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 cbetz/trove --skill hcris-analystgit clone --depth 1 https://github.com/cbetz/troveWrote 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/cbetz/trove/hcris-analyst)<a href="https://agentmods.dev/skills/cbetz/trove/hcris-analyst"><img src="https://agentmods.dev/badge/skills/cbetz/trove/hcris-analyst/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/cbetz/trove/hcris-analyst"><img src="https://agentmods.dev/badge/skills/cbetz/trove/hcris-analyst.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 | $0.00107 | $0.01835 |
| Opus 5 | $0.00053 | $0.00918 |
| Sonnet 5 | $0.00021 | $0.00367 |
| Haiku 4.5 | $0.00011 | $0.00184 |
Grade A, and why
hcris-analyst 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hcris-analyst
A skill for analyzing U.S. nonprofit hospital financials. Powered by the trove project's parsed HCRIS Hospital 2552-10 data and IRS 990 Schedule H filings, published as Parquet bundles at troveproject.com.
When to use this skill
Invoke when the user asks about:
- A specific hospital's profile — beds, revenue, charity care, ownership, etc. Identifiers are CCN (HCRIS, 6-char) or EIN (IRS, 9-char) or hospital name.
- Peer context — how does X look alongside similar hospitals.
- Field-glossary lookups — what does Worksheet S-X line Y column Z mean.
- Cross-form charity-care differences — the difference between HCRIS Worksheet S-10 charity care cost and IRS Schedule H Part I line 7a financial assistance at cost.
- Top-N descriptive queries — largest by some metric, most uncompensated care, etc., when explicitly requested.
- Schedule H amendments — has a particular EIN been amended across IRS release years.
- NL → DuckDB SQL — translate ad-hoc questions into queries over the bundles.
Don't use this skill for
- Questions about hospitals not in the U.S. (HCRIS is CMS / Medicare-specific).
- For-profit and government hospitals that don't file 990s — they're in HCRIS but not in the matched CMS+IRS dataset. The skill can answer HCRIS-only questions about them.
- Patient-level outcomes, quality metrics, or readmission rates — those live in CMS Care Compare / Hospital Compare, not HCRIS. Tell the user the data source they want is elsewhere.
- Drug-approval questions — those belong to the sibling
fda-analystskill, which ships in the same trove plugin and covers FDA novel drug approvals 2021–2024 (CDER NMEs and novel BLAs plus CBER cell and gene therapies). Hand the question over rather than answering it from here.
How to query
The data lives as Parquet bundles served over HTTPS from troveproject.com. DuckDB can query them directly. Two execution paths:
- Bash + DuckDB CLI:
duckdb -c "SELECT ... FROM read_parquet('https://troveproject.com/data/...')" - Python:
import duckdb; duckdb.sql("...").df()
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 77 lines · 107 tokens per session scan A 02f23f12f2f2
hcris-analyst is a skill published in the GitHub repository cbetz/trove (3 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,835 once invoked, about $0.0005 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
hithink-finance-symbol
A command-line tool entry for matching stock or index names, short codes, and tickers to their official identifiers. An identifier is the code needed by later market-data commands.
comptable
Comptabilité, fiscalité et facturation pour entreprises françaises. Gère écritures PCG, déclarations TVA, IS/IR, clôture annuelle, liasse fiscale (2033/2065), FEC, états financiers, et chaîne facturation (mentions obligatoires, numérotation, Factur-X/UBL/CII, plateformes agréées PDP/PA, e-reporting, réforme 2026…
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
daily-budget-check
Run a daily spend check-in against a daily budget on the Agent Monitor dashboard — today's spend vs the daily target, pace through the day, and the projected overage if the current pace holds. Uses /api/pricing/cost and /api/sessions (grouped by startedat = today). Use for a quick daily spend check-in or a…