when evaluating Nicolas Darvas-style box breakouts, new-high momentum, volume confirmation, and mechanical stop placement for liquid growth stocks.